Automatic generation method and system of clinical image reference map and medium

Abstract

The invention relates to an automatic generation method, system and device for a clinical image reference map and a medium, and the method comprises the steps: a doctor determines the anatomical positioning of a required reference map according to a browsed image, and extracts the image examination category, examination items and basic information of a patient of the patient, and the relative positions of the layer where the anatomical positioning is located in all scanning layers; the method comprises the following steps: matching same image examination items and categories in a hospital image diagnosis report database, matching basic information of a patient, examination equipment and the like according to a priority set by a doctor, determining a retrieval keyword according to anatomical positioning, determining a retrieval structured medical image report statement based on the retrieval keyword, and querying the hospital image report database. Matching the report statement and judging the report as a normal report; and calling the report image, matching a reference atlas layer based on the relative position of the anatomical positioning layer in all scanning layers, automatically generating a reference atlas, and displaying the reference atlas to a physician for reference. According to the invention, accurate and abundant imaging reference images can be provided for imaging diagnosis doctors, and the working efficiency can be improved.

Description

Technical Field

[0001] The present invention relates to the field of medical information technology, and in particular to a method, system and medium for automatically generating a clinical image reference atlas. Background Art

[0002] In recent years, the demand for medical imaging examinations has shown a rapid growth trend. The radiology department is one of the departments with the largest shortage of physicians in my country, and imaging diagnosis work faces tremendous pressure. At the same time, medical imaging diagnosis is very dependent on the physician's work experience, and radiologists need a long period of training and learning to work. With the advancement of hierarchical diagnosis and treatment and the release of primary medical needs, it is necessary to further accelerate the training process of radiologists and improve their work efficiency.

[0003] In clinical film reading, imaging physicians, especially junior physicians, need to refer to normal imaging anatomical atlases of different parts during the diagnosis process due to lack of experience. However, the current imaging anatomical atlases have the following limitations. 1. The CT atlas shows a limited number of anatomical layers, and the magnetic resonance atlas only contains some sequence images; 2. The image quality is limited by the size of the page and the printing level, and the image contrast cannot be adjusted, and the image details are insufficient; 3. The existing imaging anatomical atlases are typical atlases, built around a single person as the core. However, human anatomy has normal variations at the individual level, and there are physiological differences with gender and age, which cannot be fully covered by traditional imaging anatomical atlases; 4. The actual clinical images are affected by the differences in parameter settings, scanning orientation, and image post-processing algorithms of different scanning machines, and there are certain differences from standard images; 5. Paper books are thick, inconvenient to use, difficult to locate quickly and accurately, and time-consuming. The existing imaging anatomical atlases cannot meet the needs of current imaging diagnosis work.

[0004] Based on the above limitations of traditional imaging anatomical atlases, in current imaging diagnosis work, physicians will choose to search for report images with normal imaging diagnosis conclusions in the imaging report database as reference atlases to assist diagnosis. The imaging report is divided into a description and a conclusion part. In the description part, the physician describes all anatomical structures and lesions included in the examination item, and the conclusion gives the imaging diagnosis opinion. Taking the liver as the target anatomical part in the whole abdominal CT plain scan examination as an example, searching for "normal" in the conclusion part requires that all abdominal organs have no lesions in order to be detected. The retrieval accuracy is high, but the number of detection reports is very small. If the patient's age, gender and other basic information are matched, the number of detection reports will be further reduced. Clicking on the detection report can only browse one patient image at a time, and it is impossible to quickly display the target image and reference image on the same screen for comparison. In addition, each time the reference image is browsed, the anatomical structure needs to be re-positioned. The above retrieval and image comparison process is time-consuming and cumbersome, which affects the efficiency of clinical imaging diagnosis and is not conducive to the learning and growth of junior physicians. Summary of the invention

[0005] The purpose of the present invention is to provide a method, system and medium for automatically generating a clinical image reference atlas. The automatic generation of a clinical image reference atlas can provide accurate and rich imaging reference images for imaging diagnostic physicians, which will help improve work efficiency and meet the requirements of imaging decision support. Physicians can learn and compare in practice, which is also conducive to quickly improving the diagnostic level of junior physicians.

[0006] To achieve the above object, in a first aspect, the present invention provides a method for automatically generating a clinical image reference atlas, comprising the following specific steps:

[0007] The physician determines the anatomical location of the required reference atlas based on browsing the patient's images;

[0008] Extract the patient's imaging examination category, examination items, basic patient information, and the relative position of the layer where the anatomical location is located in all scanning layers;

[0009] Match the same imaging examination items and categories in the hospital imaging diagnosis report database, match the patient's basic information and examination equipment according to the priority set by the physician, and determine the search keywords according to the anatomical positioning;

[0010] Determine and retrieve structured medical imaging report statements based on search keywords, query the hospital imaging report database, and determine reports that match the report statements as normal;

[0011] The report image is retrieved, and the reference atlas layer is matched based on the relative position of the layer where the anatomical positioning is located in all scanning layers, and a reference atlas is automatically generated and displayed to the physician for reference.

[0012] The patient's basic information includes the patient's age, gender, preliminary diagnosis, and symptoms. The relative position of the layer where the anatomical location is located in all scanning layers is specifically to extract the image layer number A where the anatomical location is located, and extract the total scanning layer number B. The A / B value is the relative position of the anatomical location in the overall scanning layer number of the image.

[0013] The same imaging examination items and categories are matched in the hospital imaging diagnosis report database, the basic information of the patient and the examination equipment are matched according to the priority set by the physician, and the search keywords are determined according to the anatomical positioning, specifically,

[0014] Automatically match imaging diagnostic reports of the same imaging examination items and categories in the hospital imaging diagnostic report database;

[0015] Read the examination equipment, basic patient information and anatomical location of the image in the imaging diagnosis report;

[0016] According to the priority set by the physician, the correlation between the examination equipment, the patient's basic information and the images viewed by the physician is analyzed;

[0017] Select the imaging diagnostic reports that are highly relevant to the images viewed by the physician;

[0018] Perform sentence recognition on the report description part of the selected imaging diagnostic reports;

[0019] The decision logic in the imaging diagnosis report is determined as keywords through sentence recognition.

[0020] The determination logic includes "none / no obvious abnormality / increase / enlargement / decrease / reduction", "normal" and "display OK".

[0021] The Pearson correlation coefficient method is used to determine the correlation between the scanning equipment, the basic information of the patient and the image browsed by the doctor. The scanning equipment and the basic information of the patient in the read image diagnosis report are defined as sequence X, and the scanning equipment and the basic information of the patient in the image browsed by the doctor are defined as sequence Y. The calculation formula is as follows:

[0022]

[0023] Where: is the mean of the sequence X, is the mean of the sequence Y, x i is the i-th information in sequence X, y i is the i-th information in sequence Y, n is the number of information, P is the Pearson correlation coefficient, and the value of P is between [-1, 1]. The larger the absolute value of P, the higher the correlation between sequences X and Y; the smaller the absolute value of P, the lower the correlation between sequences X and Y.

[0024] The report image is retrieved, and the reference atlas layer is matched based on the relative position of the layer where the anatomical location is located in all scanning layers, and a reference atlas is automatically generated and displayed to the physician for reference, specifically,

[0025] Identify keywords in imaging diagnostic reports through sentence recognition;

[0026] Retrieve and associate to corresponding imaging diagnostic reports based on keywords;

[0027] Extract the image corresponding to the associated imaging diagnosis report;

[0028] According to the degree of relevance of the imaging diagnosis report, the extracted images are collected into a pre-display folder as a reference map for doctors to query.

[0029] In a second aspect, an embodiment of the present application provides a system for automatically generating a clinical image reference atlas, the system comprising: a memory and a processor, the memory comprising a program for a method for automatically generating a clinical image reference atlas, the program for the method for automatically generating a clinical image reference atlas implementing the following steps when executed by the processor: a physician determines the anatomical location of a required reference atlas based on browsing patient images; extracts the patient's imaging examination category, examination items, basic patient information, and the relative position of the layer where the anatomical location is located in all scanning layers; matches the same imaging examination items and categories in a hospital imaging diagnosis report database, matches the patient's basic information and examination equipment, and determines search keywords based on the anatomical location; determines to search for structured medical imaging report statements based on the search keywords, queries the hospital imaging report database, and matches the report statements to determine a normal report; retrieves the report image, matches the reference atlas layer based on the relative position of the layer where the anatomical location is located in all scanning layers, automatically generates a reference atlas, and displays it to the physician for reference.

[0030] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores program code, and when the program code is executed by a processor, the steps of the method for automatically generating a clinical image reference atlas as described above are implemented.

[0031] The beneficial effects of adopting the above embodiment are:

[0032] Clinical imaging reference atlas can display the full range and sequence of anatomical structures, and can freely adjust the image window width and window position to obtain the optimal image contrast. It is superior to traditional paper-based anatomical imaging atlases in terms of the number and quality of references.

[0033] Automatically generate clinical image reference atlases, which can automatically match the patient's age and gender to provide more accurate reference images. It can provide multiple reference atlases that meet the conditions at the same time, which helps to show the normal anatomical structure variation between individuals;

[0034] Automatically generated clinical image reference atlases can accurately match the scanning machine to avoid misjudgment due to differences in examination equipment parameter settings, scanning orientations, and image post-processing algorithms;

[0035] Automatically generate clinical image reference atlases and run them in the background, so doctors do not need to interrupt their diagnosis work by searching for reports separately. At the same time, they can quickly locate the target scanning level and display multiple reference images on the same screen, which helps image diagnosis doctors improve their work efficiency, increase the detection rate of lesions, and improve their diagnosis level.

[0036] The system can personalize the priority of matching conditions to meet the diverse needs of clinicians. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 A flow chart of the method provided in the embodiment of the present application;

[0039] Figure 2 A flow chart of determining search keywords according to anatomical positioning provided in an embodiment of the present application;

[0040] Figure 3 A flowchart for automatically generating a reference atlas and displaying it to a physician for reference provided in an embodiment of the present application;

[0041] Figure 4 This is a brain image of a patient in an embodiment of the present application;

[0042] Figure 5 and Figure 6 A brain image matching the embodiment of the present application;

[0043] Figure 7 This is a screenshot of the structured template and report of an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0046] It should be noted that the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0047] See also Figure 1, a method for automatically generating a clinical image reference atlas, comprising the following specific steps:

[0048] The physician determines the anatomical location of the required reference atlas based on browsing the patient's images;

[0049] Extract the patient's imaging examination category, examination items, basic patient information, and the relative position of the layer where the anatomical location is located in all scanning layers;

[0050] Match the same imaging examination items and categories in the hospital imaging diagnosis report database, match the patient's basic information and examination equipment, and determine the search keywords based on the anatomical location;

[0051] Determine and retrieve structured medical imaging report statements based on search keywords, query the hospital imaging report database, and determine reports that match the report statements as normal;

[0052] The report image is retrieved, and the reference atlas layer is matched based on the relative position of the layer where the anatomical positioning is located in all scanning layers, and a reference atlas is automatically generated and displayed to the physician for reference.

[0053] The patient's basic information includes the patient's age, gender, preliminary diagnosis, and symptoms. The relative position of the layer where the anatomical location is located in all scanning layers is specifically to extract the image layer number A where the anatomical location is located, and extract the total scanning layer number B. The A / B value is the relative position of the anatomical location in the overall scanning layer number of the image.

[0054] like Figure 2 As shown, the same imaging examination items and categories are matched in the hospital imaging diagnosis report database, the basic information of the patient and the examination equipment are matched, and the search keywords are determined according to the anatomical positioning, specifically,

[0055] Automatically match imaging diagnostic reports of the same imaging examination items and categories in the hospital imaging diagnostic report database;

[0056] Read the examination equipment, basic patient information and anatomical positioning in the imaging diagnosis report;

[0057] According to the priority set by the physician, the correlation between the examination equipment, the patient's basic information and the images viewed by the physician is analyzed;

[0058] Select the imaging diagnostic reports that are highly relevant to the images viewed by the physician;

[0059] Perform sentence recognition on the report description part of the selected imaging diagnostic reports;

[0060] The decision logic in the imaging diagnosis report is determined as keywords through sentence recognition.

[0061] To automatically match imaging diagnostic reports of the same imaging examination items and categories in the hospital imaging diagnostic report database, we first need to ensure the consistency of the imaging examination categories, that is, whether the physician is browsing CT images or MRI images, and secondly, we need to ensure the consistency of the imaging examination items, that is, the central organs, chest, abdomen, or musculoskeletal system. The examination equipment information is also an important factor affecting the imaging results. Due to the different precisions of different examination equipment, when matching, the examination equipment of the same model and manufacturer is given priority.

[0062] The determination logic includes "none / no obvious abnormality / increase / enlargement / decrease / reduction", "normal" and "display OK".

[0063] The Pearson correlation coefficient method is used to determine the correlation between the scanning equipment, the basic information of the patient and the image browsed by the doctor. The scanning equipment and the basic information of the patient in the read image diagnosis report are defined as sequence X, and the scanning equipment and the basic information of the patient in the image browsed by the doctor are defined as sequence Y. The calculation formula is as follows:

[0064]

[0065] Where: is the mean of the sequence X, is the mean of the sequence Y, x i is the i-th information in sequence X, y i is the i-th information in sequence Y, n is the number of information, P is the Pearson correlation coefficient, and the value of P is between [-1, 1]. The larger the absolute value of P, the higher the correlation between sequences X and Y; the smaller the absolute value of P, the lower the correlation between sequences X and Y.

[0066] like Figure 3 As shown, the report image is retrieved, and the reference atlas layer is matched based on the relative position of the layer where the anatomical positioning is located in all scanning layers, and a reference atlas is automatically generated and displayed to the physician for reference, specifically,

[0067] Identify keywords in imaging diagnostic reports through sentence recognition;

[0068] Retrieve and associate to corresponding imaging diagnostic reports based on keywords;

[0069] Extract the image corresponding to the associated imaging diagnosis report;

[0070] According to the degree of relevance of the imaging diagnosis report, the extracted images are collected into a pre-display folder as a reference map for doctors to query.

[0071] In this step, the focus is on matching the relative position of the anatomical positioning layer in all scanning layers with the reference atlas layer. For example, the doctor is browsing the 9th layer in the 20-layer CT image of the liver. Then, according to the anatomical positioning, the position value belongs to 9 / 20=0.45. The position value within the range of 0.1 above and below belongs to the position level of the anatomical positioning. At this time, the 7th to 11th layers of the matched 20-layer CT image belong to the position level of the anatomical positioning, and other anatomical positioning are directly excluded, which can increase the matching speed.

[0072] An embodiment of the present application provides a system for automatically generating a clinical image reference atlas, the system comprising: a memory and a processor, the memory comprising a program of a method for automatically generating a clinical image reference atlas, and the program of the method for automatically generating a clinical image reference atlas, when executed by the processor, implements the following steps: a physician determines the anatomical location of a required reference atlas based on browsing patient images; extracts the patient's imaging examination category, examination items, basic patient information, and the relative position of the layer where the anatomical location is located in all scanning layers; matches the same imaging examination items and categories in a hospital imaging diagnosis report database, matches the patient's basic information and examination equipment, and determines search keywords based on the anatomical location; determines to search for structured medical imaging report statements based on the search keywords, queries the hospital imaging report database, and matches the report statements to determine a normal report; retrieves the report image, matches the reference atlas layer based on the relative position of the layer where the anatomical location is located in all scanning layers, automatically generates a reference atlas, and displays it to the physician for reference.

[0073] An embodiment of the present application provides a computer-readable storage medium, which stores program code. When the program code is executed by a processor, the steps of the method for automatically generating a clinical image reference atlas as described above are implemented.

[0074] Example:

[0075] 22 years old; Female; Clinical diagnosis: systemic lupus erythematosus; Clinical symptoms: headache; Examination category: MRI; Examination site: central and facial organs; Examination items: [Head] MRI plain scan; Examination equipment: GE750.

[0076] The junior doctor found that the young woman's cerebral sulci and fissures were widened and suspected brain atrophy, but could not make a clear diagnosis. He needed to refer to the width of the sulci and fissures at the level of the bilateral lateral ventricle bodies in the head MRI T2 FLAIR sequence of a normal female aged 20-25 years.

[0077] The anatomical location is input by the physician as cerebral sulci, and the matching condition is selected as age; the system automatically extracts the examination category, examination site, and examination items and preliminarily delineates the scope of the imaging diagnosis report database, outputs set A, matches patients aged 20-25 years old in set A, and outputs set B. According to the physician's input of "cerebral sulci", the structured medical imaging report sentence is determined to be "no obvious widening of cerebral sulci and fissures", and such patients are matched as set C. Images with GE750 as the examination device are displayed preferentially. The sulci and fissures image at the level of the bilateral lateral ventricle bodies browsed by the physician is the 13th layer of the 20-layer scan image. The reference atlas is automatically displayed and positioned at the level of 13 / 20=0.65 of the overall image layers. The image sequence is identified as T2 FLAIR, and several reference atlases of the head magnetic resonance T2 FLAIR sequences of normal women aged 20-25 years old scanned on the device GE750 at the level of the bilateral lateral ventricle bodies are displayed.

[0078] Figure 4 , browse the patient's images. The first line in the upper right corner is the name of the examination device, the second line is the examination part, and the third line is the sequence name. The 13 / 20 in the lower left corner means that a total of 20 layers were scanned, and the image currently displayed is the 13th layer. The diagnostician suspects that the young woman has brain atrophy (brain atrophy is not common for patients of this age). Matching image 1 Figure 5 As shown, it is a 23-year-old normal female, 14 / 24 layers, matching image 2 as shown Figure 6 The figure shows a 23-year-old normal female with layer 14 / 22. Based on the reference atlas, it was determined that the patient did have widened cerebral sulci and brain atrophy.

[0079] Figure 7 It is the interface of the imaging report system, which can extract basic patient information.

[0080] The image findings are displayed as standardized template report descriptions. If you need to see the normal bile duct, identify the template sentence "no obvious dilatation of the intrahepatic and extrahepatic bile ducts and common bile duct".

[0081] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0082] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0083] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0084] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0085] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0086] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0087] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0088] Those skilled in the art may implement the present invention in a variety of variations without departing from the scope and essence of the present invention, such as using a feature of one embodiment to obtain another embodiment. Any modification, equivalent substitution and improvement made within the technical concept of the present invention shall be within the scope of the present invention.

Claims

1. A method for automatically generating a clinical image reference atlas, characterized in that: The specific steps include: The physician determines the anatomical location of the required reference atlas based on browsing the patient's images; Extract the patient's imaging examination category, examination items, examination equipment, basic patient information, and the relative position of the image layer where the anatomical location is located in all scanned image layers; Match the same imaging examination items and categories in the hospital imaging diagnosis report database, match the patient's basic information and examination equipment, and determine the search keywords based on the anatomical location; Determine and retrieve structured medical imaging report statements based on search keywords, query the hospital imaging report database, and determine reports that match the report statements as normal; The report image is retrieved, and the reference atlas layer is matched based on the relative position of the layer where the anatomical positioning is located in all scanning layers, and a reference atlas is automatically generated and displayed to the physician for reference.

2. The method for automatically generating a clinical image reference atlas according to claim 1, characterized in that: The patient's basic information includes the patient's age, gender, preliminary diagnosis, and symptoms. The relative position of the layer where the anatomical location is located in all scanning layers is specifically to extract the image layer number A where the anatomical location is located, and extract the total scanning layer number B. The A / B value is the relative position of the anatomical location in the overall scanning layer number of the image.

3. The method for automatically generating a clinical image reference atlas according to claim 2, characterized in that: The matching of the same imaging examination items and categories in the hospital imaging diagnosis report database, matching of the basic information of the patient and the examination equipment, and determining the search keywords according to the anatomical positioning are specifically as follows: Automatically match imaging diagnostic reports of the same imaging examination items and categories in the hospital imaging diagnostic report database; Read the examination equipment and basic patient information in the imaging diagnosis report, and read the relative position of the image layer; According to the matching priority set by the physician, the correlation between the examination equipment, the patient's basic information and the images viewed by the physician is analyzed; Select the imaging diagnostic reports that are highly relevant to the images viewed by the physician; Perform sentence recognition on the report description part of the selected imaging diagnostic reports; The decision logic in the imaging diagnosis report is determined as keywords through sentence recognition.

4. The method for automatically generating a clinical image reference atlas according to claim 3, characterized in that: The determination logic includes "none / no obvious abnormality / increase / increase / decrease / reduction", "normal" and "display OK".

5. The method for automatically generating a clinical image reference atlas according to claim 3, characterized in that: The Pearson correlation coefficient method is used to determine the correlation between the scanning equipment, the basic information of the patient and the image browsed by the doctor. The scanning equipment and the basic information of the patient in the read image diagnosis report are defined as sequence X, and the scanning equipment and the basic information of the patient in the image browsed by the doctor are defined as sequence Y. The calculation formula is as follows: Where: is the mean of the sequence X, is the mean of the sequence Y, x i is the i-th information in sequence X, y i is the i-th information in sequence Y, n is the number of information, P is the Pearson correlation coefficient, and the value of P is between [-1, 1]. The larger the absolute value of P, the higher the correlation between sequences X and Y; the smaller the absolute value of P, the lower the correlation between sequences X and Y.

6. The method for automatically generating a clinical image reference atlas according to claim 3, characterized in that: The report image is retrieved, and the reference atlas layer is matched based on the relative position of the layer where the anatomical location is located in all scanning layers, and a reference atlas is automatically generated and displayed to the physician for reference, specifically, Identify keywords in imaging diagnostic reports through sentence recognition; Retrieve and associate to corresponding imaging diagnostic reports based on keywords; Extract the image corresponding to the associated imaging diagnosis report; According to the degree of relevance of the imaging diagnosis report, the extracted images are collected into a pre-display folder as a reference map for doctors to query.

7. A system for automatically generating a clinical image reference atlas, characterized in that: The system includes: a memory and a processor, wherein the memory includes a program of a method for automatically generating a clinical image reference atlas, and when the program of the method for automatically generating a clinical image reference atlas is executed by the processor, the following steps are implemented: the physician determines the anatomical location of the required reference atlas based on browsing the patient's image; extracts the patient's imaging examination category, examination items, basic patient information, and the relative position of the layer where the anatomical location is located in all scanning layers; matches the same imaging examination items and categories in the hospital imaging diagnosis report database, matches the patient's basic information and examination equipment, and determines the search keywords based on the anatomical location; determines to search for structured medical imaging report statements based on the search keywords, queries the hospital imaging report database, and matches the report statements to determine a normal report; retrieves the report image, matches the reference atlas layer based on the relative position of the layer where the anatomical location is located in all scanning layers, automatically generates a reference atlas, and displays it to the physician for reference.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program code, and when the program code is executed by a processor, the steps of the method for automatically generating a clinical image reference atlas as described in any one of claims 1 to 6 are implemented.

Images