Artificial intelligence-based automated analysis color diagnosis system for fundus lesions

Abstract

This invention discloses an AI-based automatic analysis color diagnosis system for fundus lesions, relating to the field of ophthalmic disease diagnosis technology. It includes a fundus image acquisition module and an AI color analysis module. This AI-based automatic analysis color diagnosis system for fundus lesions, through its fundus image acquisition module, AI color analysis module, and analysis model construction module, inputs acquired fundus color images into a fundus color image processing and analysis model to obtain fundus color feature data. It then identifies the patient's lesions, diagnoses the patient's ophthalmic disease based on the identified lesions, and determines the location of the lesions in the fundus images using the fundus color feature data. This constructs a fundus image color evaluation system, improving the accuracy and reliability of ophthalmic diagnosis and assisting in the diagnosis and treatment of fundus diseases.

Description

Technical Field

[0001] This invention relates to the field of ophthalmic disease diagnosis technology, specifically to an artificial intelligence-based automatic analysis color diagnosis system for fundus lesions. Background Technology

[0002] The microvessels in the retina are the only microvessels in the human body that are not covered by skin or tissue and can be directly observed. Fundus photography can be obtained non-invasively and very economically, making it more suitable for large-scale screening. With the development of artificial intelligence technology in the field of medical imaging, screening for fundus diseases such as diabetic retinopathy, age-related macular degeneration, and glaucoma based on fundus photography has been widely used. However, current diagnoses of fundus diseases generally rely mainly on the physician's experience and the ability to detect disease, resulting in relatively poor accuracy and reliability. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention provides an artificial intelligence-based automatic analysis color diagnosis system for fundus lesions, which solves the problems mentioned in the background section.

[0004] To achieve the above objectives, the present invention is implemented through the following technical solution: an artificial intelligence-based automatic analysis color diagnosis system for fundus lesions, comprising a fundus image acquisition module, an AI color analysis module, a lesion identification module, a lesion tissue location determination module, a feature extraction module, a feature quantification module, a lesion tissue location acquisition module, an image labeling module, a data loading module, an analysis model construction module, a fundus lesion case collection module, a patient physiological and pathological structure data acquisition module, a fundus lesion color data mining module, a color feature supplementation module, a color evaluation standard construction module, an eye disease development law analysis module, and a fundus lesion color data acquisition module;

[0005] The fundus image acquisition module is used to acquire color photos of the fundus of a patient during an eye examination.

[0006] The AI ​​color analysis module is used to input the acquired fundus color photo and analyze it.

[0007] The feature extraction module is used to accurately extract the color features of the physiological and pathological structures of the fundus in the patient's fundus photographs;

[0008] The feature quantification module is used to quantify the extracted physiological and pathological structural color features of the patient's fundus;

[0009] The lesion identification module is used to identify the patient's lesions based on the acquired fundus color feature data;

[0010] The lesion location determination module is used to determine the location of lesions in a patient's fundus photograph using fundus color feature data, and to make a preliminary diagnosis of the patient's eye disease.

[0011] The lesion location acquisition module is used to acquire the location of lesions in fundus color images;

[0012] The image labeling module is used to mark the location of identified lesions in fundus color images;

[0013] The basis loading module is used to load judgment basis at the lesion marking location;

[0014] The analysis model construction module is used to construct a fundus color image processing and analysis model based on an optimized fundus color image processing and analysis algorithm.

[0015] The fundus lesion case collection module is used to collect previous fundus lesion cases;

[0016] The patient physiological and pathological structure data acquisition module is used to extract the patient's fundus physiological and pathological structures from collected fundus lesion cases, as well as the fundus physiological and pathological structures obtained from the dissection of previous specimens.

[0017] The fundus lesion color data acquisition module is used to extract fundus physiological and pathological structural color feature data from collected fundus lesion cases.

[0018] The fundus lesion color data mining module is used to perform in-depth mining of the fundus physiological and pathological structural color feature data from previous cases.

[0019] The color feature supplementation module is used to supplement the missing color feature data of the physiological and pathological structures of the fundus;

[0020] The color evaluation standard construction module is used to construct color evaluation standards based on in-depth data mining of color features;

[0021] The eye disease development pattern analysis module is used to analyze the development pattern of eye diseases based on in-depth data mining of color features, and to obtain the development pattern of eye diseases.

[0022] Optionally, the loading module includes a lesion feature acquisition module, a lesion feature analysis module, a recognition basis generation module, an AI sentence generation model, a corpus input module, an eye disease case input module, an eye disease terminology acquisition module, and a corpus acquisition module. The lesion feature acquisition module is used to acquire color features for lesion identification; the lesion feature analysis module is used to analyze the acquired color features; the recognition basis generation module is used to generate judgment criteria based on the analysis results; the AI ​​sentence generation model is used to input the analysis results into the model and automatically generate text sentences; the corpus input module is used to input eye disease corpus; the eye disease terminology acquisition module is used to collect and acquire eye disease terms; the corpus acquisition module is used to organize the collected eye disease terms and generate eye disease corpus; and the eye disease case input module is used to input collected eye disease cases.

[0023] Optionally, the image marking module includes an image acquisition module, a location positioning module, and a region marking module. The image acquisition module acquires original fundus color images for the diagnosis of fundus lesions. The location positioning module is used to determine the location of the lesion on the acquired fundus color image. The region marking module is used to mark the determined lesion location on the acquired fundus color image.

[0024] Optionally, the AI ​​sentence generation model is constructed based on machine learning and natural language processing technologies.

[0025] Optionally, the fundus image acquisition module is provided with an interactive port with the hospital image archiving and communication system to acquire fundus color images generated when a patient undergoes an eye examination and stored within the hospital image archiving and communication system.

[0026] Optionally, after marking the location of the lesion in the patient's fundus color photograph and loading the data, the lesion location determination module sends the diagnostic results and the fundus color photograph to the attending physician to assist the attending physician in diagnosing the patient's disease.

[0027] Optionally, after receiving the diagnostic data sent by this system, the attending physician can open the fundus color photograph and view the location of the lesions marked on the fundus color photograph and the basis for judgment, so as to diagnose the patient's disease.

[0028] Optionally, after the analysis model construction module constructs the fundus color image processing and analysis model, it needs to train, evaluate, and optimize the fundus color image processing and analysis model using training and evaluation samples constructed from collected fundus lesion cases to generate the final fundus color image processing and analysis model.

[0029] This invention provides an artificial intelligence-based automatic analysis color diagnosis system for fundus lesions, which has the following beneficial effects:

[0030] 1. This AI-based automated analysis color diagnosis system for fundus lesions comprises a fundus image acquisition module, an AI color analysis module, and an analysis model construction module. The acquired fundus images are input into a fundus color image processing and analysis model, which accurately extracts the color features of the patient's physiological and pathological fundus structures from the images. These extracted features are then quantified. The system uses the acquired fundus color feature data to identify lesions in the patient and diagnose the patient's eye disease based on the identified lesions. By using the fundus color feature data, the system determines the location of lesions in the fundus images, thereby constructing a fundus image color evaluation system. This improves the accuracy and reliability of ophthalmic diagnosis and assists in the diagnosis and treatment of fundus diseases.

[0031] 2. This AI-based automatic analysis color diagnosis system for fundus lesions, comprising a lesion identification module, a lesion location determination module, and an image marking module, determines the location of lesions in fundus images using fundus color feature data. It then marks the identified lesion locations in the fundus images, acquires color features for lesion identification, analyzes these features, generates judgment criteria based on the analysis results, and inputs the analysis results into an AI statement generation model. The model automatically generates text statements, which in turn generate disease diagnosis criteria. These criteria are then loaded at the lesion marking locations, and the diagnosis results, along with the fundus images, are sent to the attending physician. Upon receiving the diagnostic data from this system, the attending physician can open the fundus images to view the marked lesion locations and judgment criteria, enabling disease diagnosis and improving the accuracy and efficiency of patient eye disease identification. Attached Figure Description

[0032] Figure 1 This is a schematic diagram of the system structure of the present invention;

[0033] Figure 2 This is a schematic diagram of the loading module structure based on the present invention;

[0034] Figure 3 This is a schematic diagram of the image tagging module structure of the present invention.

[0035] The diagram shows: 1. Fundus image acquisition module; 2. AI color analysis module; 3. Lesion identification module; 4. Lesion location determination module; 5. Feature extraction module; 6. Feature quantification module; 7. Lesion location acquisition module; 8. Image labeling module; 9. Evidence loading module; 10. Analysis model construction module; 11. Fundus lesion case collection module; 12. Patient physiological and pathological structure data acquisition module; 13. Fundus lesion color data mining module; 14. Color feature supplementation module; 15. Color evaluation standard construction module; 16. Eye disease development law analysis module; 17. Fundus lesion color data acquisition module; 18. Lesion feature acquisition module; 19. Lesion feature analysis module; 20. Recognition evidence generation module; 21. AI sentence generation model; 22. Corpus input module; 23. Eye disease case input module; 24. Eye disease terminology acquisition module; 25. Corpus acquisition module; 26. Image acquisition module; 27. Location positioning module; 28. Region labeling module. Detailed Implementation

[0036] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0037] Please see Figures 1 to 3 This invention provides a technical solution: an AI-based automatic analysis color diagnosis system for fundus lesions, comprising a fundus image acquisition module 1, an AI color analysis module 2, a lesion identification module 3, a lesion tissue location determination module 4, a feature extraction module 5, a feature quantification module 6, a lesion tissue location acquisition module 7, an image labeling module 8, a data loading module 9, an analysis model construction module 10, a fundus lesion case collection module 11, a patient physiological and pathological structure data acquisition module 12, a fundus lesion color data mining module 13, a color feature supplementation module 14, a color evaluation standard construction module 15, an eye disease development law analysis module 16, and a fundus lesion color data acquisition module 17.

[0038] Fundus image acquisition module 1 is used to acquire color photos of the fundus of a patient during an eye examination;

[0039] AI color analysis module 2 is used to input the acquired fundus color photo and analyze it;

[0040] Feature extraction module 5 is used to accurately extract the color features of the physiological and pathological structures of the fundus in patient fundus color photographs;

[0041] Feature quantization module 6 is used to quantify the extracted color features of the physiological and pathological structures of the patient's fundus;

[0042] The lesion identification module 3 is used to identify the patient's lesions based on the acquired fundus color feature data;

[0043] The lesion location determination module 4 is used to determine the location of lesions in the patient's fundus color photographs through fundus color feature data, and to make a preliminary diagnosis of the patient's eye disease.

[0044] The lesion location acquisition module 7 is used to acquire the location of lesions in fundus color images;

[0045] Image labeling module 8 is used to mark the location of identified lesions in fundus color photographs;

[0046] According to loading module 9, it is used to load judgment criteria at the lesion marking location;

[0047] The analysis model construction module 10 is used to construct a fundus color image processing and analysis model based on the optimized fundus color image processing and analysis algorithm;

[0048] The fundus lesion case collection module 11 is used to collect previous fundus lesion cases;

[0049] The patient physiological and pathological structure data acquisition module 12 is used to extract the patient's fundus physiological and pathological structures from collected fundus lesion cases, as well as the fundus physiological and pathological structures obtained from the dissection of previous specimens.

[0050] The fundus lesion color data acquisition module 17 is used to extract fundus physiological and pathological structural color feature data from collected fundus lesion cases;

[0051] The fundus lesion color data mining module 13 is used to perform in-depth mining of the fundus physiological and pathological structural color feature data from previous cases.

[0052] Color feature supplementation module 14 is used to supplement the missing color feature data of fundus physiological and pathological structures;

[0053] The color evaluation standard construction module 15 is used to construct color evaluation standards based on in-depth data mining of color features;

[0054] The Eye Disease Development Pattern Analysis Module 16 is used to analyze the development pattern of eye diseases based on in-depth data mining of color features, and to obtain the development pattern of eye diseases.

[0055] Furthermore, those skilled in the art will recognize that the loading module 9 includes a lesion feature acquisition module 18, a lesion feature analysis module 19, a recognition basis generation module 20, an AI sentence generation model 21, a corpus input module 22, an eye disease case input module 23, an eye disease terminology acquisition module 24, and a corpus acquisition module 25. The lesion feature acquisition module 18 is used to acquire color features for lesion identification; the lesion feature analysis module 19 is used to analyze the acquired color features; the recognition basis generation module 20 is used to generate judgment basis based on the analysis results; the AI ​​sentence generation model 21 is used to input the analysis results into the model and automatically generate text sentences through the model; the corpus input module 22 is used to input eye disease corpus; the eye disease terminology acquisition module 24 is used to collect and acquire eye disease terms; the corpus acquisition module 25 is used to organize the collected eye disease terms and generate eye disease corpus; and the eye disease case input module 23 is used to input collected eye disease cases so that professional eye disease judgment basis can be automatically generated.

[0056] Furthermore, those skilled in the art will recognize that the image labeling module 8 includes an image acquisition module 26, a location positioning module 27, and a region labeling module 28. The image acquisition module 26 acquires original fundus color images for the diagnosis of fundus lesions. The location positioning module 27 is used to determine the location of the lesion on the acquired fundus color image. The region labeling module 28 is used to label the determined lesion location on the acquired fundus color image to assist the attending physician in diagnosing eye diseases in patients.

[0057] Furthermore, those skilled in the art will know that the AI ​​sentence generation model 21 is constructed based on machine learning technology and natural language processing technology, which makes the diagnostic basis for eye diseases generated by the AI ​​sentence generation model 21 highly professional.

[0058] Furthermore, those skilled in the art will recognize that the fundus image acquisition module 1 is provided with an interactive port with the hospital image archiving and communication system to acquire fundus color images generated when patients undergo eye examinations and stored within the hospital image archiving and communication system, so that data between this system and the hospital image archiving and communication system can be interconnected.

[0059] Furthermore, those skilled in the art will know that after marking the location of the lesion in the patient's fundus color photograph and loading the data, the lesion location determination module 4 sends the diagnostic results and the fundus color photograph to the attending physician to assist the attending physician in diagnosing the patient's disease and improve the accuracy and efficiency of identifying the patient's eye disease.

[0060] Furthermore, those skilled in the art will understand that after receiving the diagnostic data sent by this system, the attending physician can open the fundus color photograph, view the location of the lesions marked on the fundus color photograph and the basis for judgment, so as to diagnose the patient's disease and improve the accuracy of identifying the patient's eye disease.

[0061] Furthermore, those skilled in the art will know that after the analysis model construction module 10 constructs the fundus color image processing and analysis model, it needs to train, evaluate, and optimize the fundus color image processing and analysis model using training and evaluation samples constructed from collected fundus lesion cases, so as to generate the final fundus color image processing and analysis model, thereby making the applied fundus color image processing and analysis model have a better effect on the processing and analysis of the color features of fundus physiological and pathological structures.

[0062] In summary, this AI-based automated color diagnosis system for fundus lesions utilizes the following: During an eye examination, fundus images are retrieved from the hospital's image archiving and communication system via the fundus image acquisition module 1. These images are then input into a fundus color image processing and analysis model, which precisely extracts the color features of the patient's physiological and pathological fundus structures. These extracted features are quantified, and the acquired fundus color feature data is used to identify lesions. Based on the identified lesions, the system diagnoses the patient's eye disease using the fundus color feature data. The system determines the location of lesions in a patient's fundus image, marks the identified lesion tissue locations in the fundus image, obtains color features for lesion identification, analyzes the obtained color features, generates judgment criteria based on the analysis results, inputs the analysis results into AI statement generation model 21, the model automatically generates text statements, and then generates disease diagnosis criteria, loads the judgment criteria at the lesion markings, and sends the diagnosis results and fundus image to the attending physician. After receiving the diagnostic data sent by this system, the attending physician can open the fundus image and view the marked lesion locations and judgment criteria on the fundus image to make a disease diagnosis for the patient.

[0063] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. An artificial intelligence-based automatic analysis color diagnosis system for fundus lesions, characterized in that: It includes a fundus image acquisition module (1), an AI color analysis module (2), a lesion identification module (3), a lesion tissue location determination module (4), a feature extraction module (5), a feature quantification module (6), a lesion tissue location acquisition module (7), an image labeling module (8), a basis loading module (9), an analysis model construction module (10), a fundus lesion case collection module (11), a patient physiological and pathological structure data acquisition module (12), a fundus lesion color data mining module (13), a color feature supplementation module (14), a color evaluation standard construction module (15), an eye disease development law analysis module (16), and a fundus lesion color data acquisition module (17). The fundus image acquisition module (1) is used to acquire color photos of the fundus generated when the patient undergoes an eye examination; The AI ​​color analysis module (2) is used to input the acquired fundus color photo and analyze the fundus color photo; The feature extraction module (5) is used to accurately extract the color features of the physiological and pathological structures of the patient's fundus in fundus color photographs; The feature quantization module (6) is used to quantify the extracted physiological and pathological structural color features of the patient's fundus; The lesion identification module (3) is used to identify the patient's lesions based on the acquired fundus color feature data; The lesion location determination module (4) is used to determine the location of the lesion in the patient's fundus color photograph through fundus color feature data, and to make a preliminary diagnosis of the patient's eye disease. The lesion location acquisition module (7) is used to acquire the location of lesions in fundus color images; The image marking module (8) is used to mark the location of the identified lesion tissue in the fundus color photograph; The loading module (9) is used to load the judgment criteria at the lesion mark; The analysis model construction module (10) is used for optimized fundus color image processing and analysis. The algorithm is used to construct a model for processing and analyzing fundus color images; The fundus lesion case collection module (11) is used to collect previous fundus lesion cases; The patient physiological and pathological structure data acquisition module (12) is used to extract the patient's fundus physiological and pathological structures from the collected fundus lesion cases, as well as the fundus physiological and pathological structures obtained by dissecting previous specimens. The fundus lesion color data acquisition module (17) is used to extract fundus physiological and pathological structural color feature data from the collected fundus lesion cases; The fundus lesion color data mining module (13) is used to perform in-depth mining of fundus physiological and pathological structural color feature data from previous cases. The color feature supplementation module (14) is used to supplement the missing color feature data of the physiological and pathological structures of the fundus; The color evaluation standard construction module (15) is used to construct the color evaluation standard based on the color feature depth mining data; The eye disease development pattern analysis module (16) is used to analyze the eye disease development pattern based on the color feature depth mining data and obtain the eye disease development pattern.

2. The artificial intelligence-based automatic analysis color diagnosis system for fundus lesions according to claim 1, characterized in that: The loading module (9) includes a lesion feature acquisition module (18), a lesion feature analysis module (19), an identification basis generation module (20), an AI sentence generation model (21), a corpus input module (22), an eye disease case input module (23), an eye disease terminology acquisition module (24), and a corpus acquisition module (25). The lesion feature acquisition module (18) is used to acquire color features for identifying lesions; the lesion feature analysis module (19) is used to analyze the acquired color features; the identification basis generation module (20) is used to generate judgment basis based on the analysis results; the AI ​​sentence generation model (21) is used to input the analysis results into the model and automatically generate text sentences through the model; the corpus input module (22) is used to input eye disease corpus; and the eye disease terminology acquisition module (24) is used to collect and acquire eye disease terminology. The corpus acquisition module (25) is used to organize the collected eye disease terms and generate eye disease corpus; the eye disease case input module (23) is used to input the collected eye disease cases.

3. The artificial intelligence-based automatic analysis color diagnosis system for fundus lesions according to claim 1, characterized in that: The image marking module (8) includes an image acquisition module (26), a location positioning module (27), and a region marking module (28). The image acquisition module (26) acquires original fundus color images for the diagnosis of fundus lesions. The location positioning module (27) is used to determine the location of the lesion on the acquired fundus color image. The region marking module (28) is used to mark the determined lesion location on the acquired fundus color image.

4. The artificial intelligence-based automatic analysis color diagnosis system for fundus lesions according to claim 2, characterized in that: The AI ​​sentence generation model (21) is constructed based on machine learning technology and natural language processing technology.

5. The artificial intelligence-based automatic analysis color diagnosis system for fundus lesions according to claim 1, characterized in that: The fundus image acquisition module (1) is connected to the hospital image archiving and communication system via an interactive port to acquire fundus color photos of patients undergoing eye examinations stored within the hospital image archiving and communication system.

6. The artificial intelligence-based automatic analysis color diagnosis system for fundus lesions according to claim 1, characterized in that: The lesion location determination module (4) marks the lesion location in the patient's fundus color photo and loads the data, then sends the diagnosis results and fundus color photo to the attending physician to assist the attending physician in diagnosing the patient's disease.

7. The artificial intelligence-based automatic analysis color diagnosis system for fundus lesions according to claim 6, characterized in that: After receiving the diagnostic data sent by this system, the attending physician can open the fundus color photograph, view the location of the lesions marked on the fundus color photograph and the basis for judgment, so as to make a diagnosis of the patient's disease.

8. The color diagnosis of fundus lesions based on artificial intelligence automatic analysis according to claim 1 The system is characterized by: After constructing the fundus color image processing and analysis model, the analysis model construction module (10) needs to train, evaluate and optimize the fundus color image processing and analysis model by constructing training evaluation samples from collected fundus lesion cases, and generate the final fundus color image processing and analysis model.

Images