AI-based medical imaging teaching auxiliary method and system

Abstract

The invention discloses a medical imaging teaching assistance method and system based on AI, and the method comprises the steps: collecting the learning background information of all students, and evaluating the knowledge level of the students; according to the knowledge level evaluation result of the student, intelligently planning course content; evaluating the mastering degree of the students on the course knowledge points to realize the dynamic adjustment of the teaching content; inputting the student data into an AI-based learning condition evaluation model, and optimizing the teaching content and method by the teacher according to the course learning condition of the student fed back by the model; a teaching resource sharing platform is established, different specialized teachers share teaching resources and information, teaching content communication is achieved, the real-time learning degree of the students on courses is known based on an AI learning condition evaluation model, the teachers dynamically adjust the teaching content, the teaching flexibility and adaptability are improved, and the learning effect of the students is improved.

Description

Technical Field

[0001] The present invention relates to the field of medical education and is an AI-based medical imaging teaching auxiliary method and system. Background Art

[0002] The current teaching content of medical imaging courses includes bone, musculoskeletal system, respiratory system, circulatory system, digestive system, central nervous system, and otorhinolaryngology, which are taught by teachers from different professional groups. The teaching task of the same system is jointly undertaken by multiple teachers from sub-professional groups. Different specialized teachers teaching the same course often leads to poor continuity of the course, and the teaching content may be repeated or omitted. In addition, the teaching objects of this course have different backgrounds, including medical students from different professional backgrounds such as five-year clinical, forensic medicine, preventive medicine, imaging, eight-year undergraduate-master-doctoral integrated training clinical medicine, and Qiming undergraduate-master-doctor experimental classes. There are differences in the arrangement of prerequisite courses and the level of basic knowledge. The hours and course tasks are also different, and the teaching content needs to be dynamically adjusted. Summary of the invention

[0003] The present invention proposes an AI-based medical imaging teaching assistance method and system, which formulates a suitable teaching plan by evaluating the learning background of the teaching objects, intelligently plans the course content, and dynamically adjusts the teaching content according to the students' mastery of the knowledge points. By introducing a neural network-based learning situation evaluation model, accurate feedback on the students' learning situation is provided to the teacher, and the information is shared on the teaching resource sharing platform, thereby achieving flexibility and adaptability of the teaching process.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] An AI-based medical imaging teaching assistance method, the method comprising the following steps:

[0006] S1. Collect students’ learning background information and evaluate their knowledge level. The learning background information includes the academic system, major, hours of prerequisite courses and content forgotten. The evaluation results are used to formulate teaching plans;

[0007] S2. Intelligently plan course content based on the results of student knowledge level assessment to ensure that the teaching content matches the student's knowledge level;

[0008] S3. Evaluate students' mastery of course knowledge points to dynamically adjust teaching content;

[0009] S4. Input student data into the AI-based learning assessment model, and teachers optimize teaching content and methods based on the feedback from the model on students’ course learning;

[0010] S5. Establish a teaching resource sharing platform so that teachers from different specialties can share teaching resources and information and achieve the integration of teaching content.

[0011] Preferably, the evaluation of the students' knowledge level in S1 can be carried out through a pre-class examination or a questionnaire survey, etc., which is not limited here.

[0012] Preferably, the specific method of formulating the teaching plan in S1 is as follows:

[0013] The teaching contents of medical imaging include: Course A, Course B, Course C, ..., Course N;

[0014] The prerequisite courses include basic courses A1, A2, ..., A m1 There are m1 courses related to course A; the corresponding class hours are T A1 ,T A2 ,...,T Am1 , and the interval from the study of medical imaging course is t A1 ,t A2 ,...,t Am1 , and the relevance to the medical imaging course a1, a2, ..., a m1 ;

[0015] The prerequisite courses also include basic courses B1, B2, ..., B m2 There are m2 courses related to course B; the corresponding class hours are T B1 ,T B2 ,...,T Bm2 , and the interval from the study of medical imaging course is t B1 ,t B2 ,...,t Bm2 , and the relevance to medical imaging courses b1, b2, ..., b m2 ;

[0016] The prerequisite courses also include basic courses C1, C2, ..., C m3 There are m3 courses related to course C; the corresponding class hours are T C1 ,T C2 ,...,T Cm3 , and the interval from the study of medical imaging course is t C1 ,t C2 ,...,t Cm3 , and the relevance to the medical imaging course c1,c2,...,c m3 ; ...

[0018] The prerequisite courses also include basic courses N1, N2, ..., N related to the N course. mn There are mn courses related to N courses; the corresponding class hours are T N1 ,T N2 ,...,T Nmn , and the interval from the study of medical imaging course is t N1 ,t N2 ,...,t Nmn , and the relevance to the medical imaging course n1,n2,...,n mn ;

[0019] The priority of N courses is calculated according to the following formula:

[0020]

[0021] Among them, P A is the teaching priority of course A, P B is the teaching priority of course B, P C is the teaching priority corresponding to course C, ..., P N The course priorities corresponding to N courses are compared, and the course arrangement is determined according to the priority. In the teaching process, courses with high priority are taught first, and the basic content of courses with low priority is consolidated.

[0022] Preferably, the method for evaluating the mastery of course knowledge points by students in S3 is: dividing the teaching content into multiple knowledge points d1, d2, ..., d N , further calculate the mastery of knowledge points,

[0023]

[0024] in, Indicates the mastery of the i-th knowledge point; Ti indicates the hours of the prerequisite courses related to the i-th knowledge point; ti indicates the interval between the prerequisite courses related to the i-th knowledge point and the knowledge points of the medical imaging course; Indicates the memory of the prerequisite courses related to the i-th one; k i is the number of sign-ins when learning the i-th knowledge point; e i is the learning time of the i-th knowledge point; y i is the extracurricular study time of the students of the i-th knowledge point; z i is the difficulty of the ith knowledge point, which is related to the score rate in the history test.

[0025] Preferably, establishing the AI-based learning situation evaluation model in S4 comprises the following steps:

[0026] S41. The collected historical student data is used as a data set, including the student's prerequisite course grades, the medical imaging class hours learned, the supporting practical course time, the number of questions asked after class, the teacher's after-class answering time, the student's rating of the teacher, the course attendance data and the degree of knowledge mastery, as well as the corresponding historical student test scores, and normalized:

[0027]

[0028] Where X is the original data, X min and X max are the minimum and maximum values ​​of the data respectively;

[0029] S42. Input the normalized data into the input layer, and divide the data into features X=[x1,x2,x3,x4,x5,x6,x7,x8] and corresponding labels Y=[y];

[0030] Among them, x1 represents the student's prerequisite course score, x2 represents the number of hours of medical imaging courses learned, x3 represents the supporting practical course time, x4 represents the number of questions asked after class, x5 represents the teacher's answer time after class, x6 represents the student's rating of the teacher, x7 represents the course attendance data, x8 represents the degree of knowledge mastery, and y represents the student's test score;

[0031] S43. Use multiple hidden layers to extract the features of input data. The formula is: , where H is the output of the hidden layer, W and b are the weights and biases, is the ReLU function;

[0032] S44. Output the students’ learning status of the course. Map the features of the hidden layer to the students’ scores on the course learning status through the output layer. The formula is: ,in is the student's score on the course, W' and b' are the weight and bias of the output layer;

[0033] S45. Use the cross entropy loss function to optimize the model so that its output value is close to the actual student learning situation of the course.

[0034]

[0035] in is the true label, is the student's rating of the course learning situation output by the model;

[0036] S46. Use the Adam optimizer to update the weights and biases of the model to minimize the loss function:

[0037]

[0038] Where W new is the updated weight, W old is the weight before updating, is the learning rate, is the gradient of the loss function with respect to the weights.

[0039] The present invention provides an AI-based medical imaging teaching auxiliary system, which is characterized by comprising:

[0040] Student knowledge level assessment module: collects all students' learning information and assesses their basic knowledge level, including the length of study, major, hours of prerequisite courses and content forgotten. The assessment results are used to formulate teaching plans.

[0041] Intelligent course content planning module: intelligently plan course content based on the results of student knowledge level assessment to ensure that the teaching content matches the student's knowledge level;

[0042] Dynamic adjustment module of teaching content: evaluate students' mastery of course knowledge points to achieve dynamic adjustment of teaching content;

[0043] Learning situation assessment module: input student data into the AI-based learning situation assessment model, and teachers further optimize teaching content and methods based on the students' course learning situation feedback from the model;

[0044] Teaching resource sharing platform: Establish a teaching resource sharing platform, where teachers from different specialties can share teaching resources and information to achieve the integration of teaching content;

[0045] Intelligent assisted teaching system: Develop an intelligent assisted teaching system that integrates the above modules to provide one-stop teaching assistance services for teachers and students.

[0046] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0047] The present invention formulates teaching plans by comprehensively considering multiple dimensions such as the academic system, major, hours of prerequisite courses, and content forgetting, so that the teaching plans can more accurately match the students' actual levels; and based on the learning situation evaluation model of the neural network, the real-time learning level of the students for the course is understood, the teaching content is dynamically adjusted, the learning effect is improved, and the teaching content is more flexible. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0049] Figure 2 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0050] To make the purpose, technical solution and advantages of the present invention more clear, the present invention is further described in detail below in combination with specific implementations and with reference to the accompanying drawings. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0051] It is to be understood that these descriptions are exemplary only and are not intended to limit the scope of the invention.

[0052] The present invention provides an AI-based medical imaging teaching auxiliary method, such as Figure 1 As shown, the method comprises the following steps:

[0053] S1. Collect all students’ learning background information and evaluate their basic knowledge level. The learning information includes the academic system, major, hours of prerequisite courses and content forgotten. The evaluation results are used to formulate teaching plans.

[0054] Preferably, the evaluation of the students' knowledge level in S1 can be carried out through a pre-class examination or a questionnaire survey, etc., which is not limited here.

[0055] The teaching contents of medical imaging include: Course A, Course B, Course C, ..., Course N;

[0056] The prerequisite courses include basic courses A1, A2, ..., A m1 There are m1 courses related to course A; the corresponding class hours are T A1 ,T A2 ,...,T Am1 , and the interval from the study of medical imaging course is t A1 ,t A2 ,...,t Am1 , and the relevance to the medical imaging course a1, a2, ..., a m1 ;

[0057] The prerequisite courses also include basic courses B1, B2, ..., B m2 There are m2 courses related to course B; the corresponding class hours are T B1 ,T B2 ,...,T Bm2 , and the interval from the study of medical imaging course is t B1 ,t B2 ,...,t Bm2 , and the relevance to medical imaging courses b1, b2, ..., b m2 ;

[0058] The prerequisite courses also include basic courses C1, C2, ..., C m3 There are m3 courses related to course C; the corresponding class hours are T C1 ,T C2 ,...,T Cm3 , and the interval from the study of medical imaging course is t C1 ,t C2 ,...,t Cm3 , and the relevance to the medical imaging course c1,c2,...,c m3 ; ...

[0060] The prerequisite courses also include basic courses N1, N2, ..., N related to the N course. mn There are mn courses related to N courses; the corresponding class hours are T N1 ,T N2 ,...,T Nmn , and the interval from the study of medical imaging course is t N1 ,t N2 ,...,t Nmn , and the relevance to the medical imaging course n1,n2,...,n mn ;

[0061] The priority of N courses is calculated according to the following formula:

[0062]

[0063] Among them, P A is the teaching priority of course A, P B is the teaching priority of course B, P C is the teaching priority corresponding to course C, ..., P N The course priorities corresponding to N courses are compared, and the course arrangement is determined according to the priority. In the teaching process, courses with high priority are taught first, and basic content consolidation is increased for courses with low priority.

[0064] Furthermore, in order to explain in detail how the priority is calculated, taking the head and neck, chest, and abdomen imaging courses as an example, the specific method of formulating the teaching plan is as follows:

[0065] The three major contents of the medical imaging course are head and neck imaging, chest imaging, and abdominal imaging. Therefore, the prerequisite courses include basic courses related to head and neck imaging: A1 = human anatomy (general nervous system, central nervous system, visual organs, vestibulocochlear apparatus), A2 = regional anatomy (head, neck),..., AN =Neurology; the corresponding credit hour is T A1 ,T A2 ,...,T AN , and the interval from the study of medical imaging course is t A1 ,t A2 ,...,t AN , and the relevance to the medical imaging course a1, a2, ..., a N ;

[0066] The prerequisite courses also include basic courses related to chest imaging, B1 = human anatomy (respiratory system, cardiovascular system), B2 = regional anatomy (chest),..., B N = Surgery (cardiothoracic diseases); the corresponding credit hours are T B1 ,T B2 ,...,T BN , and the interval from the study of medical imaging course is t B1 ,t B2 ,...,t BN , and the relevance to medical imaging courses b1, b2, ..., b N ;

[0067] The prerequisite courses also include basic courses related to abdominal imaging, C1 = human anatomy (digestive system, urinary system, male and female reproductive system), C2 = regional anatomy (abdomen),..., C N = Surgery (digestive, urinary, and reproductive diseases); the corresponding credit hours are T C1 ,T C2 ,...,T CN , and the interval from the study of medical imaging course is t C1 ,t C2 ,...,t CN , and the relevance to the medical imaging course c1,c2,...,c N ;

[0068] The relevance of each course to the medical imaging course is related to the historical scores and prerequisite course scores of the medical imaging course.

[0069] The priority of the three courses is calculated according to the following formula:

[0070]

[0071] Among them, P A is the priority of head and neck imaging, P B is the priority of chest imaging, P CFor the priority of abdominal imaging, the calculated priorities are compared, and the course arrangement is determined according to the priority. Courses with higher priorities are taught first during the teaching process.

[0072] For example, P A >P B >P C , then the teaching sequence of the courses is to teach the head and neck imaging course, then the chest imaging course, and finally the abdominal imaging course.

[0073] By determining the teaching plan through priority, we can give priority to teaching courses with good basic knowledge learning according to the students' basic knowledge learning situation of the three courses, thus avoiding the situation where students forget the relevant basic knowledge and the learning effect decreases.

[0074] Furthermore, when teachers teach lower priority courses, they can increase the explanation of prerequisite course knowledge and improve teaching quality.

[0075] S2. Intelligently plan course content based on the results of student knowledge level assessment (combined with pre-class exams and questionnaires, etc.) to ensure that the teaching content matches the students' knowledge level.

[0076] S3. Evaluate students’ mastery of course knowledge points to dynamically adjust teaching content.

[0077] The evaluation method of students' mastery of course knowledge points is as follows: the teaching content is divided into multiple knowledge points: d1 = imaging of brain tumors, d2 = imaging of brain trauma, ..., d N = Imaging of adrenal adenoma, further calculate the mastery of knowledge points,

[0078]

[0079] in, represents the mastery of the i-th knowledge point; Ti represents the hours of the prerequisite courses related to the i-th knowledge point; ti represents the interval between the prerequisite courses related to the i-th knowledge point and the knowledge points of the medical imaging course; Indicates the memory of the prerequisite courses related to the i-th one; k i is the number of sign-ins when learning the i-th knowledge point; e i is the learning time of the i-th knowledge point; y i is the extracurricular study time of the students of the i-th knowledge point; z i is the difficulty level of the ith knowledge point, which is expressed in terms of the score rate in the history test.

[0080] S4. Input student data into the AI-based learning assessment model, and teachers further optimize teaching content and methods based on the feedback from the model on students’ course learning.

[0081] Preferably, establishing the AI-based learning situation evaluation model in S4 comprises the following steps:

[0082] S41. The collected historical student data is used as a data set, including the student's prerequisite course grades, the medical imaging class hours learned, the supporting practical course time, the number of questions asked after class, the teacher's after-class answering time, the student's rating of the teacher, the course attendance data and the degree of knowledge mastery, as well as the corresponding historical student test scores, and normalized:

[0083]

[0084] Where X is the original data, X min and X max are the minimum and maximum values ​​of the data respectively;

[0085] S42. Input the normalized data into the input layer, and divide the data into features X=[x1,x2,x3,x4,x5,x6,x7,x8] and corresponding labels Y=[y];

[0086] Among them, x1 represents the student's prerequisite course score, x2 represents the number of hours of medical imaging courses learned, x3 represents the supporting practical course time, x4 represents the number of questions asked after class, x5 represents the teacher's answer time after class, x6 represents the student's rating of the teacher, x7 represents the course attendance data, x8 represents the degree of knowledge mastery, and y represents the student's test score;

[0087] S43. Use multiple hidden layers to extract the features of input data. The formula is: , where H is the output of the hidden layer, W and b are the weights and biases, is the ReLU function;

[0088] S44. Output the students’ learning status of the course. Map the features of the hidden layer to the students’ scores on the course learning status through the output layer. The formula is: ,in is the student's score on the course, W' and b' are the weight and bias of the output layer;

[0089] S45. Use the cross entropy loss function to optimize the model so that its output value is close to the actual student learning situation of the course.

[0090]

[0091] in is the true label, is the student's rating of the course learning situation output by the model;

[0092] S46. Use the Adam optimizer to update the weights and biases of the model to minimize the loss function:

[0093]

[0094] Where W new is the updated weight, W old is the weight before updating, is the learning rate, is the gradient of the loss function with respect to the weights.

[0095] S5. Establish a teaching resource sharing platform so that teachers from different specialties can share teaching resources and information and achieve the integration of teaching content.

[0096] The present invention also provides an AI-based medical imaging teaching auxiliary system, such as Figure 2 As shown, it includes:

[0097] Student knowledge level assessment module: collects all students' learning information and assesses their basic knowledge level, including the length of study, major, hours of prerequisite courses and content forgotten. The assessment results are used to formulate teaching plans.

[0098] The students' knowledge level can be assessed through pre-class examinations or questionnaires, etc., and there are no further restrictions here.

[0099] Since medical imaging includes three courses, namely head and neck imaging, chest imaging, and abdominal imaging, this is just an example. As the content of medical imaging courses is continuously adjusted, more course content may be included.

[0100] At this time, the prerequisite courses include basic courses related to head and neck imaging A1, A2, ..., A N ; The corresponding class time is T A1 ,T A2 ,...,T AN , and the interval from the study of medical imaging course is t A1 ,t A2 ,...,t AN , and the relevance to the medical imaging course a1, a2, ..., a N ;

[0101] Prerequisite courses also include basic courses related to chest imaging B1, B2,..., B N ; The corresponding class time is T B1 ,T B2,...,T BN , and the interval from the study of medical imaging course is t B1 ,t B2 ,...,t BN , and the relevance to medical imaging courses b1, b2, ..., b N ;

[0102] The prerequisite courses also include basic courses related to abdominal imaging C1, C2, ..., C N ; The corresponding class time is T C1 ,T C2 ,...,T CN , and the interval from the study of medical imaging course is t C1 ,t C2 ,...,t CN , and the relevance to the medical imaging course c1,c2,...,c N ;

[0103] The relevance of each course to the medical imaging course is related to the historical scores and prerequisite course scores of the medical imaging course.

[0104] The priority of the three courses is calculated according to the following formula:

[0105]

[0106] Among them, P A is the priority of head and neck imaging, P B is the priority of chest imaging, P C For the priority of abdominal imaging, the calculated priorities are compared, and the course arrangement is determined according to the priority. Courses with higher priorities are taught first during the teaching process.

[0107] For example, P A >P B >P C , then the teaching sequence of the courses is to teach the head and neck imaging course, then the chest imaging course, and finally the abdominal imaging course.

[0108] By determining the teaching plan through priority, we can give priority to teaching courses with good basic knowledge learning according to the students' basic knowledge learning situation of the three courses, thus avoiding the situation where students forget the relevant basic knowledge and the learning effect decreases.

[0109] Furthermore, when teachers teach lower priority courses, they can increase the explanation of prerequisite course knowledge and improve teaching quality.

[0110] Intelligent course content planning module: intelligently plan course content based on the results of student knowledge level assessment to ensure that the teaching content matches the students' knowledge level.

[0111] Dynamic adjustment module of teaching content: evaluates students’ mastery of course knowledge points and realizes dynamic adjustment of teaching content.

[0112] The students' knowledge level can be assessed through pre-class examinations or questionnaires, etc., and there are no further restrictions here.

[0113] The teaching content is divided into multiple knowledge points d1, d2, ..., d according to head and neck imaging, chest imaging, and abdominal imaging. N , further calculate the mastery of knowledge points,

[0114]

[0115] in Indicates the mastery of the i-th knowledge point; Ti indicates the hours of the prerequisite courses related to the i-th knowledge point; ti indicates the interval between the prerequisite courses related to the i-th knowledge point and the knowledge points of the medical imaging course; Indicates the memory of the prerequisite courses related to the i-th one; k i is the number of sign-ins when learning the i-th knowledge point; e i is the learning time of the i-th knowledge point; y i is the extracurricular study time of the students of the i-th knowledge point; z i is the difficulty of the ith knowledge point, which is determined by the score rate in the history test.

[0116] Learning situation assessment module: Establish an AI-based learning situation assessment model, and teachers further optimize teaching content and methods based on students’ feedback on course learning.

[0117] Furthermore, the above-mentioned AI-based learning assessment model is constructed to assess students’ learning of the course, which includes the following steps:

[0118] S41. The collected historical student data is used as a data set, including the student's prerequisite course grades, the medical imaging class hours learned, the supporting practical course time, the number of questions asked after class, the teacher's after-class answering time, the student's rating of the teacher, the course attendance data and the degree of knowledge mastery, as well as the corresponding historical student test scores, and normalized:

[0119]

[0120] Where X is the original data, X min and X max are the minimum and maximum values ​​of the data respectively;

[0121] S42. Input the normalized data into the input layer, and divide the data into features X=[x1,x2,x3,x4,x5,x6,x7,x8] and corresponding labels Y=[y];

[0122] Among them, x1 represents the student's prerequisite course score, x2 represents the number of hours of medical imaging courses learned, x3 represents the supporting practical course time, x4 represents the number of questions asked after class, x5 represents the teacher's answer time after class, x6 represents the student's rating of the teacher, x7 represents the course attendance data, x8 represents the degree of knowledge mastery, and y represents the student's test score;

[0123] S43. Use multiple hidden layers to extract the features of input data. The formula is: , where H is the output of the hidden layer, W and b are the weights and biases, is the ReLU function;

[0124] S44. Output the students’ learning status of the course. Map the features of the hidden layer to the students’ scores on the course learning status through the output layer. The formula is: ,in is the student's score on the course, W' and b' are the weight and bias of the output layer;

[0125] S45. Use the cross entropy loss function to optimize the model so that its predicted value is close to the actual student learning situation of the course.

[0126]

[0127] in is the true label, is the model-predicted score of students on their learning of the course;

[0128] S46. Use the Adam optimizer to update the weights and biases of the model to minimize the loss function:

[0129]

[0130] Where W new is the updated weight, W old is the weight before updating, is the learning rate, is the gradient of the loss function with respect to the weights.

[0131] Through the above model and calculation process, we can effectively evaluate students' learning of the course.

[0132] Teaching resource sharing platform: Establish a teaching resource sharing platform so that teachers from different specialties can share teaching resources and information and achieve the integration of teaching content.

[0133] Intelligent assisted teaching system: Develop an intelligent assisted teaching system that integrates the above modules to provide one-stop teaching assistance services for teachers and students.

[0134] The present invention conducts a more comprehensive assessment of students' basic knowledge level by comprehensively considering multiple dimensions such as the academic system, major, hours of prerequisite courses, and content forgetting, so that the teaching plan can more accurately match the students' actual level; and based on the neural network learning situation evaluation model, the real-time learning level of students for the course can be understood, the teaching content can be dynamically adjusted, the flexibility and adaptability of teaching can be improved, and the learning effect of students can be improved.

[0135] 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 combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0136] 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.

[0137] 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.

[0138] 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. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0139] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0140] 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.

[0141] 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.

[0142] 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. An AI-based medical imaging teaching assistance method, characterized in that: The following steps are involved: S1. Collect all students’ learning background information and evaluate their knowledge level. The learning background information includes the academic system, major, hours of prerequisite courses and content forgotten. The evaluation results are used to formulate teaching plans; S2. Intelligently plan course content based on the results of student knowledge level assessment to ensure that the teaching content matches the student's knowledge level; S3. Evaluate students' mastery of course knowledge points to dynamically adjust teaching content; S4. Input student data into the AI-based learning assessment model, and teachers optimize teaching content and methods based on the feedback from the model on students’ course learning; S5. Establish a teaching resource sharing platform so that teachers from different specialties can share teaching resources and information and achieve the integration of teaching content.

2. The AI-based medical imaging teaching auxiliary method according to claim 1, characterized in that: The specific method of formulating the teaching plan in S1 is as follows: The teaching contents of medical imaging include: Course A, Course B, Course C, ..., Course N; The prerequisite courses include basic courses A1, A2, ..., A m1 There are m1 courses related to course A; the corresponding class hours are T A1 ,T A2 ,...,T Am1 , and the interval from the study of medical imaging course is t A1 ,t A2 ,...,t Am1 , and the relevance to the medical imaging course a1, a2, ..., a m1 ; The prerequisite courses also include basic courses B1, B2, ..., B m2 There are m2 courses related to course B; the corresponding class hours are T B1 ,T B2 ,...,T Bm2 , and the interval from the study of medical imaging course is t B1 ,t B2 ,...,t Bm2 , and the relevance to medical imaging courses b1, b2, ..., b m2 ; The prerequisite courses also include basic courses C1, C2, ..., C m3 There are m3 courses related to course C; the corresponding class hours are T C1 ,T C2 ,...,T Cm3 , and the interval from the study of medical imaging course is t C1 ,t C2 ,...,t Cm3 , and the relevance to the medical imaging course c1,c2,...,c m3 ; ... The prerequisite courses also include basic courses N1, N2, ..., N related to the N course. mn There are mn courses related to N courses; the corresponding class hours are T N1 ,T N2 ,...,T Nmn , and the interval from the study of medical imaging course is t N1 ,t N2 ,...,t Nmn , and the relevance to the medical imaging course n1,n2,...,n mn ; The priority of N courses is calculated according to the following formula: ， Among them, P A is the teaching priority of course A, P B is the teaching priority of course B, P C is the teaching priority corresponding to course C, ..., P N The course priorities corresponding to N courses are compared, and the course arrangement is determined according to the priority. In the teaching process, courses with high priority are taught first, and the basic content of courses with low priority is consolidated.

3. The AI-based medical imaging teaching auxiliary method according to claim 2, characterized in that: The relevance of each of the above courses to the medical imaging course is determined by the mastery of the corresponding content as specified in the syllabus, the historical performance of the medical imaging course, and the performance of the prerequisite courses.

4. The AI-based medical imaging teaching auxiliary method according to claim 2, characterized in that: The evaluation method of S3 students’ mastery of course knowledge points is to divide the teaching content into multiple knowledge points d1, d2, ..., d N , and calculate the mastery of knowledge points according to the following formula: ， in, Indicates the mastery of the i-th knowledge point; Ti indicates the hours of the prerequisite courses related to the i-th knowledge point; ti indicates the interval between the prerequisite courses related to the i-th knowledge point and the knowledge points of the medical imaging course; Indicates the memory of the prerequisite courses related to the i-th one; k i is the number of sign-ins when learning the i-th knowledge point; e i is the learning time of the i-th knowledge point; y i is the extracurricular study time of the students of the i-th knowledge point; z i is the difficulty of the ith knowledge point, which is related to the score rate in the history test.

5. The AI-based medical imaging teaching auxiliary method according to claim 4 is characterized in that: The student data described in S4 include the student's prerequisite course grades, the medical imaging course hours learned, the supporting practice course time, the number of questions asked after class, the teacher's after-class answering time, the student's rating of the teacher, the course attendance data and the degree of mastery of knowledge points.

6. The AI-based medical imaging teaching auxiliary method according to claim 5, characterized in that: Establishing the AI-based learning assessment model described in S4 includes the following steps: S41. The collected historical student data is used as a data set. The historical student data includes students' prerequisite course grades, medical imaging course hours learned, supporting practical course time, number of questions asked after class, teacher's after-class answering time, students' ratings of teachers, course attendance data and knowledge points mastered, as well as the corresponding historical student test scores, and is normalized: ， Where X is the original data, X min and X max are the minimum and maximum values ​​of the data respectively; S42. Input the normalized data into the input layer, and divide the data into features X=[x1,x2,x3,x4,x5,x6,x7,x8] and corresponding labels Y=[y]; Among them, x1 represents the student's prerequisite course score, x2 represents the number of hours of medical imaging courses learned, x3 represents the supporting practical course time, x4 represents the number of questions asked after class, x5 represents the teacher's answer time after class, x6 represents the student's rating of the teacher, x7 represents the course attendance data, x8 represents the degree of knowledge mastery, and y represents the student's test score; S43. Use multiple hidden layers to extract the features of input data. The formula is: , where H is the output of the hidden layer, W and b are the weights and biases, is the ReLU function; S44. Output the students’ learning status of the course. Map the features of the hidden layer to the students’ scores on the course learning status through the output layer. The formula is: ,in is the student's score on the course, W' and b' are the weight and bias of the output layer; S45. Use the cross entropy loss function to optimize the model so that its output value is close to the actual student learning situation of the course. ， in is the true label, is the student's rating of the course learning situation output by the model; S46. Use the Adam optimizer to update the weights and biases of the model to minimize the loss function: ， Where W new is the updated weight, W old is the weight before updating, is the learning rate, is the gradient of the loss function with respect to the weights.

7. An AI-based medical imaging teaching auxiliary system comprising the method according to any one of claims 1 to 6, characterized in that: include: Student knowledge level assessment module: collects all students' learning information and assesses their basic knowledge level, including the length of study, major, hours of prerequisite courses and content forgotten. The assessment results are used to formulate teaching plans. Intelligent course content planning module: intelligently plan course content based on the results of student knowledge level assessment to ensure that the teaching content matches the student's knowledge level; Dynamic adjustment module of teaching content: evaluate students' mastery of course knowledge points to achieve dynamic adjustment of teaching content; Learning situation assessment module: input student data into the AI-based learning situation assessment model, and teachers further optimize teaching content and methods based on the students' course learning situation feedback from the model; Teaching resource sharing platform: Establish a teaching resource sharing platform, so that teachers from different specialties can share teaching resources and information and realize the integration of teaching content; Intelligent assisted teaching system: Develop an intelligent assisted teaching system that integrates the above modules to provide one-stop teaching assistance services for teachers and students.

8. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the AI-based medical imaging teaching auxiliary method described in any one of claims 1-6 are implemented.

9. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the computer instructions are executed, the steps of an AI-based medical imaging teaching auxiliary method described in any one of claims 1-6 are executed.

Images