CN114240880A

CN114240880A - Medical scanning data processing method and device, medical equipment and storage medium

Info

Publication number: CN114240880A
Application number: CN202111545189.9A
Authority: CN
Inventors: 肖月庭; 阳光; 郑超
Original assignee: Shukun Beijing Network Technology Co Ltd
Current assignee: Shukun Beijing Network Technology Co Ltd
Priority date: 2021-12-16
Filing date: 2021-12-16
Publication date: 2022-03-25

Abstract

The application provides a medical scanning data processing method, a medical scanning data processing device, medical equipment and a storage medium, wherein the method comprises the following steps: acquiring medical scanning data to be processed, integrating the medical scanning data according to the scanning feature categories of the medical scanning data to obtain a plurality of target medical scanning data sets, after the preset focus identification algorithm corresponding to each target medical scanning data set is determined, focus identification is carried out on each target medical scanning data set based on the preset focus identification algorithm to obtain a focus identification result of each target medical scanning data set, finally, the focus identification results of each target medical scanning data set are fused to obtain focus information, the medical scanning data of multiple scanning format categories are processed at the same time, the processing efficiency of the medical scanning data is effectively improved, a large amount of information data is provided for the subsequent acquisition of the focus information, meanwhile, the accuracy of focus information is effectively improved by integrating, processing and refining the processing granularity of medical scanning data.

Description

Medical scanning data processing method and device, medical equipment and storage medium

Technical Field

The present application relates to the technical field of medical devices, and in particular, to a medical scan data processing method, an apparatus, a medical device, and a computer-readable storage medium (storage medium for short).

Background

With the development of medical diagnosis and treatment technology, the role of medical image data in auxiliary diagnosis and treatment is more and more important. Physicians can usually determine the location and type of disease of patients through medical images, and take corresponding medical measures for patients.

Due to the characteristics of human physiological tissues, different scanning format types such as CT, MR, ultrasound and the like are needed to scan the corresponding part of the patient during image acquisition, so as to obtain scanning data of different scanning format types. However, for the scan data of different scan format categories, the corresponding processing algorithm is often needed to be adopted to separately complete the lesion identification to obtain the responsive lesion information, the processing process is complex, the processing time of the scan data is long, the efficiency is low, and the accuracy rate of identifying the lesion is low.

Disclosure of Invention

In view of the above, it is necessary to provide a medical scan data processing method, an apparatus, a medical device and a storage medium for improving the processing efficiency of medical scan data.

In a first aspect, the present application provides a medical scan data processing method, including:

acquiring medical scanning data to be processed;

integrating the medical scanning data according to the scanning feature categories of the medical scanning data to obtain a plurality of target medical scanning data sets; wherein the scan feature categories of the medical scan data in the target medical scan data set are the same;

determining a preset focus identification algorithm corresponding to each target medical scanning data set, and performing focus identification on each target medical scanning data set based on the preset focus identification algorithm to obtain a focus identification result of each target medical scanning data set;

and fusing the focus identification results of the target medical scanning data sets to obtain focus information.

In some embodiments of the present application, the target medical scan data set comprises a first medical scan data set and a second medical scan data set;

according to the scanning feature category of the medical scanning data, the medical scanning data is integrated to obtain a plurality of target medical scanning data sets, and the method comprises the following steps:

dividing medical scanning data of different scanning feature classes into different first medical scanning data sets;

any two or more first medical scan data sets are combined into a second medical scan data set.

In some embodiments of the present application, the scan feature classes include a first scan feature class and a second scan feature class;

screening candidate medical scanning data with a first scanning feature category as a target first scanning feature category from the medical scanning data;

and according to the second scanning feature category of the candidate medical scanning data, performing integration processing on the candidate medical scanning data to obtain a plurality of target medical scanning data sets.

In some embodiments of the present application, the scan characteristic category includes a scan lesion category, a scan location category, or a scan format category.

In some embodiments of the present application, the integrating the medical scanning data according to the scanning feature category of the medical scanning data to obtain a plurality of target medical scanning data sets includes:

integrating medical scanning data according to the scanning focus category and the scanning format category of the medical scanning data to obtain a plurality of target medical scanning data sets; wherein, the scanning focus category and the scanning format category of the medical scanning data in the target medical scanning data set are the same;

the method comprises the following steps of identifying focuses of all target medical scanning data sets based on a preset focus identification algorithm to obtain focus identification results of all target medical scanning data sets, wherein the focus identification results comprise:

determining two target medical scanning data with associated regions according to the scanning focus category of each target medical scanning data in the target medical scanning data set;

acquiring difference data between two target medical scanning data with associated areas;

and acquiring a focus identification result of the target medical scanning data set according to the difference data.

In some embodiments of the present application, acquiring medical scan data to be processed comprises:

acquiring first medical scan data of a subject user;

acquiring second medical scanning data from the historical medical scanning data of a target user according to the scanning feature category of the first medical scanning data, wherein the scanning feature category of the second medical scanning data is the same as that of the first scanning data;

the first medical scan data and the second medical scan data are used as medical scan data to be processed.

In some embodiments of the present application, the lesion information includes at least one of lesion location information, lesion image information, and lesion trend information.

In some embodiments of the present application, the predetermined lesion recognition algorithm includes at least one of a neural network algorithm, a support vector machine algorithm, and a wavelet transform algorithm.

In some embodiments of the present application, the neural network algorithm includes a region segmentation network, a region classification network, and a region location network;

inputting medical scanning data in the target medical scanning data set into a region segmentation network to obtain focus prediction regions in the medical scanning data;

inputting the focus prediction region into a region classification network, and determining a focus target region from the focus prediction region;

and acquiring the position information and the image information of the focus target area through a regional positioning network.

In a second aspect, the present application provides a medical scan data processing apparatus, the apparatus comprising:

the scanning data acquisition module is used for acquiring medical scanning data to be processed;

the scanning data integration module is used for integrating the medical scanning data according to the scanning feature categories of the medical scanning data to obtain a plurality of target medical scanning data sets; wherein the scan feature categories of the medical scan data in the target medical scan data set are the same;

the identification result acquisition module is used for determining a preset focus identification algorithm corresponding to each target medical scanning data set, and identifying the focus of each target medical scanning data set based on the preset focus identification algorithm to obtain a focus identification result of each target medical scanning data set;

and the focus information acquisition module is used for fusing focus identification results of the target medical scanning data sets to obtain focus information.

In a third aspect, the present application further provides a medical device, the server comprising:

one or more processors;

a memory; and

one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the processor to implement the medical scan data processing method.

In a fourth aspect, the present application further provides a computer readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to perform the steps in the medical scan data processing method.

In a fifth aspect, embodiments of the present application provide a computer program product or a computer program comprising computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the method provided by the first aspect.

According to the medical scanning data processing method, the medical scanning data processing device, the medical equipment and the storage medium, a plurality of target medical scanning data sets are obtained by acquiring medical scanning data to be processed and integrating the medical scanning data according to the scanning feature categories of the medical scanning data; after a preset focus identification algorithm corresponding to each target medical scanning data set is determined, focus identification is carried out on each target medical scanning data set based on the preset focus identification algorithm to obtain a focus identification result of each target medical scanning data set, finally, the focus identification results of each target medical scanning data set are fused to obtain focus information, medical scanning data of multiple scanning format types are processed simultaneously, the processing efficiency of the medical scanning data is effectively improved, a large amount of information data are provided for subsequent acquisition of the focus information, the medical scanning data are integrated according to scanning feature types, and then data processing is carried out according to the integrated processing result, the processing granularity of the medical scanning data is refined while the data quantity is kept, and the accuracy of the focus information is effectively improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a schematic view of a medical scan data processing method according to an embodiment of the present application;

FIG. 2 is a flow chart of a medical scan data processing method in an embodiment of the present application;

FIG. 3 is a flow chart of another medical scan data processing method in an embodiment of the present application;

FIG. 4 is a schematic structural diagram of a medical scan data processing apparatus in an embodiment of the present application;

fig. 5 is a schematic structural diagram of a computer device in an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

In the description of the present application, the terms "first", "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, features defined as "first", "second", may explicitly or implicitly include one or more of the described features. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.

In the description of the present application, the word "for example" is used to mean "serving as an example, instance, or illustration". Any embodiment described herein as "for example" is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the invention. In the following description, details are set forth for the purpose of explanation. It will be apparent to one of ordinary skill in the art that the present invention may be practiced without these specific details. In other instances, well-known structures and processes are not shown in detail to avoid obscuring the description of the invention with unnecessary detail. Thus, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

In the embodiment of the present application, it should be noted that, as the medical scan data processing method provided by the present application is executed in a computer device, processing objects of each computer device all exist in the form of data or information, for example, a scan feature type, which is substantially scan feature type information, it can be understood that, in the following embodiments, if a recognition result, a position, an image, and the like are all corresponding data, so that the computer device performs processing, and details are not described herein.

In the embodiment of the present application, it should be further noted that the medical scan data processing method provided in the embodiment of the present application may be applied to a medical scan data processing system as shown in fig. 1. Wherein the medical scan data processing system comprises a terminal 100 and a server 200, the terminal 100 may be a device comprising both receiving and transmitting hardware, i.e. a device having receiving and transmitting hardware capable of performing a bi-directional communication over a bi-directional communication link. Such a device may include: a cellular or other communication device having a single line display or a multi-line display or a cellular or other communication device without a multi-line display. The terminal 100 may specifically be a desktop terminal or a mobile terminal, and the terminal 100 may also specifically be one of a mobile phone, a tablet computer, a notebook computer, and the like, or a medical device having a function of scanning and acquiring medical image, such as a CT scanner, a nuclear magnetic resonance scanner, and an ultrasound scanner. The server 200 may be an independent server, or may be a server network or a server cluster composed of servers, which includes but is not limited to a computer, a network host, a single network server, a plurality of network server sets, or a cloud server composed of a plurality of servers. Among them, the Cloud server is constituted by a large number of computers or web servers based on Cloud Computing (Cloud Computing).

It will be understood by those skilled in the art that the application environment shown in fig. 1 is only one application scenario related to the present application, and does not constitute a limitation on the application scenario of the present application, and that other application environments may further include more or less computer devices than those shown in fig. 1, for example, only 1 server 200 is shown in fig. 1, and it will be understood that the medical scan data processing system may further include one or more other servers, and is not limited herein. In addition, as shown in fig. 1, the medical scan data processing system may further include a memory for storing data, such as medical scan data.

Referring to fig. 2, an embodiment of the present application provides a medical scan data processing method, which is mainly exemplified by applying the method to the server 200 in fig. 1, and the method includes steps S210 to S240, which are as follows:

s210, medical scanning data to be processed are obtained.

The medical scanning data includes, but is not limited to, data obtained by different scanning modes such as CT (Computed Tomography), MRI (Magnetic Resonance Imaging), ultrasound, and the like, and the medical scanning data obtained by the different scanning modes are medical scanning data of different scanning format types.

Further, the data format of the medical scan data includes, but is not limited to, an image data format, a text data format, and a label data format, and it is understood that the medical scan data in the image data format refers to medical image images obtained by different scanning modes, and the medical scan data in the text data format or the label data format refers to label information of the medical image images obtained by different scanning modes, where the text data format may be a TXT format, the label data format may be a datalist format, and the text data format or the label data format may be extracted from electronic reports such as medical sheets and medical record reports, or may be obtained by text scanning paper reports such as medical sheets and medical record reports. In particular, the server may acquire multiple medical scan data of the same patient from different medical scanning devices.

S220, integrating the medical scanning data according to the scanning feature categories of the medical scanning data to obtain a plurality of target medical scanning data sets; wherein the scan feature categories of the medical scan data in the target medical scan data set are the same.

Wherein the scanning feature category includes, but is not limited to, a scanning lesion category, a scanning location category, or a scanning format category. The scan lesion category is used to identify a disease type corresponding to a lesion in the medical scan data, and different scan lesion categories correspond to different disease types, for example, the scan lesion category may include a tuberculosis lesion, a tumor lesion, a calcified lesion, a bleeding lesion, and the like. The scan location category is used to identify the organ tissue corresponding to the medical scan data, or the scan location category is used to identify the organ tissue scanned by the medical scan data, and different scan location categories correspond to different organ tissues, for example, the scan location categories include heart, liver, brain, etc. The scan format class is used to identify a scan class of the medical scan data, and the different scan format classes correspond to different scan format classes, for example, the scan format classes include a CT scan format class, an MRI scan format class, a CTA scan format class, and the like.

Specifically, after the server acquires the medical scanning data, the server may identify the medical scanning data in advance to acquire a scanning feature category corresponding to the medical scanning data. As described above, the data format of the medical scanning data includes an image data format, a text data format, and a label data format, when the medical scanning data is in the image data format, the medical scanning data may be processed through an image recognition algorithm to recognize a scanning feature category corresponding to the medical scanning data, specifically, an image classification model may be trained in advance, when the medical scanning data is acquired, the medical scanning data is directly input into the image classification model, and the scanning feature category is acquired through the image classification model; when the medical scanning data is in a text data format, the scanning feature category corresponding to the medical scanning data can be obtained through a character recognition algorithm; when the medical scanning data is in a label data format, the label value of the corresponding label can be acquired so as to determine the corresponding scanning feature category.

After the scanning feature categories and the scanning format categories of the medical scanning data are acquired, the server integrates the medical scanning data, specifically, the medical scanning data can be classified according to the scanning feature categories, and the medical scanning data with the same scanning feature categories are used as a target medical scanning data set.

For example, the scanning feature category is used as a scanning focus category, and medical scanning data is classified according to the scanning focus category of the medical scanning data to obtain a plurality of target medical scanning data sets; the categories of the scanned lesions of the medical scan data in the target medical scan data set are the same. For example, medical scan data for which the scan lesion category is a tumor lesion is divided into a target medical scan data set, medical scan data for which the scan lesion category is a tuberculosis lesion is divided into a target medical scan data set, and so on.

For another example, taking the scanning feature category as the scanning position category as an example, classifying the medical scanning data according to the scanning position category of the medical scanning data to obtain a plurality of target medical scanning data sets; the scan position categories of the medical scan data in the target medical scan data set are the same. For example, medical scan data of scan position category of lung is divided into one target medical scan data set, medical scan data of scan position category of brain is divided into one target medical scan data set, and so on.

For another example, taking the scanning feature category as the scanning format category as an example, classifying the medical scanning data according to the scanning format category of the medical scanning data to obtain a plurality of target medical scanning data sets; the scan format categories of the medical scan data in the target medical scan data set are the same. For example, CT medical scan data is divided into a target medical scan data set, MRI medical scan data is divided into a target medical scan data set, CTA medical scan data is divided into a target medical scan data set, etc.

For another example, taking the scanning feature category including the scanning lesion category and the scanning format category as an example, the medical scanning data may be classified according to the scanning lesion category and the scanning format category of the medical scanning data to obtain a plurality of target medical scanning data sets; the medical scan data in the target medical scan data set has the same category of scan lesion and the same category of scan format. Specifically, the medical scanning data sets may be classified according to the types of the scanned lesions to obtain medical scanning data with the same type of the scanned lesions, and then the medical scanning data with the same type of the scanned lesions may be secondarily classified according to the type of the scanning format to obtain target medical scanning data sets with the same type of the scanned lesions and the same type of the scanning format of each medical scanning data. For example, the medical scanning data with the scanning lesion category being tumor lesion and the scanning format category being CT scanning format category is divided into a target medical scanning data set, the medical scanning data with the scanning lesion category being tumor lesion and the scanning format category being MRI scanning format category is divided into a target medical scanning data set, the medical scanning data with the scanning lesion category being tuberculosis lesion and the scanning format category being CT scanning format category is divided into a target medical scanning data set, the medical scanning data with the scanning lesion category being tuberculosis lesion and the scanning format category being MRI scanning format category is divided into a target medical scanning data set, and the like.

For another example, taking the scanning feature category including the scanning position category and the scanning format category as an example, classifying the medical scanning data according to the scanning position category and the scanning format category of the medical scanning data to obtain a plurality of target medical scanning data sets; the lesion location category and the scan format category of the medical scan data in the target medical scan data set are the same. Specifically, the medical scanning data sets may be classified according to the scanning position categories to obtain medical scanning data with the same scanning position category, and then the medical scanning data with the same scanning position category may be secondarily classified according to the scanning format categories to obtain target medical scanning data sets with the same scanning position category and scanning format category of each medical scanning data set. For example, medical scan data with a scan position category of lung and a scan format category of CT scan format category is divided into a target medical scan data set, medical scan data with a scan position category of lung and a scan format category of MRI scan format category is divided into a target medical scan data set, medical scan data with a scan position category of brain and a scan format category of CT scan format category is divided into a target medical scan data set, medical scan data with a scan position category of brain and a scan format category of MRI scan format category is divided into a target medical scan data set, and the like.

It is understood that the scanning feature category may further include a scanning lesion category and a scanning position category, and the server may perform integration processing on the medical scanning data according to the scanning lesion category and the scanning position category to obtain a plurality of target medical scanning data sets, and the specific steps and processes thereof are the same as the examples of the scanning feature category including the scanning position category and the scanning format category, and are not described herein again.

Further, the medical scanning data are integrated, specifically, the medical scanning data can be classified according to the scanning feature categories, the medical scanning data with the same scanning feature category are used as a target medical scanning data set, then the target medical scanning data sets belonging to different scanning feature categories are combined, and the combined data set is also used as a target medical scanning data set. In particular, in one embodiment, the target medical scan data set comprises a first medical scan data set and a second medical scan data set; according to the scanning feature category of the medical scanning data, the medical scanning data is integrated to obtain a plurality of target medical scanning data sets, and the method comprises the following steps: dividing medical scanning data of different scanning feature classes into different first medical scanning data sets; any two or more first medical scan data sets are combined into a second medical scan data set.

Taking the scanning characteristic category as the scanning format category as an example, classifying the medical scanning data according to the scanning format category of the medical scanning data to obtain a plurality of first medical scanning data sets, wherein the scanning format categories of the medical scanning data in the first medical scanning data sets are the same; then, any two or more first medical scanning data sets are combined to obtain a plurality of second medical scanning data sets, and each first medical scanning data set and each second medical scanning data set are respectively used as a target medical scanning data set.

For example, according to the scanning format category of the medical scanning data, the medical scanning data is classified to obtain a first medical scanning data set corresponding to CT medical scanning data, a first medical scanning data set corresponding to MRI medical scanning data, and a first medical scanning data set corresponding to CTA medical scanning data; the CT medical scan data and the first medical scan data set corresponding to the CTA medical scan data are then combined into a second medical scan data set. At this time, the number of the target medical scanning data sets is 4, which are respectively a first medical scanning data set corresponding to CT medical scanning data, a first medical scanning data set corresponding to MRI medical scanning data, a first medical scanning data set corresponding to CTA medical scanning data, and a second medical scanning data set combining CT medical scanning data and CTA medical scanning data.

It is understood that, when the scanning feature category is the scanning lesion category or the scanning position category, the step of integrating the medical scanning data is the same as the step of integrating the scanning feature category in the scanning format category, and the description thereof is omitted here.

In addition, the medical scanning data is integrated, specifically, the target medical scanning data can be classified according to one scanning feature category to obtain a plurality of different classification results, then each classification result is subjected to secondary classification according to another scanning feature category, and finally the obtained classification result is used as a target medical scanning data set. In particular, in one embodiment, the scan feature classes include a first scan feature class and a second scan feature class; according to the scanning feature category of the medical scanning data, the medical scanning data is integrated to obtain a plurality of target medical scanning data sets, and the method comprises the following steps: screening candidate medical scanning data with a first scanning feature category as a target first scanning feature category from the medical scanning data; and according to the second scanning feature category of the candidate medical scanning data, performing integration processing on the candidate medical scanning data to obtain a plurality of target medical scanning data sets.

Taking the first scanning characteristic category as the scanning focus category and the second scanning characteristic category as the scanning format category as an example, the medical scanning data can be classified according to the scanning focus category to obtain the medical scanning data with the same scanning focus category; secondly, classifying the medical scanning data with the scanning focus category as the target scanning focus category according to the scanning format category; and finally, obtaining a plurality of target medical scanning data sets of which the scanning format types of the medical scanning data are the same and the scanning focus type is the target scanning focus type.

For example, the target scan lesion category is a tumor lesion; the server classifies the medical scanning data according to the scanning focus category to obtain the medical scanning data of which the scanning focus category is a tumor focus; and then, carrying out secondary classification on the medical scanning data of which the scanning focus category is the tumor focus according to the scanning format category, so as to divide the medical scanning data of which the scanning focus category is the tumor focus and the scanning format category is the CT scanning format category into a target medical scanning data set, divide the medical scanning data of which the scanning focus category is the tumor focus and the scanning format category is the CTA scanning format category into a target medical scanning data set, and divide the medical scanning data of which the scanning focus category is the tumor focus and the scanning format category is the MRI scanning format category into a target medical scanning data set.

In addition, taking the first scanning feature category as the scanning format category and the second scanning feature category as the scanning position category as an example, the medical scanning data may be classified according to the scanning format category to obtain medical scanning data with the same scanning format category, and then the medical scanning data with the scanning format category as the target scanning format category may be secondarily classified according to the scanning position category to finally obtain a plurality of target medical scanning data sets with the same scanning position category and the target scanning format category of the medical scanning data.

For example, the target scan lesion category is the CT scan format category. The server classifies the medical scanning data according to the scanning format category to obtain the medical scanning data of which the scanning format category is the CT scanning format category; and then, carrying out secondary classification on the medical scanning data with the scanning format type of CT scanning format according to the scanning position type, so as to divide the medical scanning data with the scanning format type of CT scanning format and the scanning position of lung into a target medical scanning data set, divide the medical scanning data with the scanning format type of CT scanning format and the scanning position of brain into a target medical scanning data set, and divide the medical scanning data with the scanning format type of CT scanning format and the scanning position of head and neck into a target medical scanning data set.

It can be understood that, according to the second scanning feature category of the candidate medical scanning data, the medical scanning data is integrated to obtain a plurality of target medical scanning data sets, specifically, the candidate medical scanning data of different scanning feature categories may be firstly divided into different first medical scanning data sets, and then any two or more first medical scanning data sets are combined into the second medical scanning data set. The different first medical scan data set and the different second medical scan data set each serve as one target medical scan data set.

It is understood that the specific process of integrating the medical scan data is determined according to the scan feature category of the medical scan data to be processed. For example, if the medical scanning data to be processed includes a plurality of medical scanning data of the same scanning position type, the same scanning lesion type and different scanning format types, the medical scanning data is integrated according to the scanning format types; for another example, if the medical scan data to be processed includes a plurality of medical scan data of the same scan position type but different scan lesion types and scan format types, the medical scan data is integrated according to the scan lesion types and the scan format types.

And S230, determining a preset focus identification algorithm corresponding to each target medical scanning data set, and performing focus identification on each target medical scanning data set based on the preset focus identification algorithm to obtain a focus identification result of each target medical scanning data set.

Specifically, after dividing medical scanning data to be processed into a plurality of target medical scanning data sets, for any one target medical scanning data set, determining a preset lesion identification algorithm corresponding to the target medical scanning data set, and performing lesion identification on each medical scanning number in the target medical scanning data set through the corresponding preset lesion identification algorithm to obtain a lesion identification result.

Specifically, the preset lesion recognition algorithm is used for obtaining a lesion recognition result according to the input medical scanning data, and may include, but is not limited to, at least one of a neural network algorithm, a support vector machine algorithm, and a wavelet transform algorithm.

The corresponding lesion recognition models of the target medical scanning data sets belonging to different scanning feature categories are also different.

For example, taking the scanning feature category as the scanning lesion category as an example, for a target medical scanning data set of any scanning lesion category, performing lesion identification on medical scanning data in the target medical scanning data set based on a preset lesion identification algorithm corresponding to the target medical scanning data set, so as to obtain lesion information corresponding to the scanning lesion category, and obtain a lesion identification result.

And taking the scanning characteristic category as the scanning position category as an example, for a target medical scanning data set of any scanning position category, performing focus identification on medical scanning data in the target medical scanning data set based on a preset focus identification algorithm corresponding to the target medical scanning data set, so as to identify all focus information of the target medical scanning data set on organ tissues corresponding to the scanning position category, and obtaining a focus identification result.

Similarly, when the scanning feature type is the scanning position type, the processing procedure is the same as that when the scanning feature type is the scanning lesion type or the scanning position type, and the description thereof is omitted here.

For another example, taking the scanning feature category including the scanning lesion category and the scanning format category as an example, for a target medical scanning data set with the same scanning lesion category and scanning format category, the server performs lesion identification on medical scanning data in the target medical scanning data set based on a corresponding preset lesion identification algorithm to obtain a lesion identification result on the target medical scanning data set; it is to be understood that the lesion identification results of the target medical scan data set include: and the lesion information related to the disease type corresponding to the scanned lesion category, such as a lesion image, an organ tissue where the lesion is located, a location area of the lesion in the organ tissue, a size of the lesion, and the like.

Specifically, taking a target medical scanning data set with a scanning feature type of calcified lesion and a scanning format type of CT scanning format as an example, dividing medical scanning data with a scanning lesion type of calcified lesion and a scanning format type of CT scanning format into a group of target medical scanning data sets, and performing lesion identification on all medical scanning data groups in the target medical scanning data sets through a preset lesion identification algorithm corresponding to the target medical scanning data sets to acquire lesion information related to calcified lesions, such as a lesion image, an organ tissue with calcified property, a region position where calcification occurs in the organ tissue, and the like. More specifically, the preset lesion identification algorithm includes a lesion identification model for identifying calcified lesions, the target medical scanning data set with the scanning lesion category being calcified lesions and the scanning format category being CT scanning format category includes medical scanning images of calcification of heart region, medical scanning images of calcification of lung, and medical scanning images of calcification of liver, and after the group of medical scanning data is obtained, all medical scanning images of the target medical scanning data set are input to the lesion identification model for identifying calcified lesions, so as to obtain information such as positions and images of calcified lesions in various organ tissues.

For another example, taking the scanning feature category including the scanning position category and the scanning format category as an example, for a target medical scanning data set with the same scanning position category and scanning format category, based on a corresponding preset lesion recognition algorithm, performing lesion recognition on medical scanning data in the target medical scanning data set to obtain a lesion recognition result on the target medical scanning data set; it is to be understood that the lesion identification results of the target medical scan data set include: the lesion information in the organ tissue corresponding to the scanning position category, such as an image of the lesion, the organ tissue where the lesion is located, the coordinate position of the lesion in the organ tissue, the type of disease corresponding to the lesion, the size of the lesion, and the like.

Specifically, taking the example that the scanning position category is a brain and the scanning format category is an MRI scanning format category, the medical scanning data whose scanning position category is a brain and the scanning format category is an MRI scanning format category is divided into a target medical scanning data set, and all medical scanning data sets in the target medical scanning data set are subjected to lesion identification through a preset lesion identification algorithm corresponding to the target medical scanning data set, so as to acquire lesion information in the brain, such as a lesion image, a disease type (e.g., tumor, hemorrhage, etc.) corresponding to a lesion, a coordinate position of the lesion in the brain, a size of the lesion, and the like. More specifically, the preset lesion identification algorithm includes lesion identification models for identifying different brain lesions, the medical scanning data with the scanning position category of the brain and the scanning format category of the MRI scanning format category includes medical scanning images of brain thrombus, medical scanning images of brain aneurysm, medical scanning images of brain infarction and the like, and when the set of medical scanning data is obtained, all the medical scanning images of the target medical scanning data set are respectively input into the lesion identification models for identifying different brain lesions, so that information such as positions and images of different lesions in the brain is obtained.

Further, in one embodiment, the lesion identification algorithm is preset as a neural network algorithm, and the neural network algorithm includes a region segmentation network, a region classification network and a region positioning network; the method comprises the following steps of identifying focuses of all target medical scanning data sets based on a preset focus identification algorithm to obtain focus identification results of all target medical scanning data sets, wherein the focus identification results comprise: inputting medical scanning data in the target medical scanning data set into a region segmentation network to obtain focus prediction regions in the medical scanning data; inputting the focus prediction region into a region classification network, and determining a focus target region from the focus prediction region; and acquiring the position information and the image information of the focus target area through a regional positioning network.

When the medical scanning data is image data, the medical scanning data can be input into the model corresponding to the neural network algorithm, and the position information and the image information of the region where the focus is located in the medical scanning data are obtained through the model corresponding to the neural network algorithm. The focus prediction region refers to a region of interest obtained by predicting a region where a focus is located in medical scanning data through a neural network algorithm. It can be understood that the lesion prediction region may or may not be the region where the lesion is located, which is finally obtained by the neural network algorithm; the focus target area refers to the area where the focus is finally obtained by the neural network algorithm.

Specifically, the region segmentation network is used for segmenting medical scanning data to obtain a region of interest, namely a prediction region where a focus is located; the region classification network is used for classifying the region of interest to determine whether the region of interest is a focus region or not to obtain a focus target region; the area positioning network is used for determining the position coordinates of the area which is the focus target, and segmenting the image of the area to obtain a focus image. Further, the area division network comprises a U-net network, the area classification network comprises an Alex-net network, and the area positioning network comprises an R-CNN network.

And S240, fusing the focus identification results of the target medical scanning data sets to obtain focus information.

After the focus identification results of each target medical scanning data set are obtained, the focus identification results are integrated, and all focus information related to the medical scanning data is output. The lesion information may include, among other things, an image of the lesion, a type of the lesion (e.g., benign, malignant, ground glass structure, etc.), coordinates of the lesion, etc. It can be understood that after the medical scanning data are integrated, the focus recognition is performed on each target medical scanning data set to obtain a focus recognition result, data of the focus recognition result is often scattered and redundant, and the data operations such as collection, sorting, cleaning and the like are performed on the focus recognition result of each target medical scanning data set to obtain complete focus information.

According to the medical scanning data processing method, a plurality of target medical scanning data sets are obtained by acquiring medical scanning data to be processed and integrating the medical scanning data according to the scanning feature categories of the medical scanning data; after a preset focus identification algorithm corresponding to each target medical scanning data set is determined, focus identification is carried out on each target medical scanning data set based on the preset focus identification algorithm to obtain a focus identification result of each target medical scanning data set, finally, the focus identification results of each target medical scanning data set are fused to obtain focus information, medical scanning data of multiple scanning format types are processed simultaneously, the processing efficiency of the medical scanning data is effectively improved, a large amount of information data are provided for subsequent acquisition of the focus information, the medical scanning data are integrated according to scanning feature types, and then data processing is carried out according to the integrated processing result, the processing granularity of the medical scanning data is refined while the data quantity is kept, and the accuracy of the focus information is effectively improved.

Referring to fig. 3, fig. 3 shows a medical scan data processing method in one embodiment, including:

and S310, acquiring medical scanning data to be processed.

S320, integrating the medical scanning data according to the scanning focus category and the scanning format category of the medical scanning data to obtain a plurality of target medical scanning data sets; wherein the scanning lesion categories and the scanning format categories of the medical scanning data in the target medical scanning data set are the same.

S330, according to the scanning focus category of each target medical scanning data in the target medical scanning data set, two target medical scanning data with associated regions are determined.

S340, difference data between two target medical scanning data with the associated area is acquired.

And S350, acquiring a focus identification result of the target medical scanning data set according to the difference data.

And S360, fusing the focus identification results of the target medical scanning data sets to obtain focus information.

After the medical scanning data is obtained, the server can firstly classify according to the scanning focus categories to obtain a plurality of initial groups of the medical scanning data, the scanning focus categories of the medical scanning data included in each initial group are the same, then carry out secondary classification on the medical scanning data in each initial group according to the scanning format categories to finally obtain a plurality of target medical scanning data sets, and the scanning focus categories and the scanning format categories of the medical scanning data included in each target medical scanning group are the same.

For example, after medical scanning data is acquired, the medical scanning data with the scanning focus category as a tumor focus is divided into an initial group, and the medical scanning data with the scanning focus category as a tuberculosis focus is divided into an initial group; then, the initial grouping of the scanning focus category as the tumor focus is classified secondarily, so that the medical scanning data of which the scanning focus category is the tumor focus and the scanning format category is the CT scanning format category is divided into a target medical scanning data set, the medical scanning data of which the scanning focus category is the tumor focus and the scanning format category is the ultrasonic scanning format category is divided into a target medical scanning data set, similarly, the initial grouping of which the scanning focus category is the tuberculosis focus is classified secondarily, the medical scanning data of which the scanning focus category is the tuberculosis focus and the scanning format category is the CT scanning format category is divided into a target medical scanning data set, the medical scanning data of which the scanning focus category is the tuberculosis focus and the scanning format category is the MRI scanning format category is divided into a target medical scanning data set, and the like.

After the server acquires each target medical scanning data set, the processing modes of any one target medical scanning data set are the same, specifically as follows: the scan location category of the medical scan data included in the target medical scan data set is obtained, and since the scan location category identifies an organ tissue in which a lesion occurs, the target medical scan data having an associated region in the target medical scan data set can be obtained based on the scan location category of the medical scan data.

For example, a CT scan is performed on the heart to obtain CT scan data of the heart and CTA scan data of coronary vessels, and since the CT scan data and the CTA scan data are both of the heart in the scan position category, the CT scan data and the CTA scan data can be determined as target medical scan data having an associated region. For another example, the patient performs CT scanning on the heart twice in the near day to obtain two CT scan data with different scan times, and since the scan position categories of the two CT scan data with different scan times are both hearts, the two CT scan data with different scan times can be determined as the target medical scan data with the associated region.

When two target medical scanning data with associated regions in the target medical scanning data set are determined to be obtained, subtraction operation can be performed on the two target medical scanning data with associated regions to obtain difference data of the target medical scanning data, and it can be understood that the difference data contains detail information related to a lesion, and compared with a lesion identification result obtained by a single medical scanning data, the overall performance and accuracy of lesion information of a lesion identification result obtained based on the difference information of the two target medical scanning data with associated regions are higher.

Specifically, after obtaining the difference data of the target medical scanning data with the associated region, the server may input the difference data into a pre-trained algorithm model, and obtain a lesion identification result through the algorithm model, where the algorithm model includes, but is not limited to, a deep learning neural network algorithm model, an SVM algorithm model, and a haar-wavelet algorithm model.

For example, for a lesion in some tissues, since the distance between organs, tissues or bones is short, the lesion and the organs or bones have an adjacent relationship, which is often difficult to distinguish, and in the process of processing medical scanning data, if a single medical scanning data is used alone to identify a lesion region, a large error occurs, and the accuracy is low; thus, the target medical scan data having an associated region in the target medical scan data set may be subtracted in advance to obtain difference data containing information accurately describing the lesion region.

Taking CT scanning of a brain as an example, when CT scanning of a brain is performed, medical scanning data (e.g., medical imaging data) obtained by CT scanning may show a physiological tissue structure of the brain, but the CT scanning data may have a problem of poor definition for a position close to a blood vessel or a bone; at this time, CT scanning may be performed on cerebral arteries of a brain to obtain CTA scanning data (i.e., a cerebral artery image), and since the types of scanning positions of the CT scanning data and the CTA scanning data are both of the brain, the CT scanning data and the CTA scanning data may be determined as target medical scanning data having a relevant region, and by obtaining difference data between the CT scanning data and the CTA image of the brain and obtaining lesion information, such as lesion image information, lesion position information, and the like, based on the difference data, the lesion information may clearly distinguish a lesion region from peripheral blood vessels or bone regions.

For another example, if a single medical scanning data is used to identify a lesion area in medical scanning data obtained by performing medical scanning twice on the same organ tissue, it is difficult to obtain a change trend of a lesion in the organ tissue from the medical scanning data, and therefore, a subtraction may be performed on target medical scanning data having an associated area in a target medical scanning data set in advance to obtain difference data, where the difference data includes difference information describing a lesion area in two medical scanning data, and the change trend information of a lesion in the organ tissue may be obtained through the difference information, thereby effectively improving the comprehensiveness of lesion information of a lesion identification result.

In one embodiment, acquiring medical scan data to be processed comprises: acquiring first medical scan data of a subject user; acquiring second medical scanning data from the historical medical scanning data of a target user according to the scanning feature category of the first medical scanning data, wherein the scanning feature category of the second medical scanning data is the same as that of the first scanning data; the first medical scan data and the second medical scan data are used as medical scan data to be processed.

The first medical scanning data and the second medical scanning data are medical scanning data of the same target user (namely, the same patient), the first medical scanning data refers to currently obtained medical scanning data, and the historical medical scanning data refers to medical scanning data generated at historical time.

As above, the scan feature category includes, but is not limited to, a scan lesion category, a scan location category, or a scan format category; when the scanning characteristic category is a scanning focus category, second medical scanning data at a historical moment are obtained according to the scanning focus category of the first medical scanning data, the second medical scanning data and the scanning focus category of the first scanning data are the same, and since the scanning focus category is used for identifying a disease type corresponding to a focus, the second medical scanning data at the historical moment are obtained according to the scanning focus category, so that all medical scanning data related to a certain disease type of a certain patient are obtained according to different disease types; when the scanning characteristic type is the scanning position type, the second medical scanning data at the historical moment is obtained according to the scanning position type of the first medical scanning data, the second medical scanning data and the scanning position type of the first scanning data are the same, because the scanning position type is used for identifying the organ tissue of the pathological change, the second medical scanning data at the historical moment is obtained according to the scanning position type, all medical scanning data of a patient related to a certain organ tissue are obtained according to different organ tissues, and through the method, the data volume and the comprehensiveness of the medical scanning data are improved, and when the medical scanning data are subsequently processed, the accuracy of a focus identification result can be effectively improved.

The medical scanning data processing method in the present application is further explained by a specific example:

a patient performs routine examination on the head, neck, heart, liver and other parts in the near day, and corresponding medical image scanning has been performed on the head, neck, heart and liver, specifically, MRI scanning and CT scanning can be performed on the head and neck to obtain head and neck MR scanning data and head and neck CT scanning data, and CT scanning and ultrasonic scanning are performed on the heart to obtain heart CT scanning data and heart ultrasonic scanning data; and carrying out CT scanning and ultrasonic scanning on the liver to obtain liver CT scanning data and liver ultrasonic scanning data.

On a certain day, the patient performs a review of the head, neck, heart, liver and other parts, and performs the medical image scanning on the head, neck, heart and liver again, and it can be understood that the type of the scanning format for performing the medical image scanning on the head, neck, heart and liver at this time is not necessarily the same as the type of the scanning format used on the previous days. After the server acquires the medical scanning data obtained by the rechecking, the server respectively identifies the scanning focus category, the scanning position category and the scanning format category of the medical scanning data, wherein the scanning focus category corresponds to the disease type, the scanning position category corresponds to the organ tissue, and the scanning format category corresponds to the scanning type of the medical scanning data, namely the disease type, the organ tissue category and the scanning type of the medical scanning data are acquired.

Then, the server may obtain medical scanning data with the same scanning lesion type and/or medical scanning data with the same scanning position type and/or medical scanning format type from medical scanning data obtained by medical image scanning performed on a patient on the same day (history) according to the scanning lesion type, the scanning position type and/or the scanning format type of the medical scanning data, and further use the medical scanning data of this time and the medical scanning data of the last day as medical scanning data to be processed.

Specifically, the server may classify medical scanning data to be processed according to a scanning lesion category to obtain initial groups of the medical scanning data, where the scanning lesion categories of the medical scanning data included in each initial group are the same; and secondly, performing secondary classification on the medical scanning data in each initial group according to the scanning format type to finally obtain a plurality of target medical scanning data sets, wherein the scanning focus type and the scanning format type of the medical scanning data included in each target medical scanning group are the same.

For example, the medical scanning data of which the scanning focus category is a tumor focus is divided into an initial group, the medical scanning data of which the scanning focus category is a vascular calcification focus is divided into an initial group, and the medical scanning data of which the scanning focus category is a vascular hemorrhage is divided into an initial group; secondly, performing secondary classification on the initial grouping of the scanning focus category which is the tumor focus, and dividing the medical scanning data of which the scanning focus category is the tumor focus and the scanning format category is the CT scanning format category into a target medical scanning data set, dividing the medical scanning data of which the scanning focus category is the tumor focus and the scanning format category is the ultrasonic scanning format category into a target medical scanning data set, and dividing the medical scanning data of which the scanning focus category is the tumor focus and the scanning format category is the MRI scanning format category into a target medical scanning data set; similarly, the primary group of the scanned lesion type of the vascular calcification lesion is secondarily classified, and the primary group of the scanned lesion type of the vascular hemorrhage lesion is secondarily classified, which is not described herein.

After the target medical scanning data sets are obtained, the server inputs medical scanning data in the target medical scanning data sets into a pre-trained neural network algorithm model aiming at each target medical scanning data set, and the neural network algorithm model is used for obtaining relevant information of focuses according to the input medical scanning data, such as focus images, focus change trend graphs and display graphs of different organ tissues of certain scanning focus categories. For example, the server inputs medical scanning data of which the scanning focus category is a tumor focus and the scanning format category is a CT scanning format category into a pre-trained neural network algorithm model, and the neural network algorithm model outputs a display diagram of the tumor focus in different organ tissues, a change trend diagram of a tumor in a certain organ tissue (for example, a liver), and the like; for another example, the server inputs medical scan data with a scan lesion type of vascular calcification lesion and a scan format type of CT scan format into a pre-trained neural network algorithm model, and the neural network algorithm model outputs a display map of vascular calcification regions in different organ tissues, a trend map of vascular calcification lesions in a certain organ tissue (e.g., heart), and the like.

In addition, the server can also classify the medical scanning data to be processed according to the scanning position category to obtain an initial grouping of the medical scanning data, the scanning position category of the medical scanning data included in each initial grouping is the same, then carry out secondary classification on the medical scanning data in the initial grouping according to the scanning format category to finally obtain a target medical scanning data set, and the scanning position category and the scanning format category of the medical scanning data included in each target medical scanning data set are the same.

For example, the medical scanning data of which the scanning position category is heart is divided into an initial group, the medical scanning data of which the scanning position category is head and neck is divided into an initial group, and the medical scanning data of which the scanning position category is liver is divided into an initial group; secondly, performing secondary classification on the initial group of which the scanning position category is the heart to realize that the medical scanning data of which the scanning position category is the heart and the scanning format category is the CT scanning format category is divided into a target medical scanning data set, the medical scanning data of which the scanning position category is the heart and the scanning format category is the ultrasonic scanning format category is divided into a target medical scanning data set, and the medical scanning data of which the scanning position category is the heart and the scanning format category is the MRI scanning format category is divided into a target medical scanning data set; similarly, the primary group whose scanning position category is head and neck is secondarily classified, and the primary group whose scanning position category is liver is secondarily classified, which is not described herein.

After the target medical scanning data sets are obtained, for each target medical scanning data set, the server inputs medical scanning data in the target medical scanning data set into a pre-trained neural network algorithm model, and the neural network algorithm model is used for obtaining relevant information of a focus according to the input medical scanning data, such as focus images, focus change trend graphs, focus types (such as benign, malignant, ground glass structure and the like), focus coordinate information and the like of all scanned focus categories in the scanning position category (namely a certain organ tissue). For example, the server inputs medical scan data of which the scan lesion type is a tumor lesion and the scan format type is a CT scan format type into a pre-trained neural network algorithm model, the neural network algorithm model outputs a display map of the tumor lesion in different organ tissues, a change trend map of a tumor in a certain organ tissue (for example, a liver), and the like, and for example, the server inputs medical scan data of which the scan position type is a liver and the scan format type is a CT scan format type into the pre-trained neural network algorithm model, the neural network algorithm model outputs a display map of a vascular calcification region in the liver, a display map of a vascular hemorrhage region in the liver, a display map of a tumor region in the liver, a tumor type, and the like.

In order to better implement the medical scan data processing method provided in the embodiment of the present application, on the basis of the medical scan data processing method provided in the embodiment of the present application, an embodiment of the present application further provides a medical scan data processing apparatus, as shown in fig. 4, the medical scan data processing apparatus 400 includes:

a scan data acquisition module 410 for acquiring medical scan data to be processed;

the scanning data integration module 420 is configured to integrate medical scanning data according to scanning feature categories of the medical scanning data to obtain a plurality of target medical scanning data sets; wherein the scan feature categories of the medical scan data in the target medical scan data set are the same;

the recognition result obtaining module 430 is configured to determine a preset lesion recognition algorithm corresponding to each target medical scanning data set, perform lesion recognition on each target medical scanning data set based on the preset lesion recognition algorithm, and obtain a lesion recognition result of each target medical scanning data set;

and a lesion information acquisition module 440, configured to fuse the lesion identification results of the target medical scanning data sets to obtain lesion information.

In some embodiments of the present application, the target medical scan data set comprises a first medical scan data set and a second medical scan data set; a scan data integration module 420, configured to divide medical scan data of different scan feature categories into different first medical scan data sets; any two or more first medical scan data sets are combined into a second medical scan data set.

In some embodiments of the present application, the scan feature classes include a first scan feature class and a second scan feature class; a scan data integration module 420, configured to filter candidate medical scan data from the medical scan data, where the first scan feature category is a target first scan feature category; and according to the second scanning feature category of the candidate medical scanning data, performing integration processing on the candidate medical scanning data to obtain a plurality of target medical scanning data sets.

In some embodiments of the present application, the scan data integration module 420 is specifically configured to integrate medical scan data according to a scan lesion category and a scan format category of the medical scan data to obtain a plurality of target medical scan data sets; wherein, the scanning focus category and the scanning format category of the medical scanning data in the target medical scanning data set are the same; a recognition result obtaining module 430, configured to determine two target medical scanning data having associated regions according to the scanning lesion category of each target medical scanning data in the target medical scanning data set; acquiring difference data between two target medical scanning data with associated areas; and acquiring a focus identification result of the target medical scanning data set according to the difference data.

In some embodiments of the present application, the scan data acquisition module 410 is specifically configured to acquire first medical scan data of a subject user; acquiring second medical scanning data from the historical medical scanning data of a target user according to the scanning feature category of the first medical scanning data, wherein the scanning feature category of the second medical scanning data is the same as that of the first scanning data; the first medical scan data and the second medical scan data are used as medical scan data to be processed.

In some embodiments of the present application, the neural network algorithm includes a region segmentation network, a region classification network, and a region location network; the recognition result obtaining module 430 is configured to input medical scanning data in the target medical scanning data set into the region segmentation network, so as to obtain a focus prediction region in each medical scanning data; inputting the focus prediction region into a region classification network, and determining a focus target region from the focus prediction region; and acquiring the position information and the image information of the focus target area through a regional positioning network.

In some embodiments of the present application, the medical scan data processing apparatus 400 may be implemented in the form of a computer program, which may be run on a computer device as shown in fig. 5. The memory of the computer device may store various program modules constituting the medical scan data processing apparatus 400, such as the scan data acquisition module 410, the classification module 420, the recognition result acquisition module 430, and the lesion information acquisition module 440 shown in fig. 4. The respective program modules constitute computer programs that cause the processor to execute the steps in the medical scan data processing methods of the embodiments of the present application described in the present specification.

For example, the computer device shown in fig. 5 may execute step S210 by the scan data acquisition module 410 in the medical scan data processing apparatus 400 shown in fig. 4. The computer device may perform step S220 through the classification module 420. The computer device may perform step S230 through the recognition result obtaining module 430. The computer device may perform step S240 through the lesion information acquisition module 440. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external computer device through a network connection. The computer program is executed by a processor to implement a medical scan data processing method.

Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In some embodiments of the present application, a medical device is provided, comprising one or more processors; a memory; and one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the processor to perform the steps of the medical scan data processing method described above. Here, the steps of the medical scan data processing method may be the steps in the medical scan data processing method of the above-described embodiments.

In some embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, which is loaded by a processor, so that the processor performs the steps of the medical scan data processing method described above. Here, the steps of the medical scan data processing method may be the steps in the medical scan data processing method of the above-described embodiments.

It will be understood by those of ordinary skill in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when executed. 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).

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 medical scan data processing method, the medical scan data processing apparatus, the computer device, and the storage medium provided in the embodiments of the present application are described in detail above, and a specific example is applied in the present application to explain the principles and embodiments of the present invention, and the description of the embodiments is only used to help understanding the method and the core idea of the present invention; meanwhile, for those skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims

1. A medical scan data processing method, comprising:

acquiring medical scanning data to be processed;

determining a preset lesion identification algorithm corresponding to each target medical scanning data set, and performing lesion identification on each target medical scanning data set based on the preset lesion identification algorithm to obtain a lesion identification result of each target medical scanning data set;

2. The method of claim 1, wherein the target medical scan data set comprises a first medical scan data set and a second medical scan data set;

the integrating the medical scanning data according to the scanning feature categories of the medical scanning data to obtain a plurality of target medical scanning data sets comprises:

any two or more of the first medical scan data sets are combined into a second medical scan data set.

3. The method of claim 1, wherein the scan feature classes comprise a first scan feature class and a second scan feature class;

4. The method of any one of claims 1 to 3, wherein the scan feature category comprises a scan lesion category, a scan location category, or a scan format category.

5. The method according to claim 4, wherein the integrating the medical scan data according to the scan feature category of the medical scan data to obtain a plurality of target medical scan data sets comprises:

integrating the medical scanning data according to the scanning focus category and the scanning format category of the medical scanning data to obtain a plurality of target medical scanning data sets; wherein the scanning lesion categories and the scanning format categories of the medical scanning data in the target medical scanning data set are the same;

the performing lesion identification on each target medical scanning data set based on the preset lesion identification algorithm to obtain a lesion identification result of each target medical scanning data set includes:

acquiring difference data between the two target medical scanning data with the associated areas;

6. The method of claim 1, wherein the acquiring medical scan data to be processed comprises:

acquiring first medical scan data of a subject user;

acquiring second medical scanning data from the historical medical scanning data of the target user according to the scanning feature category of the first medical scanning data, wherein the scanning feature category of the second medical scanning data is the same as the scanning feature category of the first scanning data;

the first medical scan data and the second medical scan data are treated as medical scan data to be processed.

7. The method of any one of claims 1 to 3, wherein the lesion information includes at least one of lesion position information, lesion image information, and lesion change trend information.

8. The method of any one of claims 1 to 3, wherein the pre-determined lesion recognition algorithm comprises at least one of a neural network algorithm, a support vector machine algorithm, and a wavelet transform algorithm.

9. The method of claim 8, wherein the neural network algorithm comprises a region segmentation network, a region classification network, and a region location network;

inputting medical scanning data in the target medical scanning data set into the region segmentation network to obtain focus prediction regions in each medical scanning data;

inputting the focus prediction region into the region classification network, and determining a focus target region from the focus prediction region;

and acquiring the position information and the image information of the focus target region through the region positioning network.

10. A medical scan data processing apparatus, comprising:

the identification result acquisition module is used for determining a preset focus identification algorithm corresponding to each target medical scanning data set, and performing focus identification on each target medical scanning data set based on the preset focus identification algorithm to obtain a focus identification result of each target medical scanning data set;

11. A medical device, characterized in that it comprises:

one or more processors;

a memory; and one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the processor to implement the medical scan data processing method of any one of claims 1 to 7.

12. A computer-readable storage medium, having stored thereon a computer program which is loaded by a processor for performing the steps of the medical scan data processing method of any one of claims 1 to 7.