RU2789260C1 - Medical decision support system based on medical image analysis - Google Patents

Abstract

FIELD: image processing.

SUBSTANCE: invention relates to the field of image processing, more specifically to a medical decision support system based on the analysis of medical images. A medical decision support system is proposed, comprising: at least one device for obtaining medical images located in a medical organization and configured to form at least one medical image based on a diagnostic study of at least one organ and/or cavity of the examined patient and transmission of said at least one medical image to the data transmission device; at least one data transmission device located in a medical organization and configured to generate data to be processed based on the received at least one medical image and transfer the data to be processed to the central medical information system (CMIS). Moreover, the data to be processed are a package containing at least two medical images; CMIS configured to receive at least one packet from at least one data transmission device, change the size and content of said at least one packet depending on the requirements and / or capabilities of at least one device for determining the pathology and transmitting at least at least one modified package to at least one pathology device; and by at least one device for determining the pathology, configured to extract said at least one medical image from the received at least one package, determine whether there is in the said at least one organ and/or cavity of the examined patient on the mentioned at least one pathology in a medical image, generating a report that contains at least one file containing an indication of the presence or absence of pathology, and transmitting the report at CMIS. Moreover, the definition of pathology is performed using a neural network previously trained for this type of diagnostic study. Moreover, the result of determining the pathology is intended to support the adoption of a medical decision on the state of the said at least one organ and/or cavity of the examined patient and/or on the treatment of the examined patient.

EFFECT: invention provides the possibility of making a medical decision with increased accuracy, increasing the availability and quality of care medical services, reducing the requirements for the personnel of medical organizations performing diagnostic tests, and for the devices included in the system.

41 cl, 9 dwg

Description

The field of technology to which the invention belongs

The present invention relates to the field of image processing, and more specifically to a medical decision support system based on medical image analysis.

State of the art

In the traditional methods of diagnosing pathologies of the chest organs, which have been used in medicine for decades, the operator of the X-ray unit or the doctor visually examined the X-ray image obtained by the unit and made a conclusion about the presence or absence of this or that pathology in the examined patient.

However, the high prevalence of cancer, heart and lung diseases, as well as the outbreak of Covid-19, which has led to a significant increase in mortality from these diseases, entail huge social costs. In medical institutions that carry out diagnostic and therapeutic activities, there is an overload and shortage of qualified medical specialists in the field of radiological studies, the evaluation and interpretation of the results of radiological studies is influenced by the human factor, there are no necessary resources for re-reading studies. The practice of carrying out diagnostic measures is associated with the risk of missing pathologies in the initial analysis of radiological studies.

These factors require fundamental research in this area in order to develop new and more effective therapeutic and diagnostic tools, including in order to improve the quality of medical decisions and, if possible, speed up the process of making medical decisions.

All this contributes to the introduction of modern digital data processing techniques into medicine. The digitalization of healthcare is accompanied by a rapidly growing volume of digitized medical information about patients, clinical databases and medical data sets that could be used to support medical decision-making. In recent years, artificial intelligence (AI) technologies have been increasingly used to work on such tasks.

For example, in known modern AI diagnostic methods such as WO 2021/031279 A1 or WO 2021/091661 A1, a neural network that has been previously trained on a labeled set of images receives a digitized x-ray image of a patient's chest, analyzes it, and makes a prediction about whether whether a given patient has a pathology, thereby helping the doctor to make an optimal informed decision.

Attempts are being made to apply a variety of neural network architectures, different training methods and different methods of image preprocessing, however, the accuracy of known methods is such that a significant part of the medical community is of the opinion that at the current level of development, such systems do not help the doctor, but rather interfere, because they may reduce the concentration of a specialist who relies partly on AI, and there may be errors in decision-making, which can affect the quality of medical services. And due to the fact that the responsibility for the decision lies with the person, the human factor is still great and labor costs and qualification requirements are high.

In this regard, in scientific and technical publications, the opinion has recently begun to form that it is necessary to use some additional data about the patient in addition to images. However, at the moment there were no specific methods and systems that would allow such processing to be carried out with high accuracy with minimal requirements both for the additional data themselves and for the devices that process such data.

The essence of the invention

In order to overcome at least some of the aforementioned shortcomings of the prior art, the present invention is directed to improving the efficiency of medical decision support systems based on the analysis of medical images.

According to the present invention, a medical decision support system is provided, comprising:

a device for obtaining medical images located in a medical organization and configured to generate at least one medical image based on a diagnostic study of at least one organ and/or cavity of the examined patient and transfer the said at least one medical image to the data transmission device;

a data transmission device located in a medical organization and configured to generate data to be processed based on the received at least one medical image and transmit the data to be processed to the device for determining the pathology; And

a device for determining pathology, configured to extract said at least one medical image from the received data to be processed and determine whether there is a pathology in said at least one organ and/or cavity of the examined patient on said at least one medical image,

moreover, the definition of pathology is performed using a neural network previously trained for this type of diagnostic study,

moreover, the result of determining the pathology is intended to support the adoption of a medical decision about the condition of the said at least one organ and/or cavity of the examined patient and/or about the treatment of the examined patient.

In one embodiment, the system further comprises a viewer located in a healthcare facility and configured to receive a pathology determination result from the pathology determination device and present the pathology determination result in a human-viewable form.

In one of the embodiments, the system further comprises a storage located in a medical organization and configured to store said at least one medical image generated by a device for obtaining medical images, data to be processed, generated by said data transmission device, and/or a pathology determination result. from a pathology device.

In one of the embodiments, the system further comprises a medical information system located in a medical organization, and the storage and data transmission device are part of the medical information system.

In one embodiment, the data to be processed contains said at least one medical image.

In one of the embodiments, the data to be processed additionally contains additional target information containing information about the patient, about the study, about the medical organization and/or about the medical specialist who conducted the study.

In one embodiment, the data to be processed further comprises a unique image identifier corresponding to each of said at least one medical image,

wherein the pathology detection result obtained by the pathology detection device after processing said at least one medical image contains a unique image identifier corresponding to the image.

In one embodiment, the data to be processed is depersonalized.

In one embodiment, the data to be processed is a packet containing a plurality of medical images,

moreover, the data transmission device is additionally configured to transmit the said packet upon reaching predetermined packet parameters or in time.

In one of the embodiments, the system further comprises a central medical information system (CMIS) configured to receive data to be processed from said data transmission device of a medical organization and transmit them to a device for determining pathology.

In one of the embodiments, the data to be processed, generated and transmitted by the data transmission device of the medical organization to the CMIS, are non-depersonalized,

moreover, the CMIS is additionally configured to depersonalize the data to be processed.

In one embodiment, the pathology detection device is further configured to:

visualization of at least one area on the image, presumably containing a pathology, if it is determined that there is a pathology in the mentioned at least one organ and/or cavity of the examined patient on the processed medical image; And

generating a report containing an image with visualization of the pathology.

In one embodiment, pathology imaging is performed on an image that is a copy of a corresponding image in which pathology is identified.

In one embodiment, the pathology detection device is further configured to:

formation of a text protocol of the study, containing at least one of: the identifier of the original image, the result of determining the pathology in numerical or text format, the time of obtaining the data to be processed, the time of obtaining the result of determining the pathology, the time of generating the study protocol, information about errors that occurred during the work devices; And

generating a report containing a text protocol of the study.

In one embodiment, the system further comprises expert equipment configured to:

receiving a pathology detection result from the pathology detection device;

providing the result of determining the pathology and the corresponding medical image to the user of the expert's equipment;

receiving input from the user to form a medical report containing a medical decision about the state of said at least one organ and/or cavity of the examined patient and/or about the treatment of the examined patient.

In one embodiment, the user of the expert equipment is a specialist of an expert organization or an external radiologist, who makes medical conclusions using the results of the operation of the pathology device and/or performs the function of an expert or consultant.

In one of the embodiments, the system contains a plurality of expert equipment, the users of which are a plurality of specialists from expert organizations or external radiologists,

moreover, different specialists of expert organizations or external radiologists perform the interpretation of different types of studies.

In one embodiment, the system comprises a plurality of medical organizations and a plurality of devices for determining pathology,

and one or more medical organizations are served by one or more different devices for determining the pathology.

In one of the embodiments, the same medical image from one medical organization is transmitted for processing to different devices for determining the pathology, which have different operating principles and/or are trained on different data sets.

In one embodiment, medical images obtained from different types of examinations from one medical organization are transferred for processing to different devices for determining the pathology, designed to process the corresponding types of examinations.

In one of the embodiments, the system further comprises a CMIS configured to:

receiving data to be processed from a data transmission device of a medical organization;

transmitting the data to be processed to the pathology detection device;

receiving a pathology detection result from the pathology detection device;

transferring the result of determining the pathology to the equipment of the expert;

obtaining a medical report formed using the expert's equipment;

transfer of the medical report to the organization or person requesting the processing of the relevant medical image.

In one of the embodiments, the CMIS is additionally configured to:

storage of medical images;

storage of personal data of patients;

depersonalizing at least a portion of the data to be processed prior to transmission to the pathology device; And

adjusting the amount and type of personal data to which the user of the CMIS is granted the right to access, depending on his level of access.

In one of the embodiments, the CMIS is additionally configured to:

receiving a request for drawing up a conclusion regarding the result of determining the pathology; And

transferring the result of determining the pathology to the equipment of the expert in response to receiving a request for drawing up an opinion,

and the request for the conclusion contains the task of interpreting the medical image and / or the result of determining the pathology, which is allowed to be performed on their own initiative by any one or more experts with the appropriate level of access to the CMIS, or which must be performed by a specific one or more experts;

and/or

receiving an image processing request for the medical image; And

transmitting the data to be processed containing the medical image to the pathology detection device in response to receiving an image processing request,

wherein the image processing request comprises a pathology detection task on the corresponding medical image, which any one or more pathology detection devices capable of processing medical images of the corresponding type can perform on its own initiative, or which a specific one or more pathology devices must perform.

In one embodiment, the request for a report or request for image processing comes from the medical organization that received the corresponding medical image, from the medical organization or person requesting image processing, from the CMIS itself, from a pathology device, or from an expert.

In one of the embodiments, the implementation of the CMIS is configured to generate requests for the preparation of an opinion, taking into account one or more of:

- working hours of the expert or the time interval during which the expert is ready to accept requests;

- the number of requests that have already been issued to the expert, but have not yet been processed;

- the minimum number of requests that the Expert Advisor is ready to accept at the same time;

- the total number of requests already processed by the expert, and requests that are assigned to this expert, during working hours;

- the number of opinions issued by the expert for the last period of time.

In one of the embodiments, the CMIS is configured to generate requests for image processing, taking into account one or more of:

- the time interval during which it is allowed to send requests to one or another device to determine the pathology;

- the number of requests that have already been issued to the device for determining the pathology, but have not yet been processed;

- the minimum number of requests that can be simultaneously processed by the device for determining the pathology;

- the total number of requests already processed by the device for determining the pathology, and requests that are assigned to this device for determining the pathology, for a predetermined period of time;

- the number of results generated by the given pathology device in the last predetermined period of time.

In one embodiment, the CMIS is configured to organize inference requests and/or image processing requests on a first-come, first-served basis.

In one of the embodiments, requests for drawing up a conclusion and requests for image processing have priority set by the medical organization that received the corresponding medical image, from the medical organization or the person who requested image processing, automatically by the CMIS itself, automatically or manually by the CMIS operator, the device for determining pathology or an expert.

In one embodiment, the priority is set based on one or more of:

- features of ongoing research,

- the profile of the organization that conducted the study,

- the patient's condition,

- the requirements of the organization or person who requested the processing of the image or the drawing up of an opinion,

- the deadline for the provision of medical services.

In one of the embodiments, the CMIS is additionally configured to:

grouping pending images into packets for transmission to a pathology device.

In one of the embodiments, the CMIS is additionally configured to:

receiving, from one or more data communication devices, one or more packets containing a plurality of images to be processed; And

changing the size and filling of packages depending on the requirements and/or capabilities of one or more devices for determining the pathology.

In one of the embodiments, the CMIS is additionally configured to validate and/or pre-process the data to be processed.

In one embodiment, the validation comprises one or more of the following checks:

- is it possible to extract an image from the data to be processed;

- whether the data attached to the request for image processing correspond to the request itself;

- whether the image is positive or negative;

- whether the image has a size equal to or greater than a predetermined minimum size supported by at least one of the pathology devices capable of processing this type of examination;

- whether the data to be processed is depersonalized;

- whether the unique identifier of the image has a predefined format.

In one embodiment, the preprocessing of the data to be processed comprises one or more of the following operations:

- converting the image to positive or negative;

- cropping the image in accordance with the area of interest pre-set in the image parameters by the medical specialist who conducted the study;

- conversion of brightness or color of the image;

- image compression to the required size;

- depersonalization of the data to be processed;

- converting the unique image identifier into a predetermined format supported by one or more pathology devices.

In one of the embodiments, the CMIS is additionally configured to:

storing at least one data set containing properly labeled medical images,

moreover, the markup contains an indication of the presence or absence of pathology.

In one embodiment, at least one dataset is for training one or more pathology devices.

In one embodiment, the implementation of at least one data set contains personal data of patients.

In one embodiment, the implementation of personal data of patients contains the sex and age of patients.

In one embodiment, the CMIS is further configured to transmit at least one set of data to the pathology device for learning purposes without depersonalization with respect to those personal data needed to train the pathology device.

In one of the embodiments, the CMIS is additionally configured to:

analysis of medical reports compiled by experts;

extracting from medical reports information about the presence or absence of pathology and the nature of the pathology, if any; And

generating at least one set of labeled medical images based on the extracted data.

In one of the embodiments, the CMIS is additionally configured to:

supplementing the markup of the generated marked up medical images with the corresponding personal data of the patient stored in the CMIS.

In one embodiment, only medical opinions prepared by experts whose skill level or rating is above a predetermined threshold are analyzed.

In one embodiment, at least one data set contains for each patient at least two medical images of the same area taken at different time periods.

In one embodiment, every at least two medical images for each patient are labeled, and the data set containing them is designed to train one or more pathology devices to ignore individual patient characteristics that should not be considered pathology, as well as track changes that occur. in the patient's body in dynamics.

In one embodiment, the pathology detection device is configured to request previous medical images from the CMIS of the analyzed area of the patient depicted in the particular image being analyzed.

Technical result

The present invention improves the efficiency of medical decision support systems based on the analysis of medical images. This provides:

- improving the accuracy of determining pathologies;

- no need to process and transfer additional data about the patient in the process of direct operation of the system;

- acceleration of data processing compared to systems that, in addition to transferring the medical image itself, require the processing and transfer of additional data about the patient in the process of direct work;

- reducing the load on data networks and on the medical decision support system in general and its components;

- ensuring increased confidentiality of the study, since only a depersonalized image is transmitted over the network;

- simplification of the definition of pathologies compared to systems that require the processing and transmission of many types of additional data about the patient;

- reduction of requirements for the qualification of medical personnel;

- reducing the influence of the human factor (mindfulness, fatigue, responsibility);

- reducing the requirements for device performance and the corresponding reduction in costs and power consumption, the possibility of reducing the size of devices;

- reduced requirements for devices that process additional data.

It should be understood that not each of the embodiments can simultaneously provide all of these advantages over all known prior art solutions. Accordingly, some embodiments may have only some of these advantages or other advantages over some known solutions.

These and other advantages of the present invention will become apparent upon reading the following detailed description with reference to the accompanying drawings.

Brief description of the drawings

On FIG. 1 shows a schematic representation of a medical decision support system according to the present invention.

On FIG. 2 shows an example of an image to be processed in a pathology detection device.

On FIG. Figures 3 and 4 show examples of images that should not pass validation.

On FIG. 5 shows a block diagram of a pathology device according to the present invention.

On FIG. 6 and 7 show example images for patients at different ages.

On FIG. 8 shows an example of an image on which regions of interest are plotted as a heat map.

On FIG. 9 shows an example of an image on which the contours of the regions of interest are plotted.

It should be understood that the figures may be represented schematically and not to scale and are intended primarily to improve understanding of the present invention.

Detailed description

General overview of the system

Next, with reference to FIG. 1, the medical decision support system 100 will be generally described.

The medical organization (MO) 110 contains a device 120 for obtaining medical images. Medical images can be, for example, x-ray images, MRI (magnetic resonance imaging) images, CT (computed tomography) images, and other images obtained by radiological (i.e. using radiation) or non-radiological (i.e., using a camera) methods. diagnostics. A medical image may also be referred to as a diagnostic image. Accordingly, the apparatus 120 may be an X-ray imaging apparatus (also may be referred to interchangeably as an X-ray diagnostic apparatus, an X-ray machine, an X-ray machine, an X-ray, etc.), a fluorographic imaging apparatus, an MRI imaging apparatus, a device for obtaining CT images; and the like. Hereinafter, solely for convenience of description, an x-ray machine may be referred to as the medical imaging device 120, however, the above information and other possible embodiments of the present invention should be taken into account.

The medical specialist, using the device 120 for obtaining medical images, performs a diagnostic examination of the organs of the examined patient. Further in this document, solely for the convenience of description, chest X-ray examination may be mentioned as an example of a diagnostic examination, however, it should be understood that in other embodiments of the implementation of the present invention, it is possible to conduct an MRI examination, a CT examination, etc., and organs to be examined may be any organs and cavities that can be examined using a device for obtaining medical images.

As a medical organization 110, according to the present invention, there can be a clinic, a polyclinic, a doctor's office, a hospital, a hospital, a hospital, a sanatorium, a medical care center, a pharmacy, a mobile unit, a mobile fluorography room, or any other organization, room or installation equipped with device 120 for obtaining medical images.

The result of the study is formed in the form of a medical image, for example, in the format of DICOM (Digital Imaging and Communications in Medicine), NIfTI (Neural Imaging Technology Initiative in Informatics), Analyze, Minc1, Minc2, or other suitable open or proprietary format. The medical specialist, if necessary, can apply filters to the image before saving, which, in his opinion, can improve the perception of the image. In addition, the image can be superimposed in one of the embodiments of any preset filters that are specific to a particular device or to a particular manufacturer.

The generated image is stored in a local data store 131, such as a store based on or as part of a PACS (DICOM image archiving and transmission system), RIS (radiological information system), MIS (medical information system) 130, or other system or device suitable for storage of medical data. If necessary, additional target information can be added to the saved image, such as information about the patient, about the study, about the medical organization, about the medical specialist, etc.

MIS 130 (including PACS or RIS) can be deployed on a general purpose computer or server, on specialized equipment, or on other data storage, processing and transmission hardware suitable for implementing the present invention and known to a person skilled in the art. In an illustrative non-limiting example, MIS 130 may be a computer having a 4-core processor, 8 GB of RAM, 60 GB disk space for the CentOS 7 operating system, 2 TB disk space for data, 1 TB disk space for the database, and 2 network adapters.

Storage 131 is shown in FIG. 1 as part of HMI 130 by way of example only, and it should be understood that other implementations are possible in which storage 131 is separate from HMI 130, resides within medical imaging device 120, or resides within another internal storage system of a medical organization. Implementations are also possible in which a medical organization does not use special systems for storing and transmitting medical data at all, but uses other available storage and transmission means for these purposes, such as a personal computer or laptop.

The data to be processed is then generated using a data communication device 132 such as PACS, RIS, MIS 130, or other suitable open or proprietary system. As with the storage 131, although the communication device 132 is shown in FIG. 1 as part of MIS 130, it can also be separate from MIS 130 or be part of another internal storage system of a medical organization.

In one of the embodiments, when forming the data to be processed in the data transmission device 132, depersonalization (anonymization, de-identification, depersonalization) of the medical image of the organs of the examined patient can be performed. To do this, patient information, which in one way or another can be considered personal, is replaced with anonymized data, from which a third party will not be able to restore the original data without having proper access to it. For example, in the case of a PACS system, the fields “PatientName” (patient name), “OtherPatientNames” (other patient names), “PatientID” (patient identifier) and, if necessary, other fields containing personal data or related to such, are anonymized.

In one of the embodiments, it may be necessary for the image to have some unique identifier (ID) of the image that does not contain personal data, so that later, upon receiving back data with such an identifier, the MIS 130 or other system or device with proper access to personal data, if necessary, could again compare the obtained data with the corresponding patient. In the illustrative non-limiting example of FIG. 2 identifier has the value "56HJ". Specific methods for generating unique identifiers are known to those skilled in the art and are not the subject of the present invention. In this case, either one separate field or a set of several fields can act as a unique identifier.

The possible values of the depersonalized data and/or the format of the unique identifiers may be predefined and known to all devices in the system, only to trusted devices, or only to the pathology device 160 so that they can determine whether the transmitted data is depersonalized. For example, in the above example in FIG. 2 identifier has the format XXYY, where X is an Arabic numeral and Y is a Latin letter.

The depersonalization process can occur both completely automatically, and if necessary, part of the depersonalization process or the entire depersonalization process can be performed with the participation of a person who can delete or edit data through the appropriate interface of the data transfer device 132 or medical information system 130.

The depersonalized data to be processed, an example of which is shown in FIG. 2 are transmitted from the medical organization 110 directly or through the central medical information system 150 to the device 160 for determining the pathology. At the same time, in one of the embodiments, the implementation of depersonalization can be performed in the central medical information system 150, and in this case, non-anonymized data can first be transmitted from the medical organization 110 to the central medical information system 150, and then depersonalized data can be transmitted from it to the device 160 for determining the pathology. data to be processed. The depersonalization process can occur both completely automatically, and if necessary, part of the depersonalization process or the entire depersonalization process can be performed with the participation of a person who can delete or edit data through the appropriate interface of the central medical information system 150.

The pathology detecting device 160 analyzes the medical image contained in the received data based on artificial intelligence (AI) methods and predicts whether the image contains a pathology. If so, the pathology detecting device 160 indicates areas in the image that contain pathologies. If there is no pathology, then the image does not change.

Optionally, the device 160 for determining the pathology can generate a report (or protocol) on the result of the work, containing a description of the result in the form of textual information.

The generated data (one or more images and/or a report) is sent back (directly or indirectly) from the pathology device 160 to the medical organization 110 that requested data processing.

The results of the work received from the device 160 for determining the pathology are provided to the responsible person, for example, a radiologist, an attending physician or other medical specialist or a person who has access to such information and is responsible for receiving and processing it in a medical organization 110, using a viewer 140 , and using them, he makes a decision about the state of the examined organs, namely the presence or absence of a particular pathology. If necessary, the medical specialist, taking into account the results of the device 160 for determining the pathology, can make a decision on the treatment of the patient. Viewer 140 in FIG. 1 is simplistically referred to as display 140, however, in the preferred embodiment, it is an AWP (workstation) of a physician. In an illustrative non-limiting example, a physician's workstation may be a computer based on an Intel Core i3 processor or equivalent, having 8 GB of RAM, 40 GB of free disk space, a DVD-R/RW CD-ROM drive, a network connection speed of 5 Mbps, monitor with a screen resolution of 1920x1080 and can be viewed using DICOM image viewers or through a web browser.

Thus, the system 100 contributes to improving the accuracy of medical decision making.

It is also possible that the data generated by the device 160 for determining the pathology is not sent directly to the medical organization 110 that requested data processing, but first (directly or through the central medical information system 150) to a specialized expert organization 170 that produces medical reports using the results. operation of the pathology device 160, or to an external radiologist 180 acting as an expert or consultant. In this case, the medical organization 110, in response to the sent medical image, can receive from the expert organization 170 or from the external radiologist 180 (again, directly or through the central medical information system 150) an immediately ready conclusion or a preliminary conclusion that can be used to make a medical decision. This allows to reduce the requirements for qualification and workload of the personnel of a medical organization 110 up to the possibility of not having a radiologist on the staff at all, which provides a significant expansion of the geography of the possible use of the system and allows you to receive highly qualified medical services in those locations where they were not available before. due to the lack of properly qualified personnel, and on the other hand, allows radiologists to connect to the system from various remote locations without being tied to a specific medical organization.

It should be understood that in this document blocks 170 and 180 are simply referred to as "expert organization 170" and "external radiologist 180", however, technically, from the point of view of the system, these blocks are equipment / devices for receiving, viewing, editing and transmitting data managed/owned/used by an expert organization 170 and an external radiologist 180.

According to the present invention, the term "external" in relation to a radiologist means that this doctor is not on the staff of the medical organization 110 that performed the x-ray examination and requested the processing of the resulting image, and / or is not physically located in this organization and / or does not have access to MIS 130 of this organization. In addition, it should be understood that the term “radiologist” (radiologist) in the context of the present invention is given in an expansive interpretation, that is, it is understood that this is a medical specialist who has a proven qualification (knowledge, skills, skills and experience) in analysis (interpretation) medical (diagnostic) images, that is, one or more of the following: analysis of X-ray results, analysis of CT results, analysis of MRI results, and the like.

The expert organization 170 may be a medical or other organization endowed with the functions of analyzing medical images and drawing conclusions and having one or more specialists of the appropriate profile and appropriate qualifications for the analysis (interpretation) of medical (diagnostic) images, that is, one or more of the following : analysis of X-ray results, analysis of CT results, analysis of MRI results, etc.

Specialists of the expert organization 170 and external radiologists 180 can access data from a specialized workstation (doctor's workstation) or using another suitable device, such as a computer, laptop, smartphone, tablet, VR helmet (virtual reality helmet), VR -glasses, etc.

On FIG. 1 depicts one medical organization 110, one pathology device 160, one expert organization 170, and one external radiologist 180 for simplicity, however, it should be understood that other embodiments are possible. For example, in one embodiment, the medical decision support system 100 may comprise multiple medical organizations 110 served by a single pathology device 160. In general, one or more healthcare organizations 110 may be served by one or more different pathology detection devices 160.

At the same time, the medical organization 110 can send the same image to different devices 160 to determine the pathology, if they have different operating principles and / or are trained on different data sets, and then the medical organization 110 can have several processing results (reports, protocols, preliminary conclusions), which is somewhat analogous to a consultation and can increase the accuracy of making a medical decision.

In addition, the medical organization 110 can send different images to different devices 160 to determine the pathology. In particular, this can be handy if they specialize in different types of research. For example, one pathology detection device 160 is for detecting pathologies of the thoracic organs, and the other is for detecting pathologies of the spine. This provides an extension of the functionality of the medical decision support system and the ability of a medical organization to receive a full range of services for processing and analyzing diagnostic tests within a single medical decision support system without the need to integrate with many different systems in order to receive services in different areas of research. In addition, developers and suppliers of pathology devices 160 may not seek to cover all possible types of examinations in an attempt to meet all the requirements of the medical decision support system 100, but rather concentrate on those types of examinations in which they have the greatest competence, which in terms of The system provides an increase in the accuracy and quality of services for each of the individual types of studies.

Likewise, different expert organizations 170 and different external radiologists 180 can specialize in exactly the types of examinations in which they have the greatest competence, which from the point of view of the system provides an increase in the accuracy and quality of service delivery for each of the individual types of examinations.

The central medical information system 150 shown in FIG. 1, an expert organization 170 or an external radiologist 180 are not required elements of the proposed medical decision support system 100. Accordingly, in one embodiment, the implementation of the medical organization 110 may communicate directly with the device 160 to determine the pathology. This provides a simplified implementation of the medical decision support system 100 . Such an implementation can be convenient, for example, in cases where the number of medical organizations 110 served by the pathology device 160 is relatively small, and expert organizations 170 or external radiologists 180 are not involved at all or their number is also relatively small.

In another embodiment, when the medical decision support system 100 includes a plurality of medical organizations 110 and/or a plurality of pathology devices 160, as well as expert organizations 170 or external radiologists 180, it is advisable to use a central medical information system 150. It should be noted that the term “central” in this case indicates, first of all, not that this is a single central server that closes all possible connections, but that the central medical information system 150 occupies a place in the middle, in the center between the other participants in the medical decision support system 100, acting as an intermediate system for collecting, storing and redistributing data. In this case, depending on the requirements of a particular application, the central medical information system 150 can be both concentrated (centralized) and distributed, including those implemented in the cloud.

The central medical information system 150 may include a plurality of data storage and processing devices. In one embodiment, the owner of the entire central health information system 150 as a whole may be a government entity, municipality, authorized body or operator, or other government or non-government commercial or non-profit entity or organization. In another embodiment, individual devices within the central health information system 150 may belong to different owners - for example, in different cities, different organizations (local operators) may provide their server equipment for use as data storage and processing devices, and a common operator may perform the functions supervision and regulation. If necessary, participants in the central medical information system 150 may be required to obtain a license for the right to work within this system and / or the right to access personal data and their storage and processing.

It has been described above that the result of operation of the pathology device 160 can be sent to an expert organization 170 or to an external radiologist 180, however, another embodiment is also possible in which such a result is only sent to the central medical information system 150, stored in it and is marked as a preliminary result requiring the opinion of a specialized medical specialist. In the future, on their own initiative (for example, to the extent possible, if there is free time, if necessary to gain experience and practice, etc.) or upon request, expert organizations 170 or external radiologists 180 with appropriate access rights, access to central medical information system 150, download preliminary results requiring a conclusion to their devices, perform analysis, draw up a conclusion and send a conclusion to the central medical information system 150, or, without downloading, view such preliminary results through their devices directly in the user interface of the central medical information system 150 and draw conclusions directly in this interface. By loading the results here is meant saving the corresponding files in the permanent memory of the device on the side of the expert organization 170 or an external radiologist 180 for further opening these files from the permanent memory.

The term "request" according to the present invention encompasses both a task that can be performed on its own initiative by any doctor or expert organization with an appropriate level of access, and a task that a specific expert organization 170 or a specific external radiologist 180 must perform.

Hereinafter, in some cases, for ease of description, the expert organization or external radiologist may be replaced by the single term “expert”. Accordingly, equipment/devices for receiving, viewing, editing, processing and transmitting data that is managed/owned/used by the expert organization 170 or external radiologist 180 may be referred to as expert equipment/device.

The request for a report may come from, for example, the medical organization 110 that originally requested the image processing, from the central medical information system 150 itself, or from the pathology device 160. In one of the embodiments, the request for data processing and / or the preparation of a conclusion may not be the medical organization in which the diagnostic study was performed, but some other organization or person. This may be applicable, for example, when the user or owner of the device 120 for obtaining medical images is one medical organization, and the conclusions on the images received by this device are compiled by an expert organization 170 or an external radiologist 180 and sent directly to the customer. This reduces the skill requirements for medical professionals using medical imaging devices 120 and expands the geography of the use of such devices, which increases the availability of quality medical services.

In addition, if one expert has difficulty in drawing up a conclusion or doubts its accuracy, then he can re-mark the current result as a preliminary result requiring a conclusion and / or send a request to another expert. This approach allows you to get a consolidated opinion on complex cases, which increases the accuracy of medical decisions and the quality of medical services.

The moment of issuing a request for an opinion may be different. As mentioned above, the request can be generated immediately when generating the result of the device 160 to determine the pathology that requires a conclusion. This approach can increase the speed of processing preliminary results and obtaining conclusions, and thereby improve the quality of medical services.

In another embodiment, it may take into account the fact that requests for analysis of each individual preliminary result, which come to many experts irregularly during the day, may cause inconvenience, anxiety and overwork, and may also have a negative impact on other work performed by this expert. To avoid these shortcomings, when generating requests to an expert, his working hours or the time interval during which this expert is ready to accept requests can be taken into account. In addition, the current load can be taken into account, that is, the number of requests that have already been issued to this Expert Advisor, but have not yet been processed. If the threshold of current requests for this Expert Advisor is reached or exceeded, new requests may not be issued to it. It can also take into account the minimum number of requests the Expert Advisor is ready to accept at the same time. To do this, preliminary results that require a conclusion can be accumulated, and when the threshold of simultaneous requests for a given expert is reached, they can be sent to this expert immediately as a package. In addition, the total workload of an expert can be taken into account, that is, the total number of requests already processed by this expert, and requests that are assigned to this expert, during working hours. If the total load threshold for a given expert is reached or exceeded, new requests may not be issued to it in order to reduce the likelihood of an error due to image analysis by a tired expert. In addition, the current performance of an expert can be taken into account, that is, the number of conclusions issued by this expert over the last period of time, and when the performance threshold is reached, in order to avoid a decrease in concentration, new requests may not be issued to him until, at the next time, during the next recalculation of performance it will not fall below the threshold again. All these measures help to ensure that the expert will perform image analysis and report with due attention and responsibility and without fatigue, as well as to ensure the flexibility of the system and the possibility of participation in it by many customers and performers.

Review requests may be stored in the central health information system 150, for example, in a first come first served basis such as FIFO (First In First Out), priority queue or other processing queue.

When the expert organization 170 or the external radiologist 180 accepts one or more requests for work, the corresponding requests can be removed (removed) from the queue to avoid duplication and the same work by different experts. In another embodiment, one or more preliminary results may initially be intended for analysis by a predetermined number of two or more experts, and then the corresponding request in the queue may contain a counter reflecting how many experts have accepted this request. When the counter reaches the required preset number, the corresponding request is removed from the queue.

Accordingly, as requests are added to the queue, as requests are removed from the queue, as requests are accepted for work by a particular expert, with a certain frequency, in a combination of the above or in any other suitable way, the above-mentioned loading parameters can be recalculated for an individual expert or for all experts.

In one embodiment, the priority of opinion requests may be set by the medical organization 110 itself requesting image processing. In another embodiment, the priority of opinion requests may be set automatically by the central medical information system 150 in accordance with the profile of the medical organization 110 requesting image processing. In yet another embodiment, the priority of opinion requests may be set manually by the user acting as the operator of the central medical information system 150. obtain an opinion on such a study may be equal to 1, and the required expert qualification may be the lowest. Otherwise, if the study is carried out in an urgent mode and there is a question of life and death of the patient, and the doctor who performed the study needs immediate assistance from colleagues, such a request may be assigned the highest priority, the number of experts from whom it is required to obtain an opinion on such a study , may be 2 or more, and the required qualification of experts may be the highest. Of course, other, intermediate options are also possible, depending on the characteristics of the studies being conducted, the profile of the organization and the patient's condition. It is not practical to describe all possible options, since they should be clear to a person skilled in the art based on the principles of the present invention. Thus, the quality of medical services is improved.

In one embodiment, the implementation may take into account the deadline for the provision of medical services, and as this deadline approaches, the priority of the corresponding request for a conclusion can increase. However, given the importance of certain types of studies and services, each study may have an appropriate priority limit depending on the nature of the studies being conducted, the profile of the institution, and the patient's condition. For example, even an overdue fluorography of a healthy person cannot be more important than a picture of a person lying in a hospital bed, who will have an operation in half an hour. In this case, priorities can be implemented, in particular, in the form of weighting factors - for example, a weighting factor of 1 can correspond to the highest priority, and initially the lowest priority request can have a weighting factor ranging from 0 to 0.5, etc. . This allows to increase the timeliness of the provision of medical services while maintaining their high quality.

In addition, when new studies requiring processing are added to the central medical information system 150, the priority initially set by the medical organization 110 requesting processing can be adjusted automatically by the system 150 itself or manually by its operator in accordance with the characteristics of the studies being conducted, the profile of the organization, the patient's condition, the date the conduct of the study and the deadline for the provision of medical services. Thus, if the study is not urgent, then it eliminates the need to send it to the central medical information system 150 as soon as possible after receiving the image in an attempt to get an early place in the queue in order to receive an early conclusion, and instead provides the ability to download studies at a time in batches - for example , once an hour or at the end of the working day. This allows you to regulate and plan the traffic and the number of simultaneous connections to the central medical information system 150, which increases the rational use of time resources, traffic and performance resources of the central medical information system 150 and other devices in the medical decision support system 100 while maintaining high timeliness and quality of services provided. medical services.

Just as requests for reporting on preliminary results from pathology devices 160 are generated, queued, and processed by the central medical information system 150, expert organizations 170, and external radiologists 180, device requests can be generated and queued. 160 to determine pathology to process images from healthcare providers 110. Pathology devices 160 may perform image processing on a specific request or poll the central health information system 150 for pending image processing requests that the device is capable of processing. In addition, depending on the load of the devices 160 to determine the pathology and their requirements, the central medical information system 150 can adjust the number and time of sending requests for image processing. Also, image processing requests may be prioritized in a manner similar to that described above for opinion requests, where applicable to pathology devices 160.

Images awaiting processing may be grouped into batches (series) for transfer to the device 160 for determining the pathology. Accordingly, the pathology detecting device 160 can perform batch processing of the received images. Grouping into packages can be performed both in the medical organization 110 and in the central medical information system 150. The central medical information system 150 can change the size and content of the packages received from the medical organizations 110 - for example, sort images by their resolution in pixels, by priority or other parameters and form new packages, and if necessary, images from different medical organizations 110 can be added to the same package.

In one embodiment, central health information system 150 may perform primary validation or pre-processing of images. Also, primary validation or pre-processing is possible on the side of the medical organization 110.

In particular, an attempt may be made to extract an image from the data to be processed. If the attempt fails, then it is concluded that the image file is corrupted or cannot be read. The reason for this may be factors such as the absence of an image in the data, the impossibility of reading metadata, the presence of any anomalous and unaccounted for tag values, etc. In this case, the data is not transferred for processing, and a corresponding indication is created for it.

A check may be made whether the data attached to the image processing request matches the request itself. For example, if the request specifies that a AP chest x-ray is to be processed, a check can be made to see if the attached data contains a AP chest x-ray. Various implementations of such a check are known to those skilled in the art and may include, for example, a pre-trained neural network (neural network) that produces the appropriate classification, or other computer vision methods. If the check fails, then such data is not transferred for processing, and a corresponding indication is created for it. Examples of such errors, when the study is claimed to be an X-ray of the chest in a direct projection, but in fact it is not and cannot be processed, are shown in Fig. 3 and 4.

In addition, a check can be made whether the image is a positive or a negative. Various implementations of such a check are known to those skilled in the art and may include, for example, a pre-trained neural network (neural network) that produces the appropriate classification, or other computer vision methods. If the inspection reveals that the image does not meet the input requirements of the pathology device 160, an appropriate conversion of the image to negative or positive can be performed.

If a region of interest (VOI) is predefined in the image parameters by the examiner, appropriate image cropping (VOI LUT) can be performed to obtain an image containing only the region of interest. For example, if the medical specialist who performed the chest x-ray has specified an area of interest, then according to the parameters embedded in the image, cropping is applied, as a result of which only the lung region remains on the image.

It can also be checked if the image has a size (pixel resolution) equal to or greater than a predetermined minimum size supported by at least one of the pathology devices 160 capable of processing this type of examination. For example, the received initial chest X-ray image requiring processing has a size of 800x800 pixels, and the medical decision support system 100 contains three pathology devices 160 capable of processing this type of examination, of which two devices support a minimum input image size equal to 1024×1024 pixels, and the third device supports a minimum size of 512×512 pixels. Accordingly, a request for processing the received image will only be sent to the third device 160 for determining the pathology. If the original image has a size less than the minimum supported by at least one of the devices 160 to determine the pathology, then such an image is not transmitted for processing, and a corresponding indication is created for it. This improves the accuracy of image processing and reduces the possibility of errors and the need to reanalyze some images by different devices 160 to determine the pathology, and thereby improve the quality of medical services.

If the pathology device 160 that accepts the image processing request requires certain input image parameters, then the central medical information system 150 or the medical organization 110 itself (for example, when the medical decision support system 100 does not contain the system 150 or if the system 100 contains only one pathology device 160 capable of processing this type of examination) can perform image preprocessing. In particular, in one of the embodiments, the conversion of the brightness and chrominance of the original image can be performed. For example, the color depth of the original image may be 12-16 bits, and as a result of the conversion, an image with a color depth of 8 bits may be obtained. In another embodiment, the image may be compressed to a desired size. Various compression methods known to those skilled in the art are applicable, so a detailed description of the compression process will not be given here.

The above functions of primary validation and pre-processing make it possible to increase the flexibility and adaptability of the medical decision support system to the various technical capabilities of the system participants, which ensures a high degree of scalability and the ability to participate in the system as many participants as possible, which increases the availability of high-quality medical services.

In addition, the central health information system 150 can check whether the data to be processed is depersonalized. To do this, it is checked whether the fields that relate to personal data contain any values, and if so, whether these values are depersonalized. For example, if the "PatientName" field is blank or contains the predefined value "0" or "Anonymous" as indicated in FIG. 2 and FIG. 4, this field is considered to be depersonalized, and the field with the value "Venus de Milo" indicated in FIG. 3, is not depersonalized. Unverified data may be depersonalized by the central health information system 150 prior to generating a data processing request or a report request.

In the case of using unique identifiers, a check can also be made whether the unique image identifier has a predetermined format. For example, if the image ID is to be strictly in XXYY format, then the image ID of FIG. 2 having the value "56HJ" will pass the test, and the image IDs of FIG. 3 and 4 with values "0" and "C3PO" will fail the test. Identifiers whose format does not meet the requirements can be converted by the central medical information system 150 before generating a request for data processing or a request for drawing up an opinion, or the corresponding data is not transferred for processing and an indication of the impossibility of processing is generated.

It should be noted that the pathology device 160 or the expert judgment device may support several different allowable values of depersonalized data and unique identifier formats, in which case the central medical information system 150 may check whether the values of the fields in the received data match. and the format of the received image identifier to at least one of the corresponding supported values and formats of the given device 160 for determining the pathology or the device of the expert, ready and able to accept the request for work. If the value does not match a predetermined valid value or the image identifier is not in the correct format, then the central health information system 150 may perform data reduction to those depersonalization requirements that are supported by the pathology device 160 or the examiner device.

The above functions of depersonalization make it possible to increase the flexibility and adaptability of the medical decision support system to the various technical capabilities of the system participants and significantly reduce the requirements for the system participants related to the processing of personal data, which ensures a high degree of scalability and the ability to participate in the system as many participants as possible, which increases the availability of high-quality medical services.

In one of the embodiments of the present invention, the central medical information system 150 can store not only those medical images that require analysis and conclusion, but also training datasets containing properly labeled medical images that are intended, among other things, for training one or more devices 160 for determining pathology, namely for training their embedded neural networks and/or computer vision algorithms. Thus, there is a single archive of training datasets that can be accessed by each of the multiple pathology devices 160 included in the medical decision support system 100, without the pathology devices 160 themselves having to separately store, maintain, update, and replenish their training datasets, as well as look for other third-party sources of training data. This reduces the requirements for system participants, which ensures a high degree of scalability and the ability to participate in the system as many participants as possible, which increases the availability of high-quality medical services.

Moreover, the same single archive of training datasets can be accessed by medical professionals, researchers and students from any location, if necessary, for example, for the purpose of education, research, search for images with similar pathology, etc. This improves the quality and accessibility of education, the quality of medical services and the availability of high-quality medical services.

In yet another embodiment of the present invention, the central medical information system 150 may store training datasets in which the medical image markup contains patient personal data such as name, gender, age, and so on. Each person, device, or system accessing the system has an access level assigned to them, and depending on the access level of a particular user, central medical information system 150 adjusts the amount of data that user can view. For example, a user with a low level of access can view the images themselves, and from their description (markup) has access only to the description of the pathology, if any. A researcher, for example, can access the sex, age, and comorbidity information of patients, if any, to conduct a study, but does not need to know the patient's name, so the central medical information system 150 does not show him the names of the patients. At the same time, the attending physician or expert preparing the opinion, having received a high level of access, can search the archive for previous images of a particular patient, entering, for example, his name or medical policy number, and the central medical information system 150 provides in response to such search for all archived images of a given patient. An implementation is also possible in which the central medical information system 150 provides all archived images of a given patient without using personal data, but simply in response to a request to provide previous images of the patient depicted in a particular image being analyzed or viewed by the user. Thus, the quality and accessibility of education, the quality of medical services and the availability of high-quality medical services are increasing.

Moreover, one or more pathology devices 160 may also access all or part of the personal data contained in the markup. If such data is needed by the pathology device 160 only for the purpose of training its neural networks and/or computer vision algorithms, then it is only used in the training process and is not stored. This significantly increases the accuracy of training and pathology prediction, which leads to an increase in the quality of medical services, while reducing the requirements for system participants (for example, in terms of processing and storing personal data), which ensures a high degree of scalability and the ability to participate in the system as the largest possible number of participants, which increases the availability of high-quality medical services.

In a further embodiment of the present invention, the central medical information system 150 can fully automatically or automatically, using input from an operator, analyze medical reports compiled by experts, extract from them information about the presence or absence of pathology and the nature of the pathology, if any, and create on the basis of extracted data labeled medical images. If necessary, the markup can also be supplemented with appropriate personal data of the patient, if the central medical information system 150 has such data. Thus, conditions are created for the constant and large-scale replenishment of training data sets. Due to this, it is possible to improve the accuracy of training and predicting pathology, which leads to an increase in the quality of medical services, while reducing the requirements for system participants (in particular, there is no need to independently replenish training data), which ensures a high degree of scalability and the ability to participate in the system the largest possible number of participants, which increases the availability of high-quality medical services.

In order to increase confidence in the new data that adds to the training datasets, the addition can be made only from the conclusions made by experts whose skill level or rating is above a predetermined threshold. Compared to the previous embodiment, this slightly reduces the speed of replenishment of training data sets, but significantly reduces the likelihood of errors in them, which makes it possible to improve the accuracy of training and pathology prediction, as well as improve the quality of medical services.

In yet another further embodiment of the present invention, a training dataset can be created containing for each patient at least two labeled medical images of the same area taken at different time periods. Thus, the pathology detecting device 160 can learn from such a data set to ignore individual characteristics of patients that should not be considered pathology, and also to track changes in the patient's body over time. Due to this, the accuracy of pathology prediction can be increased, which leads to an increase in the quality of medical services.

In addition, the central medical information system can store for each patient a history of both labeled and unlabeled images of the same area taken at different time periods. At the same time, from the point of view of the amount of data transferred and the performance of work, it may not be advisable to transfer the entire history of images at once for each patient whose current image needs to be analyzed. The pathology detection device 160 may, if necessary, query the central medical information system 150 for previous images of the patient depicted in the particular image being analyzed. For example, this may occur when the pathology detection device 160 detects a pathological probability based on the analysis of the current image is borderline (say, 35-65%, 40-60%, etc.), and the analysis of previous images can help the device 160 to determine the pathology to perform a more accurate prediction. Due to this, without a significant impact on productivity and load on the system, the accuracy of pathology prediction can be increased, which leads to an increase in the quality of medical services.

The structure of the device for determining the pathology

Next, with reference to FIG. 5, the device 200 for detecting pathology based on medical images according to the present invention will be described in detail. It should be noted that the pathology detection device 200 fully corresponds to the pathology detection device 160 shown in FIG. 1, and has the same functions and capabilities, if applicable and does not conflict with the descriptions in this section. In the following, for convenience of description, chest organs may be referred to as the examined organs, and X-ray imaging may be referred to as the medical image, however, it should be appreciated that the principles of the present invention are applicable to other types of examinations, as indicated above in this document.

The pathology determination device 200 includes a data receiving unit 210, a data storage unit 220, a data validation unit 230, an image preparation unit 240, a pathology prediction unit 250, a report generation unit 260, a data transmission unit 270, and a learning unit 280. Depending on the particular application, some of these blocks may be omitted, as will be explained in more detail later in this document.

The data receiving unit 210 receives data to be processed containing a medical image, such as an x-ray image of the chest of a patient being examined. The receiving unit 210 may be a separate chip, network card, or other suitable means capable of communicating with external devices in a wired and/or wireless manner, such as over a local area network (LAN) protocol, the Internet, etc. using Ethernet, fiber, WiFi, 4G, etc. technologies.

The data storage unit 220 stores the data received by the data receiving unit 210 so that other units of the device 200 can use it at the appropriate time. Received data can only be stored while it is being processed and deleted when it is processed. For these purposes, in one embodiment, a short-term storage device such as RAM or the like is used. In another embodiment, the received data may be stored for a longer period of time than the immediate processing time, if necessary, and then a long-term storage device such as a hard disk or the like may be used.

Additionally, the data storage unit 220 may store short-term or long-term data and/or files resulting from or during the operation of other units of the device.

The data validator 230 receives the data to be processed directly from the data receiving unit 210 or retrieves it from the data storage unit 220 . The data validator 230 then checks whether the received data is suitable for processing.

As mentioned above in the description section of the medical decision support system 100, part of the validation operations can be performed on the side of the medical organization itself or on the side of the central medical information system 150. In this case, if the device 200 for determining the pathology knows which validation operations have already been performed with regard to the data to be processed, the data validator 230 may not perform these operations, which can simplify and speed up processing, and thereby improve productivity. However, in another embodiment, the pathology device 200 may not know which validations have already been performed, or it may re-perform them for further revalidation. This can improve the quality of processing.

The specific validation operations have been described above and will not be mentioned here in detail.

Validation allows you to filter out data that cannot be analyzed or the accuracy of processing will have a deliberately low accuracy. Accordingly, the load on the most resource-intensive part of the analysis is reduced and the prediction accuracy is increased. In addition, screening out images that are not depersonalized ensures that no personal data is processed on the device 200 side, which reduces requirements for its implementation and certification.

The image preparation unit 240 receives a validated medical image from the data storage unit 220 and/or from the data validation unit 230 and performs preliminary transformations on it in order to prepare it for direct use in the pathology prediction unit 250 .

In particular, the image preparation performed in block 240 may be as follows.

The medical image to be processed is read and, if necessary, converted to grayscale with a predetermined color depth. The brightness and color parameters of the original image depend on the parameters set by the radiologist when working with the device for obtaining medical images, and are contained in the image metadata. For example, the color depth of the original image may be 12-16 bits. In this case, for example, as a result of reading and converting to an image with a color depth of 8 bits, a matrix of integer pixel values \u200b\u200bfrom 0 to 255 can be obtained. Also, as mentioned above, an appropriate conversion of the image to a negative or positive can be performed.

The initial size of medical images can be relatively large - for example, for x-rays, it averages 2500×2500 pixels, that is, 2500 pixels in height (vertically) and 2500 pixels in length (horizontally). Images in this size are generally amenable to processing using machine learning methods, but such models are very resource intensive.

In addition, the range of sizes of input medical images can be quite large, which can cause inconvenience if you try to process each individual image directly in its original size. In particular, it becomes difficult to choose a set of processing methods that are equally effective for different sizes.

In this regard, before processing large medical images, it is preferable to reduce their size. This allows, without significant loss of quality, to significantly reduce the resources expended: time, computing power, energy consumption. Various methods of size reduction are applicable - for example, compression, cropping (cropping), etc. Compression techniques are known to those skilled in the art, so a detailed description of the compression process is not provided here. As for image cropping, it will be described later.

For example, in one embodiment, if a region of interest (VOI) is predefined in the image parameters by the medical professional performing the study, appropriate image cropping (VOI LUT) can be performed to obtain an image containing only the region of interest. For example, if the medical specialist who performed the chest X-ray indicated the region of interest, then according to the parameters “embedded” in the image, cropping is applied, as a result of which only the lung region remains in the image.

In another embodiment, in addition to or instead of the aforementioned VOI LUT cropping, a search for a region of interest in an image is performed and the image is cropped by cutting off parts of the image that are not included in the found region of interest. For framing purposes, computer vision algorithms can be used that are trained to search an image for a region of interest that includes only the region delimited by the organs or cavities to be analyzed.

The aspect ratio of the cropped image depends on the size and shape of the organs or cavities to be analyzed. For further processing, it is required to bring it to a single format. To do this, the image is resized to the second size. The second image size is predetermined - for example, as a square of 224x224, 320x320 or 512x512 pixels. The selected value depends on the requirements of the specific neural network used further.

If necessary, the image can be normalized. In particular, pixel values from the original range (for example, [0…255]) are reduced to the range required by the neural network applied further (for example, [0…1]). Various normalization methods are known to those skilled in the art and are not detailed here. In an illustrative non-limiting example, simple normalization (X-Xmin)/(Xmax-Xmin) can be applied, where X is the value of the current pixel, and Xmin and Xmax are the minimum and maximum pixel values in the image to be normalized.

It should be understood that embodiments are possible in which image normalization can be performed at an earlier stage - for example, even before the first image compression. Nevertheless, it is preferable to perform it after bringing the cropped image to the second size, since this allows you to increase the accuracy at each of the previous stages of image preparation (pre-processing), as well as somewhat reduce the amount of calculations performed directly during normalization.

This creates an image prepared for further processing.

The pathology prediction unit 250 receives from the storage unit 220 and/or from the image preparation unit 240 the prepared medical image limited by the area of interest and analyzes it. In particular, the pathology predictor 250, using a pretrained neural network, determines the presence or absence of a pathology and, if present, determines the most likely boundaries within which it is located.

A doctor who has obtained the result of the above determination, has some experience, and also, if necessary, has additional information about the patient, such as anamnesis, medical history, complaints, physical condition, test results, etc., can have a more complete picture and make more accurate conclusion. Accordingly, it should be noted that the result of the operation of the proposed device is not a clinically significant medical opinion, but is used to support medical decision-making, while the clinical opinion should be taken by a radiologist.

The image processing performed in block 250 may be as follows.

The neural network interprets the resulting image in order to identify signs of pathologies, while the result of the work is the probability of the presence of signs of certain pathologies.

In the process of studying the errors of neural networks that are trained only on pathological data and analyze only the image, the authors found that some of the errors are related to the gender characteristics of patients. For example, a neural network can sometimes make mistakes in cases where the size of a woman's mammary glands differs from the average size. Also, the presence of breast implants in women often causes difficulties for the neural network and may be incorrectly recognized as a pathology. There are situations when the image shows the nipples of the mammary gland, which can also lead to processing difficulties.

In addition, the authors noticed that traditional neural networks do not take into account the natural age-sex changes in the anatomy that occur in human bone structures and internal organs. For example, with age, people may experience changes such as fibrosis (especially hilar), heart enlargement (common), elongation and sclerosis of the aorta (common), hardening of cartilage in the ribs, osteoporosis in the bones, decreased bone density (leading to increase in the transparency of the bones in the images), deforming osteoarthritis in the joints, lowering the height of the vertebral bodies, the development of subchondral sclerosis, the presence of listhesis, awl-leaved and pommer hernias, etc. Accordingly, the older the person, the more such changes can become. At the same time, it is known that, in general, there may be differences in the nature of age-related changes in the body between men and women associated with lifestyle. There are also studies showing that changes in men and women, at least in some age intervals, proceed with different intensity.

Many of these changes show up in medical images, and varying degrees of change may be considered acceptable for a certain age, but traditional neural networks do not take this into account and may incorrectly predict that a patient is sick. An erroneous indication of the presence of pathology in the image can complicate the work of a medical specialist with such an image.

For example, in FIG. 6 shows a sample x-ray image for a patient less than 65 years of age, whose lungs and spine are in age-appropriate condition.

On FIG. 7 shows a sample x-ray image for a 72 year old patient. On the part of the cardiovascular system in this picture, there is an expansion of the heart, an expansion of the superior vena cava, congestive vessels mainly in the lower sections, an enhanced pulmonary pattern; on the part of the skeletal system - arthrosis of 1 costoclavicular joint on both sides, spondylosis growths of the vertebrae in the lateral sides. All these signs are visible in the picture, and despite the fact that they are generally acceptable for a person at that age, a neural network that does not take into account the age of the patient may mistakenly consider that he is sick, and the medical specialist who received such a preliminary conclusion will have to spend extra time to study an image that doesn't really need that much attention.

Accordingly, in one embodiment, the neural network may be pre-trained to take into account additional patient data such as gender and age to improve pathology prediction accuracy.

The specific configuration of the neural network for determining pathology is not the subject of the present invention, therefore, is not disclosed in detail here.

Neural network pre-training can be performed using different training methods. For example, it may be supervised based on a plurality of medical images that have been pre-processed and labeled by suitably qualified medical professionals such as radiologists. In particular, as a result of a visual examination of the images, the doctor indicates whether there is a pathology in the presented image. In addition, for each image from the training data, the gender and age of the patient can be indicated. This is done either manually by the doctor or is read automatically from the patient data stored in the medical information system 130 of the medical organization 110 or in the central medical information system 150, or from the image metadata if it contains this information, etc.

The learning process of the neural network is controlled by the learning block 280 by applying a learning algorithm to the trained neural network using the training data. Instructions (markup) from the doctor are used by the trained neural network as ground truth. For example, in one embodiment, the markup may be 3 numbers: "1" (sick), "1" (female) and "0" (a range number indicating that the image belongs to a patient aged 0-10 years).

In an exemplary embodiment, 70% of the training images can be used directly for training and 30% for model testing. In another embodiment, a different ratio may be used, more suitable for the purposes of training a particular neural network. For example, to train a neural network, images can be divided into training, validation, and test sets. The training set size can be 70%, the validation set size can be 15%, and the test set size can be 15% of the images submitted for training. Specific ratios depend on the number of training images and are intended to test the generalized model - the extent to which the results of the study are applicable to new data is checked before using the model in production mode in a medical organization.

During the training process, images are prepared in the same way as described above with respect to block 240, and are fed to the input of the neural network, using images with both the presence and absence of pathologies. At each training step, the neural network calculates predictions for one or more images. These predictions are compared with the indication of the true presence/absence of the pathology, and, if necessary, with the indication of the true gender and age of the patient, and the value of the loss function is calculated (how much the neural network was mistaken in detecting the presence of pathology, in determining the sex and age of the patient). Further, using the gradient descent method and the backpropagation algorithm, all weights (weight coefficients) of the neural network are changed in accordance with the selected learning rate parameter in the direction opposite to the calculated gradient in order to minimize the error on the current image(s) ( I). This step is repeated many times, and as a result of the learning process, the weights of the neural network converge to the optimal ones. In the future, these weights are used by the network during the operation of the device to detect pathologies in the input images that have not been labeled.

In one of the embodiments, the output data of the pathology prediction block 250, that is, an indication of the probability of the presence of pathology, is the end result of the operation of the device 200 and is further used by other devices - for example, stored in the data storage block 220, from which it can later be retrieved on request from other devices , and/or sent to the data transfer unit 270, which transmits this result to another device - for example, to the central medical information system 150 or to the medical organization 110 that requested data processing.

In another embodiment, the output of the pathology predictor 250 is also passed to a report generator 260, which generates a report on the examination performed on the device 200. The examination report may comprise at least one of the following: a) a pathology image; b) text protocol of the study.

An image with visualization of pathology can be formed for those images for which, as a result of the analysis, a probability of the presence of pathology was found that exceeds a predetermined threshold probability of the presence of pathology, which indicates that the radiologist should pay attention to such an image. The threshold probability of the presence of a pathology in the general case is 0.5 (or 50%), but depending on the accuracy of a particular trained model and the degree of confidence in it, it can vary in practical application both up and down. For example, a medical organization may specialize in the treatment of diseases, the early detection of which is critical in terms of treatment prognosis, so it may request imaging images if the device detects a probability of pathology of only 10% or more. In another example, a medical organization may be attached to an enterprise, and the main contingent of its patients may have occupational chronic diseases of the chest, and some changes in the images in such patients may be considered acceptable, so imaging may be requested only for cases where the device has detected the possibility of having pathology 60% or more. It should be noted that many other situations are possible, which are not listed in this document, but are included in the scope of this invention. The ability to select a threshold probability of the presence of pathology allows the results of the proposed device 200 to be adapted to various specific applications, for example, to reduce the burden on medical personnel and at the same time provide early detection of pathologies with the required accuracy.

An image with visualization of pathology is a copy of the analyzed image, on which an indication of the found signs of pathologies is superimposed. For example, in the case of using the DICOM format, it can be generated as a DICOM Secondary Capture (secondary DICOM snapshot).

Various visualization options are possible. In one of the embodiments, the visualization can be performed in the form of a heat map, which performs a more intensive selection of those points and/or areas that are of greater interest in terms of the presence of pathologies, a less intensive selection of those points and/or areas that are of less interest , and those areas that, presumably, do not contain pathology, are not highlighted. The principle of selection can be different - for example, selection can be performed using a gradient of the same color (for example, shades of red or orange), using a gradient transition from one color to another (for example, from yellow to red), using an exact specifying a color (for example, blue - less likely, blue - more likely), using the size of the dot (for example, the lower the probability, the smaller the dot), etc. Various methods for constructing heat maps are applicable. An example heat map is shown in Fig. 8.

Heat maps allow you to adjust the amount of attention that a medical specialist should pay when studying a particular area in the image, eliminating the need for a detailed visual inspection of the entire image. Thus, the burden on medical personnel is reduced.

However, there are situations when the heat map is not accurate enough, in which case the doctor, on the contrary, has to spend time studying an area that is not of interest. It also turned out that in some implementations, heat maps clutter up the image, as a result of which the specialist has to spend time viewing two images at the same time: both the original image and the image with the heat map applied to it.

Accordingly, in another embodiment of the present invention, the visualization may be performed as a delineation of boundaries (or contours) covering one or more areas in the image in which there is a possibility of pathology, or in other words, in which signs of pathology are detected by the pathology predictor 250 . Various computer vision methods can be used to implement this approach. An example of an image with contours of a possible pathology plotted on it is shown in Fig. 9.

The image with the outlines of the boundaries of possible pathologies printed on it, as before, makes it possible to reduce the burden on medical personnel, while it is enough to study only it without referring to the original image. In addition, this approach makes it possible to smooth out inaccuracies in the determination of areas of interest.

Also, if necessary, the image with the visualization of the pathology may contain in text form an indication of the probability of the presence of pathology, obtained as a result of the operation of the first neural network of the pathology prediction block 250 . This eliminates the need to study any other images or files, including the original image and/or a file with a text study protocol.

Turning now to the text protocol of the study, it can be noted that it can both supplement the above image with visualization of the pathology, and replace it. The text protocol of the study contains the results of the work and a description of the operation of the device 200 in the form of textual information, for example, in CSV format. In the case of using the DICOM format, the protocol can be generated as a DICOM Structured Report (structured DICOM report).

In particular, the text protocol of the study may contain:

1) The name of the source image (link to it in the form of an appropriate identifier - for example, StudyInstanceID).

2) Recommendation (or in other words, prediction). As noted above, this recommendation may be a binary value (for example, 0 / 1), may be a number in some range indicating the likelihood of a pathology (for example, from 0 to 1), or may be in text format (for example, “probably sick / "probably healthy").

3) Timestamps - the time the study was received, the time the report was generated.

4) Information about errors in the operation of the device during the analysis, if any.

The study report obtained as a result of the operation of block 260, containing an image with visualization of the pathology and / or a text protocol of the study, is stored in the data storage block 220, from where it can later be retrieved upon request from other devices, and / or sent to the data transmission block 270, which transmits this report to another device - for example, to the central medical information system 150 or to the medical organization 110 that requested data processing.

In one embodiment, the processing results obtained by the device 200 may be stored in the device for a predetermined time (eg, seven days) if necessary, and subsequently deleted. This can be done, for example, for the purpose of backup, so that the result of the analysis can be requested and retransmitted without the need for a full reanalysis.

Thus, a pathology determination apparatus capable of automatically determining the pathology probability with improved accuracy is provided. This reduces the requirements for the qualification of medical personnel and reduces the influence of the human factor (attention, fatigue, responsibility). It also provides the possibility of using a large number of disparate data sets for training. In addition, the result of the study provides a comprehensive set of information necessary for making the correct medical decision with increased speed and accuracy.

In an illustrative non-limiting example for the purposes of the present invention, the pathology detection device 200 can be implemented as a cloud server having 24 computing cores, 64 GB RAM, 300 GB disk space for the CentOS 7 operating system, 12 TB disk space for data, disk space 1, 5 TB for the database and 2 network adapters.

Application

Systems, devices and methods according to the present invention can be used to process diagnostic medical images of organs and/or cavities in order to identify signs of pathologies in them.

Additional Implementation Features

Although the foregoing description relates to systems and devices, it should be understood that it can be fully described in terms of methods containing steps that implement the respective operations and functions of devices and blocks contained in systems and devices. The specific description of the methods essentially repeats the above description, therefore, is not separately disclosed in this document.

Although this document may indicate that data is being transmitted/sent or received/received by a person (e.g., medical professional, physician, expert), one skilled in the art should understand that such indication is used solely for the purpose of simplifying the description. , while in fact it is understood that the data is transmitted / sent or received / received by the corresponding device used and / or controlled by this person.

One or more transmission units or devices (transmitters) described herein and one or more receiver units or devices (receivers) may be physically implemented in the same transceiver unit or device or in different units or devices.

A device or a transmission unit in this document, for the sake of simplicity of description, may be referred to as a device or unit having the functions of not only transmitting, but also receiving data, information and/or signals. Similarly, the receiving device or unit may also include data, information and/or signaling functions.

Various illustrative blocks and modules described in connection with the disclosure herein may be implemented or executed by a general purpose processor, digital signal processor (DSP), application specific integrated circuit (ASIC), field programmable gate array (FPGA), or other programmable logic device (PLD), discrete logic element or transistor logic, discrete hardware components, or any combination of the foregoing, designed to perform the functions described in this document. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices (eg, a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors together with a DSP core, or any other similar configuration).

Some blocks individually or collectively may be, for example, a computer, and include a processor that is configured to call and execute computer programs from memory to perform method steps or block functions in accordance with embodiments of the present invention. According to embodiments, the device may further include a memory. The processor may call and execute computer programs from memory to execute the method. The memory may be a separate device independent of the processor or may be integrated with the processor. The memory may store code, instructions, commands, and/or data for execution on a set of one or more processors of the device described. Codes, instructions, commands may direct the processor to perform the steps of a method or device function.

The functions described herein may be implemented in hardware, software running on one or more processors, firmware, or any combination of the foregoing. The hardware and software implementing the functions may also be physically located in different locations, including such a distribution that parts of the functions are implemented in different physical locations, that is, distributed processing or distributed computing may be performed.

If necessary (for example, if the amount of data and / or calculations that need to be performed on this data is large), multi-threaded data processing can be performed, which in a simple representation can be expressed in the fact that the entire set of data to be processed is divided into a set of subsets , and each processor core performs processing on its assigned subset of data.

The above memory may be volatile or non-volatile memory, or may include both volatile and non-volatile memory. One of ordinary skill in the art will also understand that when referring to memory and storage of data, programs, codes, instructions, instructions, and the like, it is understood that there is a machine-readable (or computer-readable, processor-readable) storage medium. Computer-readable storage media includes both non-transitory computer storage media and communication media, including any transmission medium that facilitates movement of a computer program, or portion thereof, from one place to another. A non-transitory computer-readable storage medium can be any available medium that can be used to carry or store a desired piece of program code in the form of instructions or data structures, and that can be accessed by a computer, processor, or other general purpose or special processing device. destination.

By way of example, and not limitation, computer-readable media may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electronically erasable programmable read-only memory (EEPROM), flash memory. , Random Access Memory (RAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDR SDRAM) , accelerated speed synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct access bus random access memory (DR RAM), register, cache, semiconductor memories, magnetic media such as internal hard drives and removable drives, magneto-optical media and optical media such as CD-ROMs and digital versatile discs (DVDs), as well as any other media known in the art.

The information and signals described herein may be represented using any of a variety of different technologies. For example, the data, instructions, commands, information, signals, bits, symbols, and elementary signals that may be exemplified in the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combinations of the above, if applicable to the present invention.

At least one of the steps in the method or blocks in the device may use an artificial intelligence (AI) model to perform the respective operations. The AI-related function may be executed via a processor and non-volatile and/or volatile memory.

The processor may include one or more processors. At the same time, one or more processors may be a general purpose processor such as a central processing unit (CPU), an application processor (AP) and the like, a graphics-only processing unit such as a graphics processing unit (GPU), a visual processing unit (VPU). ), and/or a specialized AI processor such as a Neural Processing Unit (NPU).

One or more processors direct the processing of input data in accordance with a predefined operating rule or artificial intelligence (AI) model stored in non-volatile memory and/or non-volatile memory. A predetermined operating rule or artificial intelligence model can be obtained through training. In doing so, the processor may perform a pre-processing operation on the data to convert it into a form suitable for use as input to the artificial intelligence model.

"Obtained by training" means that by applying a learning algorithm to a trainable artificial intelligence model using a set of training data, a predefined operation rule or AI model with a desired characteristic is created. The training may be performed on the device itself running the AI according to the embodiment and/or may be implemented via a separate server/system.

An artificial intelligence model may include multiple neural network layers. Each of the multiple layers of the neural network includes a plurality of weights (coefficients) and performs a work operation for a given layer by computing using the plurality of weights of a given layer with respect to the input or calculation result of a previous layer.

Examples of neural networks include, but are not limited to, Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), Bidirectional Recurrent Deep Neural Network (BRDNN). ), generative adversarial networks (GANs), and deep Q-nets.

A learning algorithm is a method of training a predetermined target device (eg, a GPU or NPU based neural network) using a set of training data to call, enable, or control the target device to perform a determination or prediction. Examples of learning algorithms include, but are not limited to, supervised learning, unsupervised learning, partially supervised learning, or reinforcement learning.

It should be understood that although terms such as "first", "second", "third" and the like may be used in this document to describe various blocks, modules, networks, elements, components, regions, layers and/or sections ., these blocks, modules, networks, elements, components, areas, layers and/or sections should not be limited by these terms. These terms are only used to distinguish one block, module, network, element, component, region, layer, or section from another block, module, network, element, component, region, layer, or section. Thus, a first block, module, network, element, component, region, layer, or section may be referred to as a second block, module, network, element, component, region, layer, or section, without departing from the scope of the present invention. As used herein, the term "and/or" includes any and all combinations of one or more of the respective listed positions. Elements mentioned in the singular do not exclude the plurality of elements, unless otherwise specified.

The functionality of an element specified in the description or claims as a single element may be practiced by means of several components of the device, and conversely, the functionality of elements indicated in the description or claims as several separate elements may be practiced by means of a single component.

In one of the embodiments, some or all elements/blocks/modules of the proposed device are located in a common housing, can be placed on the same frame/structure/printed circuit board/crystal and are structurally connected to each other through assembly (assembly) operations and functionally through communication lines . The mentioned communication lines or channels, unless otherwise indicated, are typical communication lines known to specialists, the material implementation of which does not require creative efforts. The communication link may be a wire, a set of wires, a bus, a track, a wireless link (inductive, RF, infrared, ultrasonic, etc.). Communication protocols over communication lines are known to those skilled in the art and are not disclosed separately.

The functional connection of elements should be understood as a connection that ensures the correct interaction of these elements with each other and the implementation of one or another functionality of the elements. Particular examples of functional communication may be communication with the ability to exchange information, communication with the ability to transmit electric current, communication with the ability to transmit mechanical motion, communication with the ability to transmit light, sound, electromagnetic or mechanical vibrations, etc. The specific type of functional connection is determined by the nature of the interaction of the mentioned elements, and, unless otherwise indicated, is provided by well-known means, using principles well-known in the art.

The design of the elements of the proposed device is known to specialists in this field of technology and is not described separately in this document, unless otherwise indicated. The elements of the device can be made from any suitable material. These components can be manufactured using known methods including, by way of example only, machining, investment casting, crystal growth. Assembly, connection, and other operations as described herein are also within the knowledge of a person skilled in the art, and thus will not be explained in more detail here.

Although the exemplary embodiments have been described in detail and shown in the accompanying drawings, it should be understood that such embodiments are illustrative only and are not intended to limit the present invention, and that the present invention should not be limited to the particular arrangements and structures shown and described, since a person skilled in the art on the basis of the information set forth in the description and the knowledge of the prior art may be obvious various other modifications and embodiments of the invention, without going beyond the essence and scope of this invention.

Claims (108)

1. Medical decision support system, containing: at least one device for obtaining medical images located in a medical organization and configured to form at least one medical image based on a diagnostic study of at least one organ and/or cavity of the examined patient and transmit the said at least one medical image to data transmission device; at least one data transmission device located in a medical organization and configured to generate data to be processed based on the received at least one medical image and transfer the data to be processed to the central medical information system (CMIS), wherein the data to be processed is a package , containing at least two medical images; CMIS configured to receive at least one packet from at least one data transmission device, resize and fill said at least one packet by sorting the images contained in said at least one packet according to their resolution or priority depending on the requirements and/or capabilities of the at least one pathology device, and transmitting at least one modified packet to the at least one pathology device; And at least one device for determining the pathology, made with the possibility of extracting said at least one medical image from the received at least one package, determining whether there is in said at least one organ and / or cavity of the patient under examination on said at least pathology in one medical image, generating a report that contains at least one file containing an indication of the presence or absence of pathology, and sending the report to the CMIS, moreover, the determination of the pathology is performed automatically using the neural network contained in the device for determining the pathology and pre-trained for this type of diagnostic study, moreover, the result of determining the pathology is intended to support the adoption of a medical decision about the condition of the said at least one organ and/or cavity of the examined patient and/or about the treatment of the examined patient. 2. The system of claim 1, further comprising a viewer located in a medical facility and configured to receive a pathology determination result from the pathology determination device and present the pathology determination result in a human-viewable form. 3. The system according to claim 2, further comprising a storage located in a medical organization and configured to store said at least one medical image generated by a device for obtaining medical images, data to be processed, generated by said data transmission device, and / or a result detection of pathology from the device for determining the pathology. 4. The system according to claim 3, further comprising a medical information system located in a medical organization, and the storage and data transmission device are parts of the medical information system. 5. The system of claim 1, wherein the data to be processed comprises said at least one medical image. 6. The system according to claim 5, in which the data to be processed additionally contains additional target information containing information about the patient, about the study, about the medical organization and / or about the medical specialist who conducted the study. 7. The system of claim 5, wherein the data to be processed further comprises a unique image identifier corresponding to each of said at least one medical image, wherein the pathology detection result obtained by the pathology detection device after processing said at least one medical image contains a unique image identifier corresponding to the image. 8. The system according to any one of paragraphs. 5-7, in which the data to be processed is depersonalized. 9. The system according to claim. 1, in which the data transmission device is additionally configured to transmit the packet upon reaching predetermined packet parameters or in time. 10. The system according to claim 1, in which the data to be processed, generated and transmitted by the data transmission device of the medical organization to the CMIS, are non-depersonalized, moreover, the CMIS is additionally configured to depersonalize the data to be processed. 11. The system according to claim 1, in which the device for determining the pathology is additionally configured to: visualization of at least one area on the image, presumably containing a pathology, if it is determined that there is a pathology in the mentioned at least one organ and/or cavity of the examined patient on the processed medical image; And generating a report containing an image with visualization of the pathology. 12. The system of claim. 1, in which the imaging of the pathology is performed on the image, which is a copy of the corresponding image, which is defined pathology. 13. The system according to claim. 1, in which the device for determining the pathology is additionally configured to: formation of a text protocol of the study, containing at least one of: the identifier of the original image, the result of determining the pathology in numerical or text format, the time of obtaining the data to be processed, the time of obtaining the result of determining the pathology, the time of generating the study protocol, information about errors that occurred during the work devices; And generating a report containing a text protocol of the study. 14. The system according to claim. 1, additionally containing the equipment of the expert, made with the ability to: receiving a pathology detection result from the pathology detection device; providing the result of determining the pathology and the corresponding medical image to the user of the expert's equipment; receiving input from the user to form a medical report containing a medical decision about the state of said at least one organ and/or cavity of the examined patient and/or about the treatment of the examined patient. 15. The system according to claim 14, in which the user of the expert equipment is a specialist of an expert organization or an external radiologist who makes medical conclusions using the results of the operation of the device for determining the pathology and / or performs the function of an expert or consultant. 16. The system according to claim 15, containing at least two copies of the expert’s equipment, the users of which are, respectively, at least two specialists of expert organizations or external radiologists, moreover, different specialists of expert organizations or external radiologists perform the interpretation of different types of studies. 17. The system according to claim 1, containing at least two medical organizations and at least two devices for determining pathology, and one or more medical organizations are served by one or more different devices for determining the pathology. 18. The system according to claim 17, in which the same medical image from one medical organization is transferred for processing to different devices for determining the pathology, which have different operating principles and / or are trained on different data sets. 19. The system according to claim 17, in which medical images obtained as a result of different types of studies from one medical organization are transferred for processing to different devices for determining the pathology, designed to process the corresponding types of studies. 20. The system according to claim 1, in which the CMIS is additionally configured to: receiving a pathology detection result from the pathology detection device; transferring the result of determining the pathology to the equipment of the expert; obtaining a medical report formed using the expert's equipment; transfer of the medical report to the organization or person requesting the processing of the relevant medical image. 21. The system according to claim 20, in which the CMIS is additionally configured to: storage of medical images; storage of personal data of patients; depersonalizing at least a portion of the data to be processed prior to transmission to the pathology device; And adjusting the amount and type of personal data to which the user of the CMIS is granted the right to access, depending on his level of access. 22. The system according to claim 20, in which the CMIS is additionally configured to: receiving a request for drawing up a conclusion regarding the result of determining the pathology; And transferring the result of determining the pathology to the equipment of the expert in response to receiving a request for drawing up an opinion, and the request for the conclusion contains the task of interpreting the medical image and / or the result of determining the pathology, which is allowed to be performed on their own initiative by any one or more experts with the appropriate level of access to the CMIS, or which must be performed by a specific one or more experts; and/or receiving an image processing request for the medical image; And transmitting the data to be processed containing the medical image to the pathology detection device in response to receiving an image processing request, wherein the image processing request comprises a pathology detection task on the corresponding medical image, which any one or more pathology detection devices capable of processing medical images of the corresponding type can perform on its own initiative, or which a specific one or more pathology devices must perform. 23. The system according to claim 22, in which the request for an opinion or a request for image processing comes from a medical organization that received the corresponding medical image, from a medical organization or a person who requested image processing, from the CMIS itself, from a pathology device, or from expert. 24. The system according to claim 22, in which the CMIS is configured to generate requests for a conclusion, taking into account one or more of: - working hours of the expert or the time interval during which the expert is ready to accept requests; - the number of requests that have already been issued to the expert, but have not yet been processed; - the minimum number of requests that the Expert Advisor is ready to accept at the same time; - the total number of requests already processed by the expert, and requests that are assigned to this expert, during working hours; - the number of opinions issued by the expert for the last period of time. 25. The system according to claim 22, in which the CMIS is configured to generate requests for image processing, taking into account one or more of: - the time interval during which it is allowed to send requests to one or another device to determine the pathology; - the number of requests that have already been issued to the device for determining the pathology, but have not yet been processed; - the minimum number of requests that can be simultaneously processed by the device for determining the pathology; - the total number of requests already processed by the device for determining the pathology, and requests that are assigned to this device for determining the pathology, for a predetermined period of time; - the number of results generated by the given pathology device in the last predetermined period of time. 26. The system according to claim. 22, in which the CMIS is configured to organize requests for drawing up an opinion and / or requests for image processing in turn. 27. The system according to claim 26, in which requests for drawing up a conclusion and requests for image processing have priority set by the medical organization that received the corresponding medical image, or by the person who requested image processing, automatically by the CMIS itself, automatically or manually by the CMIS operator, the device for definition of pathology or an expert. 28. The system of claim 27, wherein the priority is set based on one or more of: - features of ongoing research, - the profile of the organization that conducted the study, - the patient's condition, - the requirements of the organization or person who requested the processing of the image or the drawing up of an opinion, - the deadline for the provision of medical services. 29. The system according to claim 20, in which the CMIS is additionally configured to: grouping pending images into packets for transmission to a pathology device. 30. The system according to claim. 1, in which the CMIS is additionally configured to validate the data to be processed, and the validation contains one or more of the following checks: - is it possible to extract an image from the data to be processed; - whether the data attached to the request for image processing correspond to the request itself; - whether the image is positive or negative; - whether the image has a size equal to or greater than a predetermined minimum size supported by at least one of the pathology devices capable of processing this type of examination; - whether the data to be processed is depersonalized; - whether the unique identifier of the image has a predefined format. 31. The system according to claim. 1, in which the CMIS is additionally configured to pre-process the data to be processed, and the pre-processing of the data to be processed comprises one or more of the following operations: - converting the image to positive or negative; - cropping the image in accordance with the area of interest pre-set in the image parameters by the medical specialist who conducted the study; - conversion of brightness or color of the image; - image compression to the required size; - depersonalization of the data to be processed; - converting the unique image identifier into a predetermined format supported by one or more pathology devices. 32. The system according to claim 21, in which the CMIS is additionally configured to: storing at least one data set containing properly labeled medical images, moreover, the markup contains an indication of the presence or absence of pathology. 33. The system of claim 32, wherein the at least one dataset is for training one or more pathology devices. 34. The system of claim. 33, wherein at least one data set contains personal data of patients. 35. The system according to claim 34, in which the personal data of patients contains the gender and age of patients. 36. The system of claim 34, wherein the CMIS is further configured to transmit at least one set of data to the pathology device for learning purposes without being depersonalized with respect to those personal data needed to train the pathology device. 37. The system according to claim 20, in which the CMIS is additionally configured to: analysis of medical reports compiled by experts; extracting from medical reports information about the presence or absence of pathology and the nature of the pathology, if any; And generating at least one set of labeled medical images based on the extracted data. 38. The system according to claim 37, in which the CMIS is additionally configured to: supplementing the markup of the generated marked up medical images with the corresponding personal data of the patient stored in the CMIS. 39. The system of claim 37, which analyzes only medical reports prepared by experts whose skill level or rating is above a predetermined threshold. 40. The system of claim. 33, wherein the at least one data set contains for each patient at least two medical images of the same area taken at different time periods. 41. The system of claim. 40, in which at least two medical images for each patient are labeled, and the data set containing them is designed to train one or more devices for determining the pathology to ignore individual characteristics of patients that should not be considered pathology, and also monitor changes occurring in the patient's body over time. 42. The system of claim 40, wherein the pathology determination device is configured to request previous medical images of the analyzed area of the patient depicted in the particular analyzed image from the CMIS.

Images