Case patient image generation method based on artificial intelligence and medical teaching interaction method

Abstract

The invention discloses a case patient image generation method and a medical teaching interaction method based on artificial intelligence, and the method comprises the steps: S1, obtaining the current case data, and extracting the pathological feature data of a patient; s2, determining a global part contour of the current case patient image according to the pathological feature data; s3, generating global instruction feature data corresponding to the global part contour based on the mapping relationship between the human body part and the instruction feature; and S4, in response to the global instruction feature data, obtaining an image material corresponding to the global instruction feature data to generate a patient image. According to the method, the case and the patient image are intelligently matched, case information visualization is achieved, a teacher can visually know the corresponding case through the patient image without opening the case and checking text content, and therefore the efficiency of selecting and editing the case by the teacher is improved, and the utilization rate of teaching time is increased.

Description

Technical Field

[0001] This application relates to the field of medical simulation, and particularly to a method for generating case patient images based on artificial intelligence and a medical teaching interaction method. Background Art

[0002] In the case editing platforms of existing medical teaching systems, the compilation of case text materials is mainly carried out. At the same time, it can also include the patient's imaging examination pictures, examination videos, sounds (such as heart sounds, breathing sounds, etc.), and conversations (such as groans, dialogue voices, etc.). Due to concerns about patient privacy, patient images are generally not loaded, and instead, generic avatars are used. In the teaching process, it usually takes a lot of time for teachers to compile and input complete cases. And in the teaching on-site environment, it is also necessary to adjust and add cases according to the students' level of medical knowledge and real-time situations. If a large amount of time is spent in the process of case editing, it will reduce the utilization rate of classroom time. Sometimes, due to on-site case editing, there may be writing errors, resulting in inconsistencies between the patient's condition and the diagnosis and treatment process in the case, which may delay teaching time and, in severe cases, may mislead students. Therefore, improving the efficiency of teaching case compilation, ensuring the accuracy of cases, and enhancing the utilization of teaching time are the problems to be solved in this application. Summary of the Invention

[0003] To solve the above problems, this application provides a method for generating case patient images based on artificial intelligence, including the following steps: S1. Obtain the current case data and extract the pathological feature data of the patient; S2. Determine the global part contour of the current case patient image according to the pathological feature data; S3. Generate global instruction feature data corresponding to the global part contour based on the mapping relationship between human body parts and instruction features; S4. In response to the global instruction feature data, obtain image materials corresponding to the global instruction feature data to generate a patient image.

[0004] Further, step S2, determining the global part contour of the current case patient image according to the pathological feature data, includes: S201. Decouple each part of the human body according to the connection relationship of human body parts, establish a human body topological structure, and extract the internal connections between parts; S202. Determine the human body part where the patient's pathology is located according to the pathological feature data, and mark the human body part as the target part; S203. Determine the global part contour of the current case patient image based on the manifestation form of the patient's pathology and the target part.

[0005] Further, in step S203, based on the manifestation form of the patient's pathology and the target site, determine the global site contour of the current case patient image. The global site contour includes a necessary global site contour and a non-necessary global site contour. This step specifically includes: S2031, Set the head as the starting point of the global site contour, and mark each part of the human body from the head to the target site as a local contour; S2032, Determine whether the patient's pathology is an external manifestation feature. If so, mark the local contour as the necessary global site contour. If not, mark the head as the necessary global site contour, mark the other parts of the local contour as non-necessary global site contours, and set the random factor attribute.

[0006] Further, step S203 also includes: S2033, Set the random factor attribute of the other parts between the head and the edge part of the global site contour to be the same as that of the edge part.

[0007] Further, in step S3, based on the mapping relationship between human body parts and instruction features, generate the global instruction feature data corresponding to the global site contour, including: S301, Based on the mapping relationship between human body parts and instruction features, determine the global instruction feature set corresponding to the global site contour. The instruction features include basic features, social features, and pathological features; S302, According to the global instruction feature set, extract the corresponding instruction feature data from the current case; S303, Determine whether all the instruction features in the global instruction feature set match the corresponding instruction feature data; If so, determine the global instruction feature set and the corresponding instruction feature data as the global instruction feature data of the current case; If not, screen out the instruction features for which the corresponding instruction feature data cannot be matched, extract the corresponding instruction feature data from the historical case with the highest similarity, supplement it to the instruction feature data, and jointly form the global instruction feature data of the current case with the global instruction feature set.

[0008] Further, in step S303, extracting the corresponding instruction feature data from the historical case with the highest similarity specifically includes: If the instruction feature for which the corresponding instruction feature data cannot be matched is a basic instruction feature, extract the corresponding instruction feature data from the historical case with the highest basic feature similarity; If the instruction feature for which the corresponding instruction feature data cannot be matched is a social instruction feature, extract the corresponding instruction feature data from the historical case with the highest social feature similarity; The instruction features for which no corresponding instruction feature data is matched are pathological instruction features, and the corresponding instruction feature data is extracted from the historical cases with the highest pathological feature similarity.

[0009] Further, in step S4, in response to the global instruction feature data, obtaining image materials corresponding to the global instruction feature data to generate a patient image further includes constructing a patient image training model, and the training process includes: S401, constructing a training set, including: Collecting historical case data, obtaining the basic feature data, social feature data, and pathological feature data of each patient, and constructing an instruction feature set and an instruction feature data set; Constructing an image material set, including image materials and the meaning labels corresponding to the image materials; S402, using the instruction feature set and the instruction feature data set as inputs, and using the meaning labels and the corresponding image materials as output results for training, and supplementing meaning labels for the image materials during the training process; S403, fusing and adjusting the image materials in the output results to generate a patient image.

[0010] Further, before obtaining the image materials corresponding to the global instruction feature data to generate a patient image, it further includes the step of: judging whether the global instruction feature data is consistent with the historical global instruction feature data. If so, the historical patient image corresponding to the historical global instruction feature data is the patient image of the current case.

[0011] This application also provides a medical teaching interaction method, which is applied to a case editing platform and includes: Constructing a historical case library, where the historical cases include case data and patient images matched with the cases; Obtaining case editing data input by a user; Screening and displaying historical cases similar to the case editing data; If no similar historical cases are screened, then matching the corresponding patient image according to the case editing data and adding it to the historical case library; Among them, the patient image is obtained by the method for generating a case patient image based on artificial intelligence as described above.

[0012] The beneficial effects of this application are as follows: By obtaining the pathological feature data in the current case data, determining the global part contour of the patient image of the current case, adding instruction features to the global part contour based on the mapping relationship between human body parts and instruction features, and selecting corresponding image materials to generate the patient image, it is realized that the patient avatar is closer to and conforms to the personal information and pathological features of the patient in the current case, and the visual matching of the case and the patient avatar is realized. Thus, the case information can be quickly identified according to the patient avatar, so that in the teaching process, the teacher can directly understand the corresponding case without opening the case and viewing the text content, thereby improving the efficiency of the teacher in selecting and editing cases and enhancing the utilization rate of teaching time; Based on artificial intelligence, a patient image training model is constructed, realizing the intelligence of image generation. Description of the Drawings

[0013] Figure 1 It is a schematic flowchart of the method for generating a case patient image based on artificial intelligence according to an embodiment of this application.

[0014] Figure 2 It is a schematic flowchart of step S2 of an embodiment of this application.

[0015] Figure 3 It is a schematic flowchart of step S203 of an embodiment of this application.

[0016] Figure 4 It is a schematic flowchart of step S3 of an embodiment of this application.

[0017] Figure 5 It is a schematic flowchart of the training process of the patient image training model according to an embodiment of this application.

[0018] Figure 6 It is a schematic diagram of the mapping relationship between human body parts and instruction features according to an embodiment of this application.

[0019] Figure 7 It is a schematic diagram of patient images of the same contour based on different cases according to an embodiment of this application.

[0020] Figure 8 It is a schematic diagram of the case display interface on the editing platform in the medical teaching interaction method according to another embodiment of this application. Detailed Embodiments

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings of this application. Apparently, the described embodiments are some, but not all, of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of this application without creative efforts shall fall within the protection scope of this application.

[0022] In actual medical teaching, teaching cases are usually edited using a teaching system. These cases can be from clinical practice or independently edited by experienced teachers. Generally, they include records of medical activities such as medical staff's examination, diagnosis, and treatment of the occurrence, development, and outcome of a patient's disease. The content mainly includes materials such as text, symbols, charts, images, and slices. Usually, the case is named after the pathology. In practical applications, teachers can select suitable cases for teaching tasks according to the classroom content and send the cases to students through intelligent devices such as mobile phones, computers, and tablets. Since a large number of cases are generally preset in the system, it is difficult for teachers to quickly find the corresponding cases. Therefore, the embodiments of the present application provide an artificial intelligence-based method for generating patient images of cases, which matches data close to the case data, presents the basic information of the patient in the case (including but not limited to gender, age, weight, skin color, etc.), pathological features, social features, etc., visualizes the case information, facilitates teachers to quickly identify the case information, and thus quickly select the teaching cases required for classroom tasks, thereby reducing the waste of classroom time and improving the utilization rate of teaching time.

[0023] As Figures 1 to 6 shown, the embodiments of the present application provide an artificial intelligence-based method for generating patient images of cases, including: S1, obtaining the current case data and extracting the pathological feature data of the patient; S2, determining the global part contour of the current case patient image according to the pathological feature data; S3, generating global instruction feature data corresponding to the global part contour based on the mapping relationship between human body parts and instruction features; S4, in response to the global instruction feature data, obtaining image materials corresponding to the global instruction feature data to generate a patient image.

[0024] In this embodiment, by extracting the pathological feature data, information such as the occurrence site and condition of the patient's pathology in the case can be determined, so as to determine the human body part contour to be presented in the patient image.

[0025] Based on different human body parts, the features to be presented are different. As shown in Figure 6, some of the features corresponding to the presented human body parts are shown as a reference. For example, the head has features such as facial features, hair, skin color, and expression, while parts such as the body need to add features such as clothing. According to the human body part contour, corresponding features are added, such as facial features, clothing, etc., as well as the embodiment of the patient's basic information (including but not limited to gender, age, weight, skin color, etc.) and social attributes (including but not limited to personality, occupation, etc.) features on the patient image. By presenting these features on the patient image, the basic information, social attributes, and pathological features of the patient are presented closer to the patient.

[0026] Through this embodiment, based on the mapping relationship between human body parts and instruction features, the instruction features required for improving the patient image are perfected, and the corresponding image materials are extracted to generate the patient image, making the patient portrait closer to and conforming to the real patient features, visualizing the pathological features, so as to distinguish the pathological features of different patients and facilitate the visual recognition of the user's case information. For example, Figure 7 As shown in Figure 7 , a schematic diagram of the patient image generated based on the corresponding patient attributes in different cases for the same human body contour is shown.

[0027] Due to the variety of case types, some cases can present pathological features, such as phenotypic pathological features like external injuries and bleeding, while some cases do not have phenotypic pathological features. Through this step, the overall contour of the patient image can be determined according to the manifestation form of the pathology and the human body part where it is located, so that for different pathological parts and different manifestation forms, the patient image contours are different, avoiding all patient images presenting as complete human body images, highlighting the pathological features at the same time, facilitating visual search, and removing the feature addition of redundant human body parts, reducing the operation of data processing.

[0028] Therefore, in this embodiment, step S2, determining the global part contour of the patient image of the current case according to the pathological feature data, specifically includes: S201, decoupling each part of the human body according to the connection relationship of human body parts, establishing a human body topology structure, and extracting the internal connection between each part; S202, determining the human body part where the patient's pathology is located according to the pathological feature data, and marking the human body part as the target part; S203, based on the manifestation form of the patient's pathology and the target part, determining the global part contour of the patient image of the current case, where the global part contour includes a necessary global part contour and a non-necessary global part contour. This step specifically includes: S2031, setting the head as the starting point of the global part contour, and marking each part of the human body from the head to the target part as the local contour; S2032, judging whether the patient's pathology is an external phenotypic feature. If so, marking the local contour as the necessary global part contour; otherwise, marking the head as the necessary global part contour, marking the other parts of the local contour as the non-necessary global part contour, and setting the random factor attribute.

[0029] Due to the setting of the random factor, it may cause some parts or individual parts between the head and the end of the patient image to be non-display parts, resulting in the incoherence of the human body parts in the patient image and affecting the visual effect. Therefore, it further includes step S2033, setting the random factor attribute of the other parts between the head and the edge part of the global part contour to be the same as that of the edge part.

[0030] Since the case data is sourced from clinical practice or written by teachers, the content can be either rich or concise. For some cases, the feature data required to generate a patient image can be extracted, while for others, the feature data needed to generate a patient image may be lacking. Moreover, due to different feature data, the presentation of the patient image also varies.

[0031] Therefore, in this embodiment, step S3, based on the mapping relationship between human body parts and instruction features, generates global instruction feature data corresponding to the global part contour, which specifically includes: S301, based on the mapping relationship between human body parts and instruction features, determines the global instruction feature set corresponding to the global part contour. The instruction features include basic features, social features, and pathological features; S302, according to the global instruction feature set, extracts the corresponding instruction feature data from the current case; S303, determines whether all of the global instruction feature set matches the corresponding instruction feature data; If yes, determines the global instruction feature set and the corresponding instruction feature data as the global instruction feature data of the current case; If no, filters out the instruction features for which the corresponding instruction feature data has not been matched, extracts the corresponding instruction feature data from the historical case with the highest similarity, supplements it to the instruction feature data of the current case, and jointly constitutes the global instruction feature data of the current case with the global instruction feature set of the current case.

[0032] In order to make the instruction feature data extracted from historical cases closer to the cases and more in line with the patient image, therefore, in this implementation, in step S303, extracting the corresponding instruction feature data from the historical case with the highest similarity specifically includes: If the instruction feature for which the corresponding instruction feature data has not been matched is a basic instruction feature, extracts the corresponding instruction feature data from the historical case with the highest basic feature similarity; If the instruction feature for which the corresponding instruction feature data has not been matched is a social instruction feature, extracts the corresponding instruction feature data from the historical case with the highest social feature similarity; If the instruction feature for which the corresponding instruction feature data has not been matched is a pathological instruction feature, extracts the corresponding instruction feature data from the historical case with the highest pathological feature similarity.

[0033] In this implementation, step S4, in response to the global instruction feature data, obtains the image materials corresponding to the global instruction feature data to generate a patient image, and also includes constructing a patient image training model. The training process includes: S401, constructs a training set, including: Collects historical case data, obtains the basic feature data, social feature data, and pathological feature data of each patient, and constructs an instruction feature set and an instruction feature data set; Among them, the instruction feature set includes basic feature instructions, social feature instructions, and pathological feature instructions; the basic feature data includes but is not limited to the patient's name, gender, age, height, weight, race, etc., the social feature data includes but is not limited to the patient's personality, occupation, economic status, education level, etc., and the pathological feature data includes but is not limited to body surface features, expression features, body posture features, etc.; Construct an image material set, including image materials and the corresponding meaning labels of the image materials; S402: Use the instruction feature set and the instruction feature data set as inputs, and use the meaning labels and the corresponding image materials as the output results for training, and supplement the meaning labels for the image materials during the training process; S403: Integrate and adjust the image materials in the output results to generate a patient image.

[0034] In this step, by constructing a patient image training model, it is possible to quickly identify the case instruction features and match the corresponding image materials to generate a patient image.

[0035] In this embodiment, before obtaining the image materials corresponding to the global instruction feature data to generate a patient image, the following steps are further included: determining whether the global instruction feature data is consistent with the historical global instruction feature data. If so, the historical patient image corresponding to the historical global instruction feature data is the patient image of the current case.

[0036] The embodiment of the present application also provides a medical teaching interaction method, which is applied to a case editing platform and includes: Construct a historical case library, where the historical cases include case data and patient images matching the cases; Obtain the case editing data input by the user; Screen and display the historical cases similar to the case editing data; If no similar historical cases are screened, then match the corresponding patient image according to the case editing data and add it to the historical case library; Among them, the patient image is obtained by the above-mentioned method for generating a case patient image based on artificial intelligence.

[0037] As Figure 8 shown, it is the display of cases with different pathologies on the case editing platform. Teachers can quickly identify case information through the visual patient images matching the cases, so as to select the corresponding course teaching tasks and distribute them to students, improving the teacher's interaction experience, reducing the time for editing and screening cases, and improving the utilization rate of classroom time.

Claims

1. A method for generating case patient images based on artificial intelligence, characterized in that: The following steps are involved: S1, obtain the current case data and extract the patient's pathological characteristic data; S2, determining the global part contour of the current case patient image according to the pathological feature data; S3, generating global instruction feature data corresponding to the global part contour based on the mapping relationship between the human body parts and the instruction features; S4, in response to the global instruction feature data, acquiring image material corresponding to the global instruction feature data to generate a patient image.

2. The method for generating case patient images based on artificial intelligence according to claim 1, characterized in that: Step S2, determining the global part contour of the current case patient image according to the pathological feature data, including: S201, decoupling various parts of the human body according to the connection relationship between the parts of the human body, establishing a human body topological structure, and extracting the internal connection between the parts; S202, determining the body part where the patient's pathology is located according to the pathological characteristic data, and marking the body part as a target part; S203, determining a global part contour of the current case patient image based on the manifestation of the patient's pathology and the target part.

3. The method for generating case patient images based on artificial intelligence according to claim 2, characterized in that: Step S203, based on the manifestation of the patient's pathology and the target part, determine the global part contour of the current case patient image, the global part contour includes a necessary global part contour and a non-essential global part contour, this step specifically includes: S2031, setting the head as the starting point of the global part contour, marking various parts of the human body from the head to the target part as local contours; S2032, determining whether the patient's pathology is an external phenotypic feature, if yes, marking the local contour as a necessary global part contour, if no, marking the head as a necessary global part contour, marking other parts of the local contour as non-essential global part contours, and setting a random factor attribute.

4. The method for generating case patient images based on artificial intelligence according to claim 3, characterized in that: Step S203 also includes: S2033: Setting the random factor attributes of other parts between the head and the edge part of the global part contour to be consistent with the edge part.

5. The method for generating case patient images based on artificial intelligence according to claim 1, characterized in that: Step S3, based on the mapping relationship between the human body parts and the command features, generating global command feature data corresponding to the global part contour, including: S301, based on the mapping relationship between human body parts and instruction features, determining a global instruction feature set corresponding to the global part contour, wherein the instruction features include basic features, social features, and pathological features; S302, extracting corresponding instruction feature data from the current case according to the global instruction feature set; S303, determining whether all instruction features in the global instruction feature set match corresponding instruction feature data; Yes, determining that the global instruction feature set and the corresponding instruction feature data are the global instruction feature data of the current case; No, filter out the instruction features that are not matched to the corresponding instruction feature data, extract the corresponding instruction feature data from the historical cases with the highest similarity, add them to the instruction feature data, and together with the global instruction feature set, constitute the global instruction feature data of the current case.

6. The method for generating case patient images based on artificial intelligence according to claim 5, characterized in that: In step S303, the corresponding instruction feature data is extracted from the historical cases with the highest similarity, specifically including: The instruction feature that has not been matched to the corresponding instruction feature data is the basic instruction feature, and the corresponding instruction feature data is extracted from the historical cases with the highest basic feature similarity; The instruction feature that is not matched to the corresponding instruction feature data is a social instruction feature, and the corresponding instruction feature data is extracted from the historical cases with the highest social feature similarity; The instruction feature that is not matched to the corresponding instruction feature data is a pathological instruction feature, and the corresponding instruction feature data is extracted from the historical cases with the highest pathological feature similarity.

7. The method for generating case patient images based on artificial intelligence according to claim 1, characterized in that: Step S4, in response to the global instruction feature data, acquiring image materials corresponding to the global instruction feature data to generate a patient image, and also includes building a patient image training model, the training process includes: S401, build a training set, including: Collect historical case data, obtain basic characteristic data, social characteristic data, and pathological characteristic data of each patient, and build instruction characteristic sets and instruction characteristic data sets; Constructing an image material set, including image materials and meaning labels corresponding to the image materials; S402, taking the instruction feature set and the instruction feature data set as input, taking the meaning label and the corresponding image material as output results, and performing training, and supplementing the meaning label for the image material during the training process; S403: Fusing and adjusting the image materials in the output result to generate a patient image.

8. The method for generating case patient images based on artificial intelligence according to claim 7, characterized in that: Before obtaining the image material corresponding to the global instruction feature data to generate a patient image, the method also includes the steps of: determining whether the global instruction feature data is consistent with the historical global instruction feature data; if so, the historical patient image corresponding to the historical global instruction feature data is the patient image of the current case.

9. A medical teaching interactive method, characterized in that: Applied to case editing platform, including: Building a historical case database, wherein the historical cases include case data and patient images matching the cases; Get the case editing data entered by the user; Filter and display historical cases similar to the edited data of the case; If no similar historical cases are screened, the corresponding patient images are matched according to the case editing data and added to the historical case library; Wherein, the patient image is obtained by the patient image generation method described in any one of claims 1 to 8.

Images