Medical image capability assessment method and device and computer readable storage medium

Abstract

The invention relates to the technical field of medical care informatics, and discloses a medical image capability assessment method and device and a computer readable storage medium. The method comprises the following steps: setting a standard examination item of a medical image, and carrying out graded score assignment on the standard examination item to obtain a score of the standard examination item; then acquiring medical image data, and standardizing the medical image data according to the standard inspection items to obtain standardized data; and finally, based on the standardized data and the standard examination item score, a comprehensive score is calculated through a weighted average method and is used for evaluating the medical image capability. The problems of data non-standardization, lack of objective quantification standards, insufficient large sample data analysis, limitation of expert review, low assessment accuracy and the like in existing medical image capability assessment are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical care informatics, and in particular to a medical imaging capability assessment method, device and computer-readable storage medium. Background Art

[0002] Medical imaging capability is an indicator that reflects the level of medical institutions, health examination institutions, etc. in medical imaging. Evaluating medical imaging capability is conducive to horizontal comparison between different medical institutions, health examination institutions, etc., and reflects their ability to handle medical imaging business.

[0003] At present, the types of medical imaging examinations on the market are complex and have a low degree of standardization. The definitions and standardized statistical calibers of information such as examination sites, examination item names, and scanning methods are inconsistent among hospitals, which increases the complexity of medical imaging data and makes it impossible to conduct effective big data analysis and interconnection. Summary of the invention

[0004] In order to better perform medical imaging capability assessment, the present invention provides a medical imaging capability assessment method, device and computer-readable storage medium.

[0005] A first aspect of the present invention provides a method for evaluating medical imaging capabilities, comprising the following steps:

[0006] Set standard examination items for medical imaging, and grade and score the standard examination items to obtain the scores of the standard examination items;

[0007] Acquire medical imaging data, and standardize the medical imaging data according to standard examination items to obtain standardized data;

[0008] Based on the standardized data and the scores of standard examination items, the comprehensive score is calculated by weighted average method to evaluate medical imaging capabilities;

[0009] Among them, the information contained in the standard examination items includes the cognitive difficulty level. The standard examination items are scored according to the cognitive difficulty level. The higher the cognitive difficulty level, the higher the corresponding score.

[0010] A second aspect of the present invention provides a medical imaging capability assessment device, comprising:

[0011] An information storage module, used to store information included in standard inspection items;

[0012] A grading and scoring module is used to grade and score standard inspection items to obtain the scores of standard inspection items;

[0013] A standardization module is used to standardize medical imaging data according to standard examination items to obtain standardized data;

[0014] A calculation module, used to calculate the comprehensive score by weighted average method based on the standardized data and the scores of the standard inspection items;

[0015] Among them, the information contained in the standard inspection items includes the cognitive difficulty level. The grading and scoring module scores the standard inspection items according to the cognitive difficulty level. The higher the cognitive difficulty level, the higher the corresponding score.

[0016] A third aspect of the present invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps of the above method.

[0017] In the present invention, standard examination items for medical imaging are set, and the standard examination items are graded and scored to obtain the standard examination item scores; then medical imaging data is acquired, and the medical imaging data is standardized according to the standard examination items to obtain standardized data; finally, based on the standardized data and the standard examination item scores, a comprehensive score is calculated by the weighted average method to evaluate the medical imaging capability; the problems existing in the existing medical imaging capability assessment, such as non-standardized data, lack of objective quantitative standards, insufficient large sample data analysis, limitations in expert review, and low evaluation accuracy, are solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The figure is a flow chart of a medical imaging capability assessment method according to an embodiment of the present invention.

[0019] Figure 2 The figure is a flowchart of a medical imaging capability assessment method in another embodiment of the present invention.

[0020] Figure 3 The present invention is a flowchart of a method for evaluating medical imaging capabilities in another embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0022] like Figure 1 As shown, an embodiment of the first aspect of the present invention provides a medical imaging capability assessment method, which includes the following steps:

[0023] Step 100: setting standard examination items for medical images, and grading and scoring the standard examination items to obtain the scores of the standard examination items;

[0024] Step 200: Acquire medical image data, and standardize the medical image data according to standard examination items to obtain standardized data;

[0025] Step 300: Based on the standardized data and the scores of the standard examination items, a comprehensive score is calculated by weighted average method to evaluate the medical imaging capability;

[0026] Among them, the information contained in the standard examination items includes the cognitive difficulty level. The standard examination items are scored according to the cognitive difficulty level. The higher the cognitive difficulty level, the higher the corresponding score.

[0027] It should be noted that the standard examination items of medical imaging refer to the items for examining the human body through medical imaging technology, such as computed tomography (CT), nuclear magnetic resonance imaging (NMRI), B-mode ultrasound (B-ultrasound), etc. Different medical institutions, health examination institutions, etc. (hereinafter collectively referred to as medical imaging institutions) may not name the medical imaging examination items consistently. For example, medical imaging institution A names the CT examination item of the skull base as "CT skull base (plain scan + 3D reconstruction)", while medical imaging institution B may name it "head skull base + processing", which makes it difficult to process data in the same way, which is not conducive to the ability assessment and comparison of different medical imaging institutions.

[0028] In the present invention, standard examination items of medical imaging are set up, which are used as the benchmark for the standardization of medical imaging data of different medical imaging institutions, so as to ensure that the same standards and methods are used when evaluating the examination items of different medical imaging institutions, thereby unifying the evaluation results, reducing subjectivity and uncertainty; it can make it easier to compare the examination items and better understand the differences and advantages and disadvantages of each examination item. The standard examination items are graded and scored, and different levels are divided according to the difficulty of the examination items, corresponding to different scores, so that the evaluation of the examination items is easy to quantify, which is conducive to the comprehensiveness, fairness, practicality and guidance of the medical imaging ability evaluation, and helps to more comprehensively and quantifiably evaluate all aspects of imaging ability. If the grading and scoring are not performed, all examination items will be treated equally, and it is difficult to distinguish the difficulty and importance of different examination items, resulting in the evaluation results being not comprehensive and accurate; moreover, the evaluation results will lack a sense of hierarchy and depth, and it is difficult to accurately reflect the ability performance of medical imaging institutions at different levels. After obtaining the medical imaging data, it is first standardized, and then combined with the standard examination item scores, a weighted average calculation is performed to obtain a comprehensive score, which can reflect the medical imaging ability. Among them, medical imaging data can be obtained from medical imaging institutions, such as from tertiary hospitals or above. Medical imaging data can include but is not limited to the institution, department, equipment type, location, scanning method, examination item name, etc. of the data source.

[0029] In one possible implementation, the information included in the standard examination items includes the name of the standard examination item, the item code, the body part, the equipment type, the scanning method, the post-processing method, the item identification and the cognitive difficulty level.

[0030] It should be noted that, in addition to the cognitive difficulty level, other information included in the standard examination items can be flexibly set according to the medical imaging assessment requirements to provide a basis for subsequent assessments. For example, Table 1 shows the information included in a standard examination item. Different examination items may include different information, which will not be repeated here.

[0031] Table 1 Example of information included in a standard inspection item

[0032]

[0033] In one possible implementation, the cognitive difficulty level of the standard inspection item is determined by the cognitive difficulty of the standard inspection item. The cognitive difficulty calculation formula of the standard inspection item is:

[0034]

[0035] Where L(Pi) represents the cognitive difficulty of the standard inspection items; W d (Pi) represents the complexity weight factor of the standard inspection item; Wq (Pi) represents the inspection quantity weight factor of the standard inspection item; W t (Pi) represents the time consumption weight factor of the standard inspection item; Pi represents the i-th standard inspection item, i is a positive integer; a, b, c represent weight coefficients, and a+b+c=1;

[0036] in,

[0037]

[0038] Where D(Pi) represents the complexity of standard inspection items; F(Pi) represents the frequency of standard inspection items that meet the difficulty vocabulary and rules in the text data related to medical imaging inspection items counted by the natural language processing (NLP) model; MaxF represents the maximum frequency of standard inspection items that meet the difficulty vocabulary and rules in the text data related to medical imaging inspection items counted by the natural language processing model; k represents the adjustment coefficient; Q(Pi) represents the inspection volume of standard inspection items within a certain period of time (for example, one year); AT(Pi) represents the average time required to complete the standard inspection items; and n represents the total number of standard inspection items.

[0039] It should be noted that the cognitive difficulty level of the examination items is divided according to factors such as the complexity of the examination items, the amount of examination, and time consumption. The higher the cognitive difficulty level, the higher the corresponding score will be. The higher the score, the better the cognitive ability of medical imaging ability. The cognitive difficulty level comprehensively considers the complexity weight factor, the examination amount weight factor, and the time consumption weight factor, which improves the accuracy of grading and scoring. When calculating the complexity weight factor, the NLP model is used to analyze a large amount of text data related to medical imaging examination items (such as examination reports, operating instructions, quality control reports, expert experience summaries, etc.). Based on complexity-related vocabulary and rules, the NLP model traverses the text data related to medical imaging examination items and counts the frequency of standard examination items that meet the difficulty vocabulary and rules. The vocabulary related to complexity can be "complex operation", "high resolution requirements", "multi-parameter adjustment", etc., and the complexity-related vocabulary library and semantic rule set are constructed accordingly. The training of the NLP model belongs to the prior art and will not be repeated here.

[0040] In one embodiment, the cognitive difficulty levels include level one, level two, level three, level four and level five, and accordingly, level one standard examination items are assigned 1 point, level two standard examination items are assigned 2 points, level three standard examination items are assigned 3 points, level four standard examination items are assigned 4 points, and level five standard examination items are assigned 5 points.

[0041] It should be noted that the cognitive difficulty level can include other levels, and the scores of standard examination items at each level can also be other scores, as long as the higher the cognitive difficulty level, the higher the score. The cognitive difficulty of different standard examination items may be different. For example, if NMRI is more cognitively difficult than B-ultrasound, a higher cognitive difficulty level (such as level 4) can be set for NMRI, and a higher score (such as 4 points) can be assigned accordingly; a lower cognitive difficulty level (such as level 1) can be set for B-ultrasound, and a lower score (such as 1 point) can be assigned accordingly.

[0042] In one embodiment, in step 200, standardizing the medical image data according to the standard examination items includes:

[0043] Medical imaging data is governed and cleaned, and matched with standard examination items according to matching rules, thereby converting medical imaging data into standard examination item data.

[0044] It should be noted that the step of standardizing medical imaging data according to standard examination items can ensure the consistency and comparability of medical imaging data from different medical imaging institutions. For example, the medical imaging data from a hospital contains examination item data with the original name of "head skull base + processing", and the name of the standard examination item matched according to the matching rule may be "CT skull base (plain scan + 3D reconstruction)".

[0045] In one possible implementation, the matching rules are obtained by training a natural language processing (NLP) model.

[0046] It should be noted that using the NLP model to obtain matching rules can improve the standardization efficiency. Through training, the NLP model can learn the rules between input data and output data, which belongs to the prior art and will not be described here.

[0047] In one embodiment, the formula for calculating the comprehensive score by weighted average method is:

[0048] ;

[0049] Among them, S f represents the comprehensive score, Q i represents the inspection quantity of the i-th standard inspection item, S i Represents the score of the i-th standard inspection item, where i is a positive integer.

[0050] It should be noted that the comprehensive score is related to the inspection volume, the type of inspection items and the score of the standard inspection items. The inspection volume refers to the cumulative number of times the inspection items are done, which can be obtained based on the name of the inspection items in the medical imaging data. For example, the inspection volume of the medical imaging department of a hospital is 100, among which the inspection volume of the first type of inspection item is 30, and the corresponding standard inspection item score is 1 point; the inspection volume of the second type of inspection item is 50, and the corresponding standard inspection item score is 4 points; the inspection volume of the third type of inspection item is 20, and the corresponding standard inspection item score is 8 points; then (30*1+50*4+20*8) / 100=3.9, that is, the comprehensive score is 3.9 points. The higher the comprehensive score, the higher the medical imaging ability, and vice versa.

[0051] like Figure 2 As shown, in one possible implementation, the medical imaging capability assessment method further includes the following steps:

[0052] Step 400: Calculate the coverage of standard inspection items based on the standardized data, where the calculation formula is:

[0053] The coverage rate of standard inspection items = (the number of types of standard inspection items in the standardized data / the number of types of conventional standard inspection items)*100%.

[0054] For example, Department A of Hospital A only carried out three types of examination items in a certain period of time, namely, the first type of examination item (standard examination items that the department should do), the second type of examination item (standard examination items that the department should do), and the third type of examination item (standard examination items that non-departments should do). Then the number of types of standard examination items that Department A should do is 2; the number of types of routine standard examination items is defined as 100. In this way, the coverage rate of standard examination items of Department A is: 2 / 100 * 100% = 2.00%. The higher the coverage rate of standard examination items of a department, the stronger the comprehensive imaging capability of the department, and vice versa.

[0055] like Figure 3 As shown, in one possible implementation, the medical imaging capability assessment method further includes the following steps:

[0056] Step 500: Calculate the proportion of advanced standard inspection items based on the standardized data, where the calculation formula is:

[0057] The proportion of advanced standard inspection items = (the number of advanced standard inspection items in the standardized data / the number of standard inspection items in the standardized data)*100%.

[0058] For example, Hospital B only carried out three types of examination items in a certain period of time. The first type of examination item is an advanced examination item with a total of 50 examination items; the second type of examination item is also an advanced examination item with a total of 20 examination items; the third type of examination item is a common examination item with a total of 30 examination items. It can be seen that the number of advanced standard examination items is 70 (the sum of the examination quantities of the first and second types of examination items), and the proportion of advanced standard examination items is: (50+20) / (50+30+20) * 100% = 70.00%. The higher the proportion of advanced examination items, the stronger the imaging capability, and vice versa.

[0059] It should be noted that the coverage rate of standard examination items and the proportion of advanced standard examination items can reflect the breadth of medical imaging institutions' cognition of clinical medical imaging examinations, thereby improving the accuracy of medical imaging capability assessment. The higher the percentage of standard examination items actually performed to the number of conventional standard examination items, the higher the cognitive ability, and vice versa. The higher the percentage of advanced standard examination items to the number of standard examination items, the higher the cognitive ability, and vice versa. The types of conventional standard examination items can be obtained by collecting the types of daily examination items of departments in multiple tertiary hospitals and conducting big data analysis; or, they can be obtained through actual surveys or defined by manual experience. Advanced standard examination items refer to standard examination items with a cognitive difficulty level of three or above.

[0060] An embodiment of the second aspect of the present invention provides a medical imaging capability assessment device, comprising:

[0061] An information storage module, used to store information included in standard inspection items;

[0062] A grading and scoring module is used to grade and score standard inspection items to obtain the scores of standard inspection items;

[0063] A standardization module is used to standardize medical imaging data according to standard examination items to obtain standardized data;

[0064] A calculation module, used to calculate the comprehensive score by weighted average method based on the standardized data and the scores of the standard inspection items;

[0065] Among them, the information contained in the standard inspection items includes the cognitive difficulty level. The grading and scoring module scores the standard inspection items according to the cognitive difficulty level. The higher the cognitive difficulty level, the higher the corresponding score.

[0066] In one embodiment, the calculation module is further used to calculate the coverage of standard inspection items based on the standardized data.

[0067] In one possible implementation manner, the calculation module is further used to calculate the proportion of high-level standard inspection items based on the standardized data.

[0068] It should be noted that the method in which the grading and scoring module grades and scores standard examination items, the standardization module standardizes medical imaging data, and the calculation module performs calculations is the same as the aforementioned method.

[0069] An embodiment of the third aspect of the present invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps of the aforementioned method.

[0070] It will be appreciated by those skilled in the art that all or part of the processes in the above method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, which, when executed, can include the processes of the above method. The computer-readable storage medium may include non-volatile and / or volatile memory. The non-volatile memory may include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM) or an external cache memory.

[0071] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for evaluating medical imaging capabilities, characterized in that: The following steps are involved: Set standard examination items for medical imaging, and grade and score the standard examination items to obtain the scores of the standard examination items; Acquire medical imaging data, and standardize the medical imaging data according to standard examination items to obtain standardized data; Based on the standardized data and the scores of standard examination items, the comprehensive score is calculated by weighted average method to evaluate medical imaging capabilities; Among them, the information contained in the standard examination items includes the cognitive difficulty level. The standard examination items are scored according to the cognitive difficulty level. The higher the cognitive difficulty level, the higher the corresponding score.

2. The method according to claim 1, characterized in that The information contained in the standard inspection items includes the name of the standard inspection item, item code, location, equipment type, scanning method, post-processing method, item identification and cognitive difficulty level.

3. The method according to claim 1, characterized in that The cognitive difficulty level of the standard inspection items is determined by the cognitive difficulty of the standard inspection items. The cognitive difficulty calculation formula of the standard inspection items is: ， Where L(Pi) represents the cognitive difficulty of the standard inspection items; W d (Pi) represents the complexity weight factor of the standard inspection item; W q (Pi) represents the inspection quantity weight factor of the standard inspection item; W t (Pi) represents the time consumption weight factor of the standard inspection item; Pi represents the i-th standard inspection item, i is a positive integer; a, b, c represent weight coefficients, and a+b+c=1; in, ， Among them, D(Pi) represents the complexity of standard inspection items; F(Pi) represents the frequency of standard inspection items that meet the difficulty vocabulary and rules in the text data related to medical imaging inspection items counted by the natural language processing model; MaxF represents the maximum frequency of standard inspection items that meet the difficulty vocabulary and rules in the text data related to medical imaging inspection items counted by the natural language processing model; k represents the adjustment coefficient; Q(Pi) represents the inspection volume of standard inspection items within a certain period of time; AT(Pi) represents the average time required to complete the standard inspection items; n represents the total number of standard inspection items.

4. The method according to claim 1, characterized in that: Standardization of medical imaging data according to standard examination items includes: Medical imaging data is governed and cleaned, and matched with standard examination items according to matching rules, thereby converting medical imaging data into standard examination item data.

5. The method according to claim 4, characterized in that The matching rules are obtained by training the natural language processing model.

6. The method according to claim 1, characterized in that The formula for calculating the comprehensive score using the weighted average method is: ； Among them, S f represents the comprehensive score, Q i represents the inspection quantity of the i-th standard inspection item, S i Represents the score of the i-th standard inspection item, where i is a positive integer.

7. The method according to claim 1, characterized in that The following steps are also included: Based on the standardized data, the coverage of standard inspection items is calculated, where the calculation formula is: The coverage rate of standard inspection items = (the number of types of standard inspection items in the standardized data / the number of types of conventional standard inspection items)*100%.

8. The method according to claim 1, characterized in that The following steps are also included: Based on the standardized data, the proportion of advanced standard inspection items is calculated, where the calculation formula is: The proportion of advanced standard inspection items = (the number of advanced standard inspection items in the standardized data / the number of standard inspection items in the standardized data)*100%.

9. A medical imaging capability assessment device, characterized in that: include: An information storage module, used to store information included in standard inspection items; A grading and scoring module is used to grade and score standard inspection items to obtain the scores of standard inspection items; A standardization module is used to standardize medical imaging data according to standard examination items to obtain standardized data; A calculation module, used to calculate the comprehensive score by weighted average method based on the standardized data and the scores of the standard inspection items; Among them, the information contained in the standard inspection items includes the cognitive difficulty level. The grading and scoring module scores the standard inspection items according to the cognitive difficulty level. The higher the cognitive difficulty level, the higher the corresponding score.

10. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor, the processor executes the steps of the method according to any one of claims 1 to 8.

Images