CN113555088A

CN113555088A - Image processing method, device, system and storage medium

Info

Publication number: CN113555088A
Application number: CN202010327365.0A
Authority: CN
Inventors: 陈磊
Original assignee: Shanghai United Imaging Intelligent Healthcare Co Ltd
Current assignee: Shanghai United Imaging Intelligent Healthcare Co Ltd
Priority date: 2020-04-23
Filing date: 2020-04-23
Publication date: 2021-10-26

Abstract

The application relates to an image processing method, an image processing device, an image processing system and a storage medium. The method is applied to an image processing system, the image processing system comprises an image management subsystem, a server and a client, and the method comprises the following steps: the server receives the spine image sent by the image management subsystem; the server receives a processing request for the spine image sent by the client; the processing request comprises at least one processing mode; the server obtains each target image processing module corresponding to each processing mode from a preset mapping relation based on each processing mode; the mapping relation comprises a corresponding relation between a plurality of processing modes and the image processing module; and the server processes the spine image by adopting each target image processing module to obtain a processing result of the spine in the spine image and sends the processing result of the spine to the client. The method can save labor and time.

Description

Image processing method, device, system and storage medium

Technical Field

The present application relates to the field of image processing technologies, and in particular, to an image processing method, an image processing apparatus, an image processing system, and a storage medium.

Background

The spine consists of vertebrae, the vertebral bodies of which comprise the largest part of the spine, and intervertebral discs, which comprise a small part of the spine. Generally, the spine includes vertebrae and sacrum composed of cervical vertebrae, thoracic vertebrae, lumbar vertebrae, etc., and coccyx, and it is seen that the spine is very important for the human body. Nowadays, as the sitting time of people increases, more and more people have spine pathological changes, which seriously affect the normal life of people, so the spine detection is very necessary.

In the related art, when a doctor detects the spine of a patient, generally, a medical image taken by a subject is transmitted to a reading system of a hospital, and then the medical image of the subject can be observed on the reading system, parameters such as a window width and a window position on the reading system can be manually adjusted to observe the image, and the spine of the subject can be checked according to experience to obtain a detection result.

However, the above technique has a problem that it takes a lot of labor and time to examine the subject.

Disclosure of Invention

In view of the above, it is desirable to provide an image processing method, an apparatus, a system, and a storage medium capable of saving labor and time in view of the above technical problems.

An image processing method is applied to an image processing system, the image processing system comprises an image management subsystem, a server and a client, and the method comprises the following steps:

the server receives the spine image sent by the image management subsystem;

the server receives a processing request for the spine image sent by the client; the processing request comprises at least one processing mode;

the server obtains each target image processing module corresponding to each processing mode from a preset mapping relation based on each processing mode; the mapping relation comprises a corresponding relation between a plurality of processing modes and the image processing module;

the server processes the spine image by adopting each target image processing module to obtain a processing result of the spine in the spine image, and sends the processing result of the spine to the client.

In one embodiment, the image processing system further includes a gateway, and the server receives the spine image sent by the image management subsystem, and includes:

the server receives the spine image sent by the image management subsystem via the gateway.

In one embodiment, the server is an extranet server, and the method further includes:

the extranet server encrypts the spine processing result by adopting a preset encryption algorithm and stores the spine encryption processing result into the first database.

In one embodiment, the sending the processing result of the spine to the client includes:

the external network server receives login information sent by the client;

the external network server verifies the login information, and decrypts the encrypted processing result of the spine after the login information is successfully verified to obtain the decrypted processing result of the spine;

and the extranet server sends the decryption processing result of the vertebra to the client.

In one embodiment, the method further includes:

the server receives an updating request sent by the client; the update request includes identity information of the client;

the server verifies the identity information of the client;

if the server successfully verifies the identity information of the client, receiving a newly added image processing module and a corresponding newly added processing mode sent by the client;

and the server updates the mapping relation based on the newly added image processing module and the corresponding newly added processing mode.

In one embodiment, the method further includes:

the server acquires a rechecking processing result of the vertebra and compares the processing result of the vertebra with the rechecking processing result of the vertebra; the rechecking processing result of the vertebra is a processing result obtained after the vertebra image is processed again;

if the processing result of the vertebra is different from the rechecking processing result of the vertebra, determining the processing result of the vertebra, the rechecking processing result of the vertebra and the vertebra image as typical case data information, and storing the typical case data information into a second database;

the server improves the image processing modules in the mapping relationship based on the typical case data information in the second database.

In one embodiment, the method further includes:

the server receives identity information of a detection object corresponding to the spine image; the identity information is sent by the image management subsystem;

the server generates a visual spine image and a spine detection report of the detection object based on the processing result of the spine and the identity information of the detection object corresponding to the spine image;

and the server associates the visual spine image of the detection object with the spine detection report and then displays the spine image and the spine detection report on the display interface.

An image processing device is applied to an image processing system, the image processing system comprises an image management subsystem, a server and a client, and the device comprises:

the first receiving module is used for receiving the spine image sent by the image management subsystem;

the second receiving module is used for receiving a processing request for the spine image sent by the client; the processing request comprises at least one processing mode;

the determining module is used for obtaining each target image processing module corresponding to each processing mode from a preset mapping relation based on each processing mode; the mapping relation comprises a corresponding relation between a plurality of processing modes and the image processing module;

and the processing and sending module is used for processing the spine image by adopting each target image processing module to obtain a processing result of the spine in the spine image and sending the processing result of the spine to the client.

An image processing system comprises an image management subsystem, a server and a client, wherein the server comprises a memory and a processor, the memory stores a computer program, and the processor realizes the following steps when executing the computer program:

the server receives the spine image sent by the image management subsystem;

A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:

the server receives the spine image sent by the image management subsystem;

The image processing method, the device, the system and the storage medium are applied to an image processing system, the image processing system comprises an image management subsystem, a server and a client, the server receives a spine image sent by the image management subsystem and a processing request which is sent by the client and comprises at least one processing mode, each target processing module corresponding to each processing mode is obtained from a preset mapping relation based on each processing mode, each target processing module is adopted to process the spine image to obtain a spine processing result, and the spine processing result is sent to the client. In the method, the processing of the spine image can be completed through an automatic flow, and the obtained processing result of the spine is sent to the client, and the spine detection process does not need manual operation at all, so that the method can save labor and time; in addition, because the processing module corresponding to the processing mode can be called to process the spine image in the method, the processing result of the spine is obtained, and the spine detection process does not need to manually detect the spine image according to experience, so that the processing/detection result of the spine obtained by the method is objective and more accurate, and the conditions of missed detection and false detection caused by manual detection according to experience can be reduced.

Drawings

FIG. 1 is a diagram of an exemplary embodiment of an image processing method;

FIG. 2 is a flow diagram illustrating a method for image processing according to one embodiment;

FIG. 3 is a flow chart illustrating an image processing method according to another embodiment;

FIG. 4 is a flowchart illustrating an image processing method according to another embodiment;

FIG. 5 is a flowchart illustrating an image processing method according to another embodiment;

FIG. 6 is a flowchart illustrating an image processing method according to another embodiment;

FIG. 7 is a flowchart illustrating an image processing method in an embodiment in which the server is an intranet server;

FIG. 8 is a flowchart illustrating an image processing method when the server is an extranet server according to an embodiment;

FIG. 9 is a block diagram showing the configuration of an image processing apparatus according to an embodiment;

fig. 10 is an internal configuration diagram of a server in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

In the newly published' ten stubborn diseases in the world health organization, the cervical spondylosis is ranked the second, the incidence rate of the disease is 17.3% according to the latest report in China, more than 2 hundred million patients exist in China, and the annual cost for treating the cervical spondylosis is as high as 5 hundred million and more. A recent survey of 2000 cervical spondylopathy patients in China shows that: the number of people suffering from cervical spondylosis of teenagers and office workers is increased, and the proportion of the people under 30 years old is 22% higher than that of the patients between 30 years old and 50 years old. In recent 20 years, the high-incidence age of cervical spondylosis is from 55 years to 39 years, and the cervical spondylosis is getting younger and younger. Therefore, more and more people have spine pathological changes, which seriously affect the normal life of people, and therefore, the spine detection is very necessary. At present, when a doctor detects the spine of a patient, generally, a medical image shot by a subject is transmitted to a reading system of a hospital, and then the medical image of the subject can be observed on the reading system, parameters such as a window width and a window position on the reading system can be manually adjusted to observe the image, and the spine of the subject can be checked according to experience to obtain a detection result. However, the above-described technique is problematic in that it takes a lot of labor and time to examine a subject, and the detection result varies from person to person and is difficult to objectively quantify. The present application provides an image processing method, apparatus, system and storage medium, which can solve the above technical problems.

The image processing method provided by the application can be applied to the application environment shown in fig. 1, and the application environment can be an image processing system. The image management subsystem 102 communicates with the server 104 via a network, and the server 104 and the client 106 may also communicate via a network. The image Management subsystem 102 may be a PACS System (Picture Archiving and Communication System), a RIS System (radio Information Management System), a HIS System (Hospital Information System), a LIS System (Laboratory Information Management System), a CT/MR (Computed Tomography, Magnetic Resonance) workstation, or the like, the server 104 may be implemented by an independent server or a server cluster composed of a plurality of servers, such as a web server, an AI (Artificial Intelligence) server, or the like, and the client 106 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices.

The execution subject of the embodiment of the present application may be an image processing system, an image processing apparatus, or a server in the image processing system, and the method of the embodiment of the present application will be described below with reference to the server as the execution subject.

In an embodiment, an image processing method is provided, which is applied to an image processing system, where the image processing system includes an image management subsystem, a server, and a client, and the application of the method to the server in fig. 1 is taken as an example to explain how the server receives and processes a spine image and returns a processing result of the spine. As shown in fig. 2, the method may include the steps of:

s202, the server receives the spine image sent by the image management subsystem.

The server may be a server inside the hospital, that is, a server for transmitting and processing data based on an intranet in the hospital (may also be referred to as an intranet server), or may be a server outside the hospital, that is, a server for transmitting and processing data based on an external network in the hospital (may also be referred to as an extranet server). The image management subsystem is mainly referred to as a PACS (Picture Archiving and Communication Systems) system, a RIS (radiology information management system), a CT/MR (Computed Tomography, Magnetic Resonance) workstation, and the like.

The spine image may be a spine image of the object to be detected, may be a spine image of the object to be detected obtained by scanning a specific spine part or a whole body spine part of the object to be detected, may also be a spine image of the object to be detected obtained in a database in which the spine image of the object to be detected is stored in advance, or may be other acquisition modes, and after the spine image is acquired, the spine image may be transmitted to a PACS/RIS system or a CT/MR workstation for storage. It should be noted that the spine image stored in the PACS/RIS system or the CT/MR workstation is generally DICOM data of the spine image. Meanwhile, configuration information such as keywords can be set in the PACS/RIS system or the CT/MR workstation, so that when the spine image is sent, the spine image can be found firstly through keyword search and then sent.

In addition, when sending the DICOM data of the spine image to the server, the image management subsystem may directly send the DICOM data of the spine image to the server, may also send the DICOM data of the spine image to the server through the gateway, and of course, may also send the DICOM data of the spine image to the server through the gateway and then through the router connected to the intranet inside the hospital, and of course, may also send the DICOM data of the spine image to the server through the router connected to the intranet inside the hospital, then through the gateway, and finally through the router connected to the external network of the hospital, and of course, other manners are also possible, and this embodiment is not limited specifically here.

S204, the server receives a processing request for the spine image sent by the client; the processing request includes at least one processing mode.

The processing method herein refers to what kind of processing is performed on the spine image, and may include, for example, detection processing, segmentation processing, classification processing, quantization processing, and the like.

In addition, the client may be a terminal where a doctor is located, which may also be referred to as a doctor workstation, which may be a mobile phone, a desktop, a laptop, an IPAd of the doctor, and the like, and may be disposed at the same location as the image management subsystem, or may be disposed at different locations, for example, in a hospital, the image management subsystem is disposed in a scanning device operating room, and the doctor workstation may be disposed in a scanning device operating room, or may be disposed in a doctor office; meanwhile, the client of the doctor can be in the hospital or outside the hospital. Of course, the client may also be a client where the user is located, and the client where the user is located may be a mobile phone, a desktop, a laptop, an IPAd, and the like of the user, and of course, the client where the user is located may be inside the hospital or outside the hospital. The following embodiments are mainly described by taking a client as an example of a client where a doctor is located.

Further, when the client sends the processing request to the server, if the processing request includes a plurality of processing methods, all the processing methods may be sent to the server at one time, or each processing method may be sent to the server in sequence, or other sending methods may be used. In addition, when the client sends the processing request to the server, the processing request for the spine image may be sent to the server through a router connected to an intranet inside the hospital, or the processing request for the spine image may be sent to the server through a router connected to an external network outside the hospital, or other manners may be used, and the present embodiment is not limited to this embodiment.

S206, the server obtains each target image processing module corresponding to each processing mode from a preset mapping relation based on each processing mode; the mapping relationship includes a correspondence between a plurality of processing modes and the image processing module.

The image processing module refers to a preset module for processing a spine image, and may include, for example, a spine detection module, a spine segmentation module, a spine classification module, a spine quantization module, and the like, where the spine detection module may include a detection model formed by a neural network, the spine segmentation module may include a segmentation model or an existing segmentation algorithm, the spine classification module may include a classification model, all of the three modules may be obtained by using a spine training image and a spine standard training in advance, and the spine quantization module may include a plurality of quantization analysis methods, such as a method for calculating an intervertebral distance, a method for calculating a curvature of a spine, and the like. Here, the processing manner in the mapping relationship is the same as that in S204 described above, and refers to what kind of processing is performed on the spine image, and may include, for example, detection processing, segmentation processing, classification processing, quantization processing, and the like.

In addition, when the image processing modules are preset, what processing operation is performed by each image processing module may also be obtained, that is, the processing mode corresponding to each image processing module may be obtained, and then each image processing module and the corresponding processing mode may be bound to obtain the mapping relationship and stored. Thus, when the server receives various processing modes of the spine sent by the client, the image processing module corresponding to each processing mode can be obtained in the stored mapping relation and can be marked as the target image processing module.

And S208, the server processes the spine image by adopting each target image processing module to obtain a spine processing result in the spine image, and sends the spine processing result to the client.

After obtaining the target image processing modules, the server may sequentially process the DICOM data of the spine image according to a preset processing sequence, for example, each called target image processing module of the spine includes a segmentation module, a classification module, and a quantization module, so that the DICOM data of the spine image may be segmented by the segmentation module to obtain a spine segmentation result, then the spine segmentation result is classified by the classification module to obtain a spine classification result, and then the spine segmentation result and/or the spine classification result is subjected to quantization analysis by the quantization module to obtain a spine quantization analysis result. Here, the spine segmentation result, the spine classification result, the spine quantitative analysis result, and the like may be used as the spine processing result.

After obtaining the spine processing result, the server may store the spine processing result, and then may perform extranet transmission or intranet transmission according to the actual needs of the doctor, for example, when the doctor is inside the hospital, the spine processing result may be transmitted to the doctor's client through a router connected to the intranet inside the hospital, and when the doctor is outside the hospital, the spine processing result may be transmitted to the doctor's client through a router connected to an external network outside the hospital, which may be other ways, and this embodiment is not limited specifically herein.

The image processing method is applied to an image processing system, the image processing system comprises an image management subsystem, a server and a client, the server receives a spine image sent by the image management subsystem and a processing request which is sent by the client and comprises at least one processing mode, each target processing module corresponding to each processing mode is obtained from a preset mapping relation based on each processing mode, each target processing module is adopted to process the spine image to obtain a spine processing result, and the spine processing result is sent to the client. In the method, the processing of the spine image can be completed through an automatic flow, and the obtained processing result of the spine is sent to the client, and the spine detection process does not need manual operation at all, so that the method can save labor and time; in addition, because the processing module corresponding to the processing mode can be called to process the spine image in the method, the processing result of the spine is obtained, and the spine detection process does not need to manually detect the spine image according to experience, so that the processing/detection result of the spine obtained by the method is objective and more accurate, and the conditions of missed detection and false detection caused by manual detection according to experience can be reduced.

In another embodiment, another image processing method is provided, and the embodiment relates to a specific process of how a server receives a spine image when the image processing system further comprises a gateway. On the basis of the above embodiment, the above S202 may include the following steps:

The image management subsystem is connected with the gateway, the gateway can be a front-end processor arranged in a hospital and generally refers to intermediate equipment of a hospital transmission system, when the image management subsystem obtains a spine image, the spine image can be sent to the front-end processor, then the front-end processor directly sends the spine image to the server through the router, or the front-end processor carries out data format conversion on the spine image sent by the image management subsystem, and sends the converted spine data to the server through the router. The spine image sent by the image management subsystem is forwarded to the server through the gateway, so that the physical isolation of the spine data in the transmission process can be realized, and the harm to the safety of the data is avoided.

In the image processing method provided by this embodiment, the server may receive the spine image sent by the image management subsystem via the gateway. Data can be transmitted through the gateway, so that the safety of the data between the image management subsystem and the server can be ensured.

In another embodiment, another image processing method is provided, and the embodiment relates to a specific process of how the server receives the spine image if the server is an extranet server. On the basis of the above embodiment, the method may further include the steps of:

The preset Encryption Algorithm may be md5 Algorithm (Message-Digest Algorithm 5), DES (Data Encryption Standard) Algorithm, IDEA Algorithm (International Data Encryption Algorithm), DSA (Digital Signature Algorithm), and the like.

In addition, the extranet server herein may include a web server and an AI server, etc., wherein the web server may be connected with the AI server. When the image management subsystem sends the spine image, the spine image may be sent to the web server, and then the web server may forward the spine image to the AI server for processing.

After the extranet server obtains the processing result of the spine, the processing result of the spine can be encrypted by adopting an encryption algorithm to obtain an encrypted processing result, and the encrypted processing result is recorded as the encryption processing result of the spine. In addition, when the image management subsystem obtains the spine image according to the keyword, the information of the object to be detected corresponding to the spine image can also be obtained, and when the spine image is transmitted, the information of the corresponding object to be detected can also be correspondingly transmitted to the extranet server, so that the information of the object to be detected and the encryption processing result of the corresponding spine can be associated and stored in the first database.

Accordingly, if the doctor client wants to observe the spine image and the spine processing result of the object to be detected, the extranet server needs to send the spine processing result to the doctor client, and as shown in fig. 3, sending the spine processing result to the client in S208 may include the following steps:

s302, the external network server receives login information sent by the client.

S304, the external network server verifies the login information, and decrypts the encrypted result of the spine after the login information is successfully verified to obtain the decrypted result of the spine.

S306, the extranet server sends the decryption processing result of the vertebra to the client.

The login information may be identity information of a login person at the client, such as an identity card number, a telephone number, a work card number, a micro signal number, and the like, or may be information obtained by combining the identity information of the login person and a password, where the password may be a character, a number, a letter, and the like.

In addition, when the processing result of the spine is encrypted, correspondingly, a decryption program corresponding to the encryption algorithm may be set to decrypt the encrypted data into the original processing result of the spine.

Generally, an extranet server presets login information which is registered and authenticated by some login personnel and recorded as standard login information, then a doctor can input the login information on a client when needing to check a processing result of the spine of an object to be detected, the input login information is transmitted to the extranet server through a router connected with an external network of a hospital, the extranet server can match the input login information with the standard login information after receiving the login information input by the doctor, if the matching is successful, namely one of the input login information and the standard login information is the same, a decryption program can be started to decrypt an encryption processing result of the spine, the decrypted processing result is obtained and recorded as a decryption processing result of the spine, and then the server can send the decryption processing result of the spine to the client through the router connected with the external network of the hospital, therefore, doctors can check the processing result of the spine on the client of the doctors, and remote observation and examination are realized; if the matching is unsuccessful, namely the input login information is different from the login information in the standard login information, the server can output alarm information to prompt that the input login information is unsafe information.

In the image processing method provided by this embodiment, if the server is an extranet server, the extranet server may encrypt the processing result of the spine to obtain an encrypted processing result of the spine, and when the client needs to observe the processing result of the spine, the login information may be input, and after the login information is successfully verified, the encrypted processing result of the spine is decrypted and the decrypted spine processing result is sent to the client. In this embodiment, since the processing result of the spine can be encrypted under the condition that the client is connected to the external network, and the encrypted processing result of the spine can be decrypted only when the login information of the client is successfully verified, the privacy and the security of data in the spine detection process can be ensured.

In another embodiment, another image processing method is provided, and the embodiment relates to a specific process of how to update the mapping relationship between the processing mode and the image processing module. On the basis of the above embodiment, as shown in fig. 4, the method may further include the following steps:

s402, the server receives an updating request sent by the client; the update request includes identity information of the client.

S404, the server verifies the identity information of the client.

S406, if the server successfully verifies the identity information of the client, the server receives the newly added image processing module and the corresponding newly added processing mode sent by the client.

S408, the server updates the mapping relation based on the newly added image processing module and the corresponding newly added processing mode.

The identity information of the client may be the model of the client, the identification number of the corresponding doctor of the client, a telephone number, a employee's card number, a micro-phone number, and the like. The authentication method of the server for the identity information of the client is similar to that of the login information, and is not described herein again.

In addition, the added image processing module can be an image processing module obtained by improving or changing the original image processing module, the corresponding processing mode can be the original processing mode, and can also be a reestablished image processing module, the corresponding processing mode can be a reset processing mode, the processing mode corresponding to the newly added image processing module is not only the original processing mode or the reset processing mode, all of them can be referred to as new processing mode, after obtaining the new processing module and new processing mode, the server can replace the image processing module and the processing mode in the original mapping relation with the newly added image processing module and the newly added processing mode, or directly add the newly added image processing module and the newly added processing mode into the original mapping relation without changing the original image processing module and the original processing mode.

The image processing method provided in this embodiment may verify the identity information sent by the client, receive the newly added image processing module and the newly added image processing mode after the verification is successful, and update the mapping relationship based on the newly added image processing module and the corresponding newly added processing mode. In this embodiment, since the mapping relationship between the original image processing module and the original processing method can be updated, the diversity and richness of the image processing module and the processing method on the server can be ensured, so that the modules that can be used for processing the spine at a later stage are richer, and different modification requirements of the user/doctor can be met.

In another embodiment, another image processing method is provided, and the embodiment relates to a specific process of rechecking the processing result of the spine and updating the original image processing module according to the rechecking result. On the basis of the above embodiment, as shown in fig. 5, the method may further include the following steps:

s502, the server acquires a rechecking processing result of the vertebra and compares the processing result of the vertebra with the rechecking processing result of the vertebra; the rechecking processing result of the vertebra is a processing result obtained after the vertebra image is processed again.

And S504, if the spine processing result is different from the spine rechecking processing result, determining the spine processing result, the spine rechecking processing result and the spine image as typical case data information, and storing the typical case data information into a second database.

S506, the server improves the image processing module in the mapping relation based on the typical case data information in the second database.

In this embodiment, the processing results of all the vertebrae are not reprocessed, but generally, only the initially obtained processing result of the vertebrae is processed again, that is, the error is rechecked to obtain the rechecked processing result, for example, after the doctor observes the processing result of the vertebrae, if a significant error is detected, for example, the curvature of the cervical vertebrae displayed on the segmentation result of the vertebrae is significantly straight, but the curvature of the quantization result of the vertebrae corresponds to the inverse arch, the segmentation result of the vertebrae can be subjected to quantitative analysis again, where the quantitative analysis again may be to recalculate the quantization parameter on the segmentation result of the vertebrae, then obtain a requantization result through the recalculated quantization parameter, then compare whether the two quantization results corresponding to the segmentation result of the vertebrae are the same, if not the two quantization results are the same, then the two quantization results corresponding to the segmentation result of the spine may be all stored in the second database, and the spine image and the corresponding other processing results except the quantization results may also be stored in the second database.

That is, the second database stores the data information about the erroneous case as the processing result of the spine obtained after the original image processing module processes the spine image, but the second database may also store some cases in which the processing result of the spine has no error but the doctor feels that the case has been calculated incorrectly. Then, subsequently after the spine detection is completed, the data information of the case with the processing error in the second database may be used to improve the function of the original image processing module, so as to improve the processing performance of the original image processing module, for example, to improve the calculation accuracy.

The image processing method provided in this embodiment may perform a review on the processing result of the spine, and compare the review result of the spine with the initial processing result, and if the review result of the spine is different from the initial processing result, the image processing module in the original mapping relationship may be modified by using the review result of the spine and the initial processing result. In this embodiment, since the original image processing module can be modified by two different processing results of the spine, the performance of the modified image processing module can be better, and thus, the accuracy of the obtained spine processing result is higher when the spine image is subsequently processed.

In another embodiment, another image processing method is provided, which relates to the specific process of how to generate a visual report of the spine and how to display the report and image of the spine. On the basis of the above embodiment, as shown in fig. 6, the method may further include the following steps:

s602, the server receives identity information of a detection object corresponding to the spine image; identity information is sent to the server by the image management subsystem.

S604, the server generates a visual spine image and a spine detection report of the detection object based on the spine processing result and the identity information of the detection object corresponding to the spine image.

And S606, the server displays the visualized spine image of the detection object and the spine detection report on the display interface after associating the visualized spine image with the spine detection report.

The identity information of the detection object can be an identity card number, a telephone number, a work card number, a micro-signal number, height, gender, age and the like of the detection object.

Specifically, a blank detection report may be preset, and the contents of the detection report, such as identity information of the detection object, a quantization result, a segmentation image, and the like, may be listed above; and then after obtaining the identity information of the detection object, the processing result of the vertebra corresponding to the detection object and the vertebra image, correspondingly outputting the identity information of the detection object, the processing result of the vertebra and the vertebra image to a corresponding position of a blank detection report so as to obtain a detection report of the detection object. In addition, based on the obtained processing result of the spine, technologies such as MPR (multi-planar reconstruction), 3D display, and 4D display may be used to generate visual display images of the spine such as 2D, 3D, and 4D, where the MPR display image of 2D may display a multi-tissue grayscale image of the spine and highlight a lesion on the spine, the 3D display image may display a multi-tissue reconstruction result of the spine and highlight a lesion on the spine, and the 4D display image may display a curvature of the spine and a normal movement trajectory of the spine in animation.

In addition, after obtaining the spine display image of the detection object and the spine detection report, the spine display image and the spine detection report may be associated with each other and displayed together, where the spine display image corresponds to the description text in the spine detection report one by one, for example: selecting a report character of 'waist 4/5 with intervertebral disc protruding towards the left rear side of the intervertebral disc', highlighting the processing results of the vertebrae such as the waist 4, the waist 5 and the intervertebral disc, and grading the volumes, sizes, narrowness and severity of the waist 4, the waist 5 and the intervertebral disc in the display interface; similarly, the tissues such as vertebrae to be analyzed can be selected on the display interface, and whether the processing result of the vertebrae has corresponding text description in the diagnosis report can be checked, so that the corresponding image and the corresponding text can be checked from the text.

The image processing method provided in this embodiment may generate a visualized spine image and a spine detection report based on the identity information of the detection object, the processing result of the corresponding spine, and the spine image, and display the visualized spine image and the spine detection report in a correlated manner. In the embodiment, since the visualized spine display image and the spine detection report can be generated, the follow-up observation of the doctor can be facilitated, so as to obtain a more accurate detection result.

In another embodiment, in order to facilitate a more detailed description of the technical solution of the present application, the following description is made in conjunction with two more detailed embodiments, where the two embodiments take servers as an intranet server inside a hospital and an extranet server outside the hospital respectively as an example, and first, when the server is an intranet server inside the hospital, the method may include the following steps a 1-A8:

a1, the intranet server receives the spine image sent by the image management subsystem via the gateway (also called front-end processor) and the router.

A2, the intranet server receives a processing request for the spine image sent by the client; the processing request includes at least one processing mode.

And A3, the intranet server obtains each target image processing module corresponding to each processing mode from a preset mapping relation based on each processing mode.

A4, the intranet server processes the spine image by adopting each target image processing module to obtain the processing result of the spine in the spine image, and sends the processing result of the spine to the client.

A5, the intranet server obtains the spine rechecking processing result obtained after the spine image is processed again, compares the spine processing result with the spine rechecking processing result, and if the spine processing result is different from the spine rechecking processing result, determines the spine processing result, the spine rechecking processing result and the spine image as typical case data information and stores the typical case data information in the second database.

A6, the intranet server improves the image processing module in the mapping relation based on the typical case data information in the second database.

A7, the intranet server receives an update request sent by the client; the update request includes identity information of the client; verifying the identity information of the client; if the identity information of the client is successfully verified, receiving a newly added image processing module and a corresponding newly added processing mode sent by the client; and updating the mapping relation based on the newly added image processing module and the corresponding newly added processing mode.

A8, the intranet server receives the identity information of the detection object corresponding to the spine image sent by the image management subsystem; generating a visual spine image of the detection object and a spine detection report of the detection object based on the processing result of the spine and the identity information of the detection object corresponding to the spine image; and displaying the visualized spine image of the detection object and the spine detection report on a display interface after the visualization spine image of the detection object is associated with the spine detection report.

For example, referring to fig. 7, the PACS/RIS system and the CT/MR workstation transmit DICOM data of the spine to the front-end processor, the front-end processor transmits the DICOM data of the spine to the AI server through the router, the AI server performs disease classification and quantitative calculation on the DICOM data of the spine, and then returns the processing result of the spine to the doctor workstation through the router, so that the doctor workstation can obtain multi-organization segmentation and quantitative data, and then can store the data in the first database (i.e. the database server in the figure) and store the related data of the error case in the second database (i.e. the typical case database in the figure).

Next, when the server is an extranet server outside the hospital and the extranet server is divided into an external web server and an external AI server, the method may include the following steps B1-B10:

b1, the extranet server receives the spine image sent by the image management subsystem via the intranet router, the gateway (may also be called as a front-end processor), and the extranet router.

B2, the extranet server receives a processing request for the spine image sent by the client; the processing request includes at least one processing mode.

And B3, the extranet server obtains each target image processing module corresponding to each processing mode from the preset mapping relation based on each processing mode.

And B4, the extranet server processes the spine image by adopting each target image processing module to obtain a spine processing result in the spine image, and sends the spine processing result to the client.

And B5, the extranet server encrypts the spine processing result by adopting a preset encryption algorithm and stores the spine encryption processing result into the first database.

B6, the external network server receives the login information sent by the client; verifying the login information, and decrypting the encrypted processing result of the vertebra after the login information is successfully verified to obtain a decrypted processing result of the vertebra; and sending the decryption processing result of the spine to the client.

And B7, the extranet server acquires a spine rechecking processing result obtained after the spine image is processed again, compares the spine processing result with the spine rechecking processing result, determines the spine processing result, the spine rechecking processing result and the spine image as typical case data information if the spine processing result is different from the spine rechecking processing result, and stores the typical case data information into a second database.

B8, the extranet server improves the image processing module in the mapping relation based on the typical case data information in the second database.

B9, the extranet server receives the update request sent by the client; the update request includes identity information of the client; verifying the identity information of the client; if the identity information of the client is successfully verified, receiving a newly added image processing module and a corresponding newly added processing mode sent by the client; and updating the mapping relation based on the newly added image processing module and the corresponding newly added processing mode.

B10, the extranet server receives the identity information of the detection object corresponding to the spine image sent by the image management subsystem; generating a visual spine image of the detection object and a spine detection report of the detection object based on the processing result of the spine and the identity information of the detection object corresponding to the spine image; and displaying the visualized spine image of the detection object and the spine detection report on a display interface after the visualization spine image of the detection object is associated with the spine detection report.

Illustratively, referring to fig. 8, the PACS/RIS system and the CT/MR workstation send the DICOM data of the spine to the front-end processor via the intranet router, the front-end processor sends the DICOM data of the spine to the web server via the extranet router, the web server forwards the data to the AI server, the AI server performs disease classification and quantitative calculation on the DICOM data of the spine, and then returns the processing result of the spine to the web server, the web server may encrypt the data, store the encrypted data in the first database (i.e., the database server in the figure), and store the data related to the error case in the second database (i.e., the typical case database in the figure); when a doctor needs to check the processing result of the spine, the encrypted data can be decrypted after the identity information of the client is successfully verified, and the decryption processing result of the spine is returned to the doctor workstation through the extranet router, so that the doctor workstation can obtain multi-organization segmentation and quantitative data.

It should be understood that although the various steps in the flow charts of fig. 2-6 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-6 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.

In one embodiment, as shown in fig. 9, there is provided an image processing apparatus applied to an image processing system including an image management subsystem, a server, and a client, including: a first receiving module 10, a second receiving module 11, a determining module 12 and a processing and sending module 13, wherein:

a first receiving module 10, configured to receive a spine image sent by an image management subsystem;

the second receiving module 11 is configured to receive a processing request for a spine image sent by a client; the processing request comprises at least one processing mode;

the determining module 12 is configured to obtain, based on each processing mode, each target image processing module corresponding to each processing mode from a preset mapping relationship; the mapping relation comprises a corresponding relation between a plurality of processing modes and the image processing module;

and the processing and sending module 13 is configured to process the spine image by using each target image processing module to obtain a processing result of the spine in the spine image, and send the processing result of the spine to the client.

For specific limitations of the image processing apparatus, reference may be made to the above limitations of the image processing method, which are not described herein again.

In another embodiment, on the basis of the above embodiment, if the image processing system further includes a gateway, the first receiving module 10 is further configured to receive a spine image sent by the image management subsystem via the gateway.

In another embodiment, on the basis of the above embodiment, if the server is an extranet server, the apparatus may further include an encryption module, configured to encrypt the processing result of the spine by using a preset encryption algorithm, and store the encryption processing result of the spine in the first database.

Optionally, the processing and sending module 13 may include a receiving unit, a verifying unit, and a sending unit, where:

the receiving unit is used for receiving login information sent by the client;

the verification unit is used for verifying the login information and decrypting the encrypted processing result of the vertebra after the login information is successfully verified to obtain a decrypted processing result of the vertebra;

and the sending unit is used for sending the decryption processing result of the vertebra to the client.

In another embodiment, another image processing apparatus is provided, and on the basis of the above embodiment, the apparatus may further include an update module, configured to receive an update request sent by a client; the update request includes identity information of the client; verifying the identity information of the client; if the identity information of the client is successfully verified, receiving a newly added image processing module and a corresponding newly added processing mode sent by the client; and updating the mapping relation based on the newly added image processing module and the corresponding newly added processing mode.

In another embodiment, another image processing apparatus is provided, and on the basis of the above embodiment, the apparatus may further include an improvement module, configured to obtain a result of the spine rechecking process, and compare the result of the spine process with the result of the spine rechecking process; the rechecking processing result of the vertebra is a processing result obtained after the vertebra image is processed again; if the processing result of the vertebra is different from the rechecking processing result of the vertebra, determining the processing result of the vertebra, the rechecking processing result of the vertebra and the vertebra image as typical case data information, and storing the typical case data information into a second database; based on the typical case data information in the second database, the image processing module in the mapping relationship is improved.

In another embodiment, another image processing apparatus is provided, and on the basis of the above embodiment, the apparatus may further include a generation display module, configured to receive identity information of a detection object corresponding to the spine image; the identity information is sent by the image management subsystem; generating a visual spine image and a spine detection report of the detection object based on the processing result of the spine and the identity information of the detection object corresponding to the spine image; and displaying the visualized spine image of the detection object and the spine detection report on a display interface after the visualization spine image of the detection object is associated with the spine detection report.

The respective modules in the image processing apparatus described above may be wholly or partially implemented by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, an image processing system is provided, which comprises an image management subsystem, a server and a client, wherein the internal structure of the server can be as shown in fig. 10. The server includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the server is configured to provide computing and control capabilities. The memory of the server comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the server is used for storing image processing data. The network interface of the server is used for communicating with an external terminal through network connection. The computer program is executed by a processor to implement an image processing method.

Those skilled in the art will appreciate that the architecture shown in fig. 10 is a block diagram of only a portion of the architecture associated with the subject application, and does not constitute a limitation on the servers to which the subject application applies, as a particular server may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, there is provided an image processing system comprising an image management subsystem, a server, a client, the server comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the following steps when executing the computer program:

receiving a spine image sent by an image management subsystem;

receiving a processing request for a spine image sent by a client; the processing request comprises at least one processing mode;

based on each processing mode, obtaining each target image processing module corresponding to each processing mode from a preset mapping relation; the mapping relation comprises a corresponding relation between a plurality of processing modes and the image processing module;

and processing the spine image by adopting each target image processing module to obtain a processing result of the spine in the spine image, and sending the processing result of the spine to the client.

In one embodiment, the processor, when executing the computer program, further performs the steps of:

and receiving the spine image sent by the image management subsystem through the gateway.

and encrypting the spine processing result by adopting a preset encryption algorithm, and storing the spine encryption processing result into a first database.

receiving login information sent by a client; verifying the login information, and decrypting the spine encryption processing result after the login information is successfully verified to obtain a spine decryption processing result; and sending the decryption processing result of the spine to the client.

receiving an updating request sent by a client; the update request includes identity information of the client; verifying the identity information of the client; if the identity information of the client is successfully verified, receiving a newly added image processing module and a corresponding newly added processing mode sent by the client; and updating the mapping relation based on the newly added image processing module and the corresponding newly added processing mode.

obtaining a rechecking processing result of the vertebra, and comparing the processing result of the vertebra with the rechecking processing result of the vertebra; the rechecking processing result of the vertebra is a processing result obtained after the vertebra image is processed again; if the processing result of the vertebra is different from the rechecking processing result of the vertebra, determining the processing result of the vertebra, the rechecking processing result of the vertebra and the vertebra image as typical case data information, and storing the typical case data information into a second database; based on the typical case data information in the second database, the image processing module in the mapping relationship is improved.

receiving identity information of a detection object corresponding to the spine image; the identity information is sent by the image management subsystem; generating a visual spine image and a spine detection report of the detection object based on the processing result of the spine and the identity information of the detection object corresponding to the spine image; and displaying the visualized spine image of the detection object and the spine detection report on a display interface after the visualization spine image of the detection object is associated with the spine detection report.

In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:

receiving a spine image sent by an image management subsystem;

In one embodiment, the computer program when executed by the processor further performs the steps of:

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. An image processing method is applied to an image processing system, the image processing system comprises an image management subsystem, a server and a client, and the method comprises the following steps:

the server receives the spine image sent by the image management subsystem;

and the server processes the spine image by adopting each target image processing module to obtain a processing result of the spine in the spine image and sends the processing result of the spine to the client.

2. The method of claim 1, wherein the image processing system further comprises a gateway, and wherein the server receives the spine image transmitted by the image management subsystem, comprising:

3. The method of claim 1, wherein the server is an extranet server, the method further comprising:

and the extranet server encrypts the processing result of the vertebra by adopting a preset encryption algorithm and stores the encryption processing result of the vertebra into a first database.

4. The method of claim 3, wherein sending the processing results of the spine to the client comprises:

the external network server receives login information sent by the client;

the extranet server verifies the login information and decrypts the encrypted processing result of the vertebra after the login information is successfully verified to obtain a decrypted processing result of the vertebra;

and the extranet server sends the decryption processing result of the spine to the client.

5. The method according to any one of claims 1-4, further comprising:

the server receives an updating request sent by the client; the update request comprises identity information of the client;

the server verifies the identity information of the client;

and the server updates the mapping relation based on the newly-added image processing module and the corresponding newly-added processing mode.

6. The method according to any one of claims 1-4, further comprising:

and the server improves the image processing module in the mapping relation based on the typical case data information in the second database.

7. The method according to any one of claims 1-4, further comprising:

the server receives identity information of a detection object corresponding to the spine image; the identity information is sent to the server by the image management subsystem;

and the server displays the visualized spine image and the spine detection report on a display interface after associating the visualized spine image with the spine detection report.

8. An image processing apparatus applied to an image processing system including an image management subsystem, a server, and a client, the apparatus comprising:

the second receiving module is used for receiving a processing request of the spine image sent by the client; the processing request comprises at least one processing mode;

the determining module is used for obtaining each target image processing module corresponding to each processing mode from a preset mapping relation; the mapping relation comprises a corresponding relation between a plurality of processing modes and the image processing module;

9. An image processing system comprising an image management subsystem, a server, a client, the server comprising a memory and a processor, the memory storing a computer program which when executed by the processor implements the steps of the method of any of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.