Ophthalmic disease curative effect evaluation method and device, terminal equipment and storage medium

Abstract

The invention discloses an ophthalmic disease curative effect evaluation method and device, terminal equipment and a storage medium, and the method comprises the steps: determining a first visual feature set of a patient under disease deterioration and a second visual feature set of the patient under disease improvement according to the disease type and disease degree of the patient; processing the original image according to the first visual feature set and the second visual feature set to generate a plurality of candidate subjective images after improvement and deterioration for a patient to select, and comparing a target subjective image which is selected by the patient and conforms to the vision of the patient with an initial subjective image generated during the first doctor seeing; therefore, the eye disease treatment effect report of the patient can be finally determined, so that the patient can be helped to evaluate the eye disease treatment effect through the remote mobile terminal under the condition that the patient cannot see a doctor offline, and the patient can be effectively helped to know the treatment condition of the eye disease of the patient in time.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and particularly to a method, device, terminal device and storage medium for evaluating the curative effect of ophthalmic diseases. Background Art

[0002] Ophthalmic diseases are characterized by "seeing is the disease", and the diagnosis highly depends on symptoms, signs and image diagnosis. Visual symptoms are one of the most basic manifestations in ophthalmic diseases, and most patients have visual symptoms such as blurred vision and distorted vision. Different visual symptoms indicate different diseases. For example, if a patient feels that there is a layer of gauze in front of the eyes when looking at things, it may indicate cataracts, and distorted vision indicates age-related macular degeneration or related fundus diseases. Experienced doctors can initially judge the diseases suffered by patients based on their visual symptoms and also evaluate the treatment effect according to the changes in symptoms.

[0003] Therefore, for the current evaluation of the treatment effect of patients' eye diseases, patients need to go to a medical institution for a face-to-face consultation with a doctor after each treatment course. However, many patients cannot conduct an in-person consultation on time due to reasons such as the long distance to the ophthalmic hospital. In the case where patients and doctors cannot timely understand the condition, it may lead to no timely intervention when the disease worsens, and thus cause irreparable consequences. Summary of the Invention

[0004] Embodiments of the present invention provide a method, device, terminal device and storage medium for evaluating the curative effect of ophthalmic diseases, which can effectively help patients timely understand the treatment situation of their own eye diseases.

[0005] An embodiment of the present invention provides a method for evaluating the curative effect of ophthalmic diseases, which is applicable to a remote mobile terminal used by patients and includes:

[0006] Obtaining an original image, an initial subjective image, the disease type of the patient, and the degree of illness; wherein, the initial subjective image is an image video generated by modifying the original image according to the description made by the patient at the time of the initial diagnosis.

[0007] According to the disease type and the degree of illness, determining a first visual feature set of the patient in the case of disease deterioration and a second visual feature set of the patient in the case of disease improvement;

[0008] Processing the original image according to the first visual feature set and the second visual feature set to generate a plurality of candidate subjective images;

[0009] Compare the target subjective image with the initial subjective image to generate a comparison result, and generate a report on the treatment effect of the patient's eye disease based on the comparison result; wherein, the target subjective image is a candidate subjective image that the patient currently selects from the candidate subjective images after viewing the original image and that conforms to their own vision.

[0010] Further, determining the first visual feature set of the patient under disease deterioration and the second visual feature set of the patient under disease improvement according to the disease type and the degree of illness includes:

[0011] According to the degree of illness, determine several improvement levels and several deterioration levels compared to the degree of illness under all disease levels preset for the disease type.

[0012] According to the disease type, improvement level, and deterioration level, match several first visual features of the disease type at each deterioration level from a preset eye disease feature database to construct a first visual feature set, and match several second visual features of the disease type at each improvement level to construct a second visual feature set.

[0013] Further, the candidate subjective images include: a first candidate subjective image generated according to the first visual feature set and a second candidate subjective image generated according to the second visual feature set;

[0014] Processing the original image according to the first visual feature set and the second visual feature set to generate several candidate subjective images includes:

[0015] Randomly extract several first visual features from the first visual feature set multiple times to form several first video editing feature sequences;

[0016] Randomly extract several second visual features from the second video feature set multiple times to form several second video editing feature sequences;

[0017] Input the original image and each first video editing feature sequence into a video editing model respectively, so that the video editing model edits and adjusts the original image according to the first video editing feature sequence to generate the first candidate subjective image;

[0018] Input the original image and each second video editing feature sequence into a video editing model respectively, so that the video editing model edits and adjusts the original image according to the second video editing feature sequence to generate the second candidate subjective image.

[0019] Further, the construction of the video editing model includes:

[0020] Obtain a number of video images, extract a number of visual features from the eye disease feature database, and use the video editing feature sequences composed of a number of the visual features to edit each of the video images respectively to generate a number of visual images;

[0021] Construct model training samples according to each visual image, the video image corresponding to each visual image, and the video editing feature sequences composed of a number of visual features;

[0022] Construct an initial video editing model;

[0023] Use the visual images in each model training sample as the output, and use the video images and video editing feature sequences in the corresponding model training samples as the input to train the initial video editing model; during the training process, judge whether the initial video editing model converges according to the to-be-evaluated images output by the initial video editing model and the corresponding visual images, and generate the video editing model when it is determined that the initial video editing model converges.

[0024] Further, comparing the target subjective image with the initial subjective image to generate a comparison result includes:

[0025] According to the target subjective image, determine a number of target visual features of the target subjective image and the target disease levels corresponding to each target visual feature;

[0026] According to the initial subjective image, determine a number of initial visual features of the initial subjective image;

[0027] Compare the target visual features and the initial visual features, analyze the change trend of the patient's visual features, and use the target disease level and the change trend of the visual features as the comparison result.

[0028] Another embodiment of the present invention provides a device for evaluating the curative effect of ophthalmic diseases, including:

[0029] A data acquisition module, configured to acquire original images, an initial subjective image, the disease type of the patient, and the degree of illness; wherein, the initial subjective image is an image video generated by modifying the original image according to the description made by the patient at the first diagnosis;

[0030] A feature acquisition module, configured to determine a first set of visual features of the patient under disease deterioration and a second set of visual features of the patient under disease improvement according to the disease type and the degree of illness;

[0031] An image generation module, configured to process the original image according to the first set of visual features and the second set of visual features to generate a number of candidate subjective images;

[0032] A curative effect evaluation module, configured to compare a target subjective image with the initial subjective image to generate a comparison result, and generate a report on the treatment effect of the eye disease of the patient according to the comparison result; wherein, the target subjective image is a candidate subjective image selected by the patient from the candidate subjective images after viewing the original image currently and conforming to his own vision.

[0033] Further, the feature acquisition module determines a first visual feature set of the patient under disease deterioration and a second visual feature set of the patient under disease improvement according to the disease type and the degree of illness, including:

[0034] According to the degree of illness, determine several improvement levels and several deterioration levels compared with the degree of illness under all disease levels preset for the disease type;

[0035] According to the disease type, improvement level, and deterioration level, match several first visual features of the disease type at each deterioration level from a preset eye disease feature database to construct a first visual feature set, and match several second visual features of the disease type at each improvement level to construct a second visual feature set.

[0036] Further, the curative effect evaluation module compares the target subjective image with the initial subjective image to generate a comparison result, including:

[0037] According to the target subjective image, determine several target visual features of the target subjective image and the target disease level corresponding to each target visual feature;

[0038] According to the initial subjective image, determine several initial visual features of the initial subjective image;

[0039] Compare the target visual features and the initial visual features, analyze the change trend of the visual features of the patient, and use the target disease level and the change trend of the visual features as the comparison result.

[0040] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a method for evaluating the curative effect of an ophthalmic disease as described in any one of the above embodiments.

[0041] Another embodiment of the present invention provides a storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the storage medium is located to execute a method for evaluating the curative effect of an ophthalmic disease as described in any one of the above embodiments.

[0042] The implementation of the present invention has the following beneficial effects:

[0043] The present invention discloses a method, device, terminal device and storage medium for evaluating the curative effect of ophthalmic diseases. The method first determines a first visual feature set of a patient under disease deterioration and a second visual feature set of the patient under disease improvement according to the disease type and the degree of illness of the patient, and then processes the original image according to the first visual feature set and the second visual feature set to generate a number of candidate subjective images for the patient to select. Then, the target subjective image selected by the patient that matches his own vision is compared with the initial subjective image generated at the first visit, and finally, a report on the treatment effect of the patient's eye disease is determined. Therefore, the present invention can help patients evaluate the curative effect of eye diseases through a remote mobile terminal when they are unable to visit the doctor offline, effectively helping patients understand the treatment of their own eye diseases in a timely manner. Description of the Drawings

[0044] Figure 1 is a schematic flowchart of a method for evaluating the curative effect of ophthalmic diseases provided by an embodiment of the present invention.

[0045] Figure 2 is a schematic structural diagram of a device for evaluating the curative effect of ophthalmic diseases provided by an embodiment of the present invention. Detailed Embodiments

[0046] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above description of the drawings are intended to cover non-exclusive inclusion.

[0048] In the description of the embodiments of the present application, technical terms such as "first" and "second" are only used to distinguish different objects and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity, specific order or primary-secondary relationship of the indicated technical features. In the description of the embodiments of the present application, "a plurality" means two or more unless otherwise specifically defined.

[0049] As used herein, the mention of "embodiment" means that the specific features, structures, or characteristics described in connection with the embodiment may be included in at least one embodiment of the present application. The appearance of this phrase at various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0050] In the description of the embodiments of the present application, the term "and / or" is merely a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Additionally, the character " / " in this text generally indicates an "or" relationship between the associated objects before and after.

[0051] In the description of the embodiments of the present application, the term "plurality" refers to two or more (including two). Similarly, "multiple groups" refers to two or more groups (including two groups), and "multiple pieces" refers to two or more pieces (including two pieces).

[0052] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installation", "connection", "connection", "fixation", etc. should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or integrated; it can also be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to specific circumstances.

[0053] See Figure 1 , which is a schematic flowchart of a method for evaluating the curative effect of an ophthalmic disease provided by an embodiment of the present invention, including:

[0054] S1. Obtain the original image, the initial subjective image, the disease type of the patient, and the degree of illness; wherein, the initial subjective image is an image video generated by modifying the original image according to the description made by the patient during the initial diagnosis.

[0055] In a preferred embodiment of the present invention, this embodiment is applicable to the remote mobile terminal of the patient. The remote mobile terminal can be an intelligent device with an Internet connection function such as a mobile phone, a tablet computer, a laptop computer, etc. When the patient needs to evaluate the curative effect, the patient can evaluate the curative effect through the APP of the ophthalmic disease diagnosis and treatment institution loaded on the remote mobile terminal or by logging in to the website link of the ophthalmic disease diagnosis and treatment institution.

[0056] For patients with only one affected eye, at the first diagnosis, the patient uses the healthy eye to view the original image, and then describes the differences between the original images seen by the affected eye and the normal eye. A text-to-video model or a technician edits the original image according to the description to generate the initial subjective image seen by the patient's affected eye. For patients with both eyes affected, the patient describes the scene seen after viewing the original image to generate an image to be modified. After the patient undergoes a series of examinations to confirm the disease, the doctor asks questions based on the symptoms of the confirmed disease and improves the image to be modified according to the results of the questions to generate the initial subjective image.

[0057] Further, according to the diagnosis results of the patient's visit to the ophthalmology institution, determine the patient's disease type and degree of illness. For example, the disease type is: diabetic retinopathy, and the degree of illness is: severe non-proliferative diabetic retinopathy.

[0058] S2. According to the disease type and the degree of illness, determine the first visual feature set of the patient under disease deterioration and the second visual feature set of the patient under disease improvement;

[0059] Preferably, the step of determining the first visual feature set of the patient under disease deterioration and the second visual feature set of the patient under disease improvement according to the disease type and the degree of illness includes:

[0060] S21. According to the degree of illness, determine several improvement levels and several deterioration levels compared to the degree of illness among all disease levels preset for the disease type;

[0061] S22. According to the disease type, improvement level, and deterioration level, match several first visual features of the disease type at each deterioration level from a preset ophthalmic disease feature database to construct a first visual feature set, and match several second visual features of the disease type at each improvement level to construct a second visual feature set.

[0062] In a preferred embodiment of the present invention, still taking diabetic retinopathy as an example, the preset disease levels include: mild non-proliferative diabetic retinopathy, moderate non-proliferative diabetic retinopathy, severe non-proliferative diabetic retinopathy, proliferative diabetic retinopathy, and diabetic macular edema. When it is determined that the patient's initial visit is severe non-proliferative diabetic retinopathy, the improvement levels are mild non-proliferative diabetic retinopathy and moderate non-proliferative diabetic retinopathy, while the deterioration levels are proliferative diabetic retinopathy and diabetic macular edema.

[0063] Further, an eye disease feature database is pre - constructed, which records several types of eye diseases and the visual features of each eye disease under different conditions. For example: Patients with mild non - proliferative diabetic retinopathy will have slight blurred vision when looking at things. Patients with moderate non - proliferative diabetic retinopathy will have mild blurred vision, a slightly darker visual field area, and a slightly visual field defect. Patients with severe non - proliferative diabetic retinopathy will have obvious blurred vision, and there may be dark areas or black shadows in part of the visual field. Patients with proliferative diabetic retinopathy will have large black shadows or floating dark spots, the visual field may be severely blocked or there may be local blind areas, and at the same time, there will be a visual effect of severe vision fluctuations. Patients with diabetic macular edema will have distorted vision, a decline in color recognition ability, the colors of objects will appear darker or blurred, and there may be black spots or blind areas in the central visual field due to impaired central vision. Therefore, in this embodiment, the obtained visual features include the visual features of mild non - proliferative diabetic retinopathy, including: intermittent blurred vision; the visual features of moderate non - proliferative diabetic retinopathy, including: persistent blurred vision, a visual field occlusion area of 5 - 10%; the visual features of proliferative diabetic retinopathy, including: a visual field occlusion area > 10%, visual field vibration; the visual features of diabetic macular edema, including: distorted vision, the visual field occlusion area is located in the center of the visual field, etc.

[0064] S3. Process the original image according to the first visual feature set and the second visual feature set to generate a number of candidate subjective images;

[0065] Preferably, the candidate subjective images include: a first candidate subjective image generated according to the first visual feature set and a second candidate subjective image generated according to the second visual feature set;

[0066] The process of processing the original image according to the first visual feature set and the second visual feature set to generate a number of candidate subjective images includes:

[0067] S31. Randomly extract several first visual features from the first visual feature set multiple times to form several first video editing feature sequences;

[0068] S32. Randomly extract several second visual features from the second video feature set multiple times to form several second video editing feature sequences;

[0069] S33. Input the original image and each first video editing feature sequence into a video editing model respectively, so that the video editing model edits and adjusts the original image according to the first video editing feature sequence to generate the first candidate subjective image;

[0070] S34. Input the original image and each second video editing feature sequence into a video editing model respectively, so that the video editing model edits and adjusts the original image according to the second video editing feature sequence to generate the second candidate subjective image.

[0071] In a preferred embodiment of the present invention, considering the randomness of the patient's disease condition change and uncertain symptoms, a number of visual features are randomly selected from the first visual feature set and the second visual feature set. These visual features may belong to visual features of the same disease level or may be visual features of different disease levels.

[0072] Preferably, the construction of the video editing model includes:

[0073] S01. Obtain a number of video images, and extract a number of visual features from the eye disease feature database. Use the video editing feature sequences constituted by the number of visual features to edit each of the video images respectively to generate a number of visual images.

[0074] S02. Construct a model training sample according to each visual image, the video image corresponding to each visual image, and the video editing feature sequences constituted by a number of visual features.

[0075] S03. Construct an initial video editing model.

[0076] S04. Use the visual images in each model training sample as the output, and use the corresponding video images and video editing feature sequences in the model training sample as the input to train the initial video editing model. During the training process, judge whether the initial video editing model converges according to the to-be-evaluated image output by the initial video editing model and the corresponding visual image. When it is determined that the initial video editing model converges, generate the video editing model.

[0077] In a preferred embodiment of the present invention, a pre-trained video processing model such as vid2vid is selected; a series of image processing algorithms are defined based on disease progression knowledge, for example: blur filtering (simulating refractive error or macular degeneration), low contrast / low saturation (simulating optic neuropathy), visual field occlusion (simulating glaucoma visual field defect), distortion / fluctuation (simulating vitreous body lesion). Combining eye disease knowledge with different patients' individual data makes the conversion effect more in line with the real visual experience. Use the patient feedback data to fine-tune the model to improve the personalized effect.

[0078] S4. Compare the target subjective image with the initial subjective image to generate a comparison result, and generate a report on the treatment effect of the patient's eye disease based on the comparison result. The target subjective image is a candidate subjective image selected by the patient from the candidate subjective images that conforms to his own vision after viewing the original image currently.

[0079] In a preferred embodiment of the present invention, to avoid psychological suggestion when the patient selects a video, resulting in inaccurate selection of the image. In this embodiment, the candidate subjective images of improvement and deterioration are shuffled for the patient to select, so that after the patient observes the original video with the diseased eye, then uses the normal eye to select the target subjective image that conforms to his own vision from the candidate subjective images according to what the diseased eye observes.

[0080] Preferably, the comparison of the target subjective image with the initial subjective image to generate a comparison result includes:

[0081] S41. Determine a number of target visual features of the target subjective image and the corresponding target disease levels for each target visual feature according to the target subjective image.

[0082] S42. Determine a number of initial visual features of the initial subjective image according to the initial subjective image.

[0083] S43. Compare the target visual features and the initial visual features, analyze the change trend of the patient's visual features, and use the target disease level and the change trend of the visual features as the comparison result.

[0084] In a preferred embodiment of the present invention, if the target visual features in the target subjective image simultaneously adopt the visual features of visual field occlusion area > 10% in proliferative diabetic retinopathy and distorted vision in the visual features of diabetic macular edema with visual field vibration, then the change trend of the patient's visual features is the new symptoms of distorted vision and visual field vibration. The comparison result includes: proliferative diabetic retinopathy, diabetic macular edema, and the new symptoms of distorted vision and visual field vibration. And a report on the treatment effect of the eye disease is generated based on this comparison result.

[0085] This embodiment provides a method for evaluating the curative effect of ophthalmic diseases. First, according to the disease type and the degree of illness of the patient, the first visual feature set of the patient under disease deterioration and the second visual feature set of the patient under disease improvement are determined. Then, based on the first visual feature set and the second visual feature set, the original image is processed to generate a number of candidate subjective images for the patient to select. Furthermore, the target subjective image selected by the patient that matches his own vision is compared with the initial subjective image generated at the first visit, and finally, a report on the treatment effect of the patient's eye disease is determined, which effectively helps the patient to timely understand the treatment situation of his own eye disease.

[0086] See Figure 2 , which is a schematic structural diagram of an ophthalmic disease curative effect evaluation device provided by an embodiment of the present invention, including:

[0087] A data acquisition module for acquiring the original image, the initial subjective image, the disease type of the patient, and the degree of illness; wherein, the initial subjective image is an image video generated by modifying the original image according to the description made by the patient at the first diagnosis.

[0088] A feature acquisition module for determining the first visual feature set of the patient under disease deterioration and the second visual feature set of the patient under disease improvement according to the disease type and the degree of illness;

[0089] An image generation module for processing the original image according to the first visual feature set and the second visual feature set to generate a number of candidate subjective images;

[0090] A curative effect evaluation module for comparing the target subjective image with the initial subjective image to generate a comparison result, and generating a report on the treatment effect of the patient's eye disease according to the comparison result; wherein, the target subjective image is a candidate subjective image selected by the patient from the candidate subjective images that matches his own vision after watching the original image currently.

[0091] Preferably, the feature acquisition module determines the first visual feature set of the patient under disease deterioration and the second visual feature set of the patient under disease improvement according to the disease type and the degree of illness, including:

[0092] According to the degree of illness, determine several improvement levels and several deterioration levels compared with the degree of illness from all disease levels preset for the disease type;

[0093] According to the disease type, improvement level, and deterioration level, match a number of first visual features of the disease type at each deterioration level from a preset ophthalmic disease feature database to construct a first visual feature set, and match a number of second visual features of the disease type at each improvement level to construct a second visual feature set.

[0094] Preferably, the efficacy evaluation module compares the target subjective image with the initial subjective image to generate a comparison result, including:

[0095] According to the target subjective image, determine a number of target visual features of the target subjective image and the target disease level corresponding to each target visual feature;

[0096] According to the initial subjective image, determine a number of initial visual features of the initial subjective image;

[0097] Compare the target visual features and the initial visual features, analyze the change trend of the patient's visual features, and use the target disease level and the change trend of the visual features as the comparison result.

[0098] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that they have a communication connection, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement without creative work.

[0099] Those skilled in the art can clearly understand that for the convenience and simplicity, the specific working process of the device described above can refer to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0100] Another preferred embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements an ophthalmic disease efficacy evaluation method as described in any one of the above embodiments.

[0101] The terminal device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory.

[0102] The so-called processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the terminal device, and connects various parts of the entire terminal device through various interfaces and lines.

[0103] The memory can be used to store the computer program. By running or executing the computer program stored in the memory, and calling the data stored in the memory, the processor realizes various functions of the terminal device. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, at least one magnetic disk storage device, flash device, or other volatile solid-state storage devices.

[0104] Another preferred embodiment of the present invention provides a storage medium, which is a computer-readable storage medium. The computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiments can be realized. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0105] The above are the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements are also regarded as the protection scope of the present invention.

Claims

1. A method for evaluating the curative effect of an ophthalmic disease, characterized in that, A remote mobile terminal applicable to patient applications, including: Obtain the original image, the initial subjective image, the patient's disease type, and the degree of illness; wherein, the initial subjective image is an image video generated by modifying the original image according to the description made by the patient during the initial diagnosis of the original image. According to the disease type and the degree of illness, determine the first visual feature set of the patient under disease deterioration and the second visual feature set of the patient under disease improvement. Process the original image according to the first visual feature set and the second visual feature set to generate a number of candidate subjective images. Compare the target subjective image with the initial subjective image to generate a comparison result, and generate a report on the treatment effect of the patient's eye disease according to the comparison result; wherein, the target subjective image is a candidate subjective image selected from the candidate subjective images by the patient currently after viewing the original image and conforming to the patient's own vision.

2. The method for evaluating the curative effect of an ophthalmic disease according to claim 1, wherein The step of determining the first visual feature set of the patient under disease deterioration and the second visual feature set of the patient under disease improvement according to the disease type and the degree of illness includes: According to the degree of illness, determine several improvement levels and several deterioration levels compared to the degree of illness from all disease levels preset for the disease type. According to the disease type, improvement level, and deterioration level, match several first visual features of the disease type at each deterioration level from a preset eye disease feature database to construct a first visual feature set, and match several second visual features of the disease type at each improvement level to construct a second visual feature set.

3. The efficacy evaluation method for an ophthalmic disease according to claim 2, wherein The candidate subjective images include: a first candidate subjective image generated according to the first visual feature set and a second candidate subjective image generated according to the second visual feature set. The step of processing the original image according to the first visual feature set and the second visual feature set to generate a number of candidate subjective images includes: Randomly extract several first visual features from the first visual feature set multiple times to form several first video editing feature sequences. Randomly extract several second visual features from the second video feature set multiple times to form several second video editing feature sequences. Input the original image and each first video editing feature sequence into a video editing model respectively, so that the video editing model edits and adjusts the original image according to the first video editing feature sequence to generate the first candidate subjective image. Input the original image and each second video editing feature sequence into a video editing model respectively, so that the video editing model edits and adjusts the original image according to the second video editing feature sequence to generate the second candidate subjective image.

4. The method for evaluating the curative effect of an ophthalmic disease according to claim 3, wherein The construction of the video editing model includes: Obtain several video images, extract several visual features from the eye disease feature database, and use the video editing feature sequences composed of several of the visual features to edit each of the video images respectively to generate several visual images. Construct model training samples based on the video editing feature sequences composed of various visual images, the video images corresponding to the visual images, and a number of visual features; Construct an initial video editing model; Use the visual images in each model training sample as the output, and use the corresponding video images and video editing feature sequences in the model training samples as the input to train the initial video editing model; during the training process, judge whether the initial video editing model converges according to the to-be-evaluated images output by the initial video editing model and the corresponding visual images, and generate the video editing model when it is determined that the initial video editing model converges.

5. The efficacy evaluation method for an ophthalmic disease according to claim 4, characterized in that, The comparison of the target subjective image with the initial subjective image to generate a comparison result includes: Determine a number of target visual features of the target subjective image and the target disease levels corresponding to the target visual features according to the target subjective image; Determine a number of initial visual features of the initial subjective image according to the initial subjective image; Compare the target visual features and the initial visual features, analyze the change trend of the patient's visual features, and use the target disease level and the change trend of the visual features as the comparison result.

6. An efficacy evaluation device for ophthalmic diseases, characterized in that, Include: A data acquisition module for acquiring original images, an initial subjective image, the patient's disease type, and the degree of illness; wherein, the initial subjective image is an image video generated by modifying the original image according to the description of the original image made by the patient during the initial diagnosis. A feature acquisition module for determining a first set of visual features of the patient in the case of disease deterioration and a second set of visual features of the patient in the case of disease improvement according to the disease type and the degree of illness; An image generation module for processing the original image according to the first set of visual features and the second set of visual features to generate a number of candidate subjective images; An efficacy evaluation module for comparing the target subjective image with the initial subjective image to generate a comparison result, and generating an eye disease treatment effect report of the patient according to the comparison result; wherein, the target subjective image is a candidate subjective image selected from the candidate subjective images by the patient that conforms to his own vision after viewing the original image.

7. The efficacy evaluation device for an ophthalmic disease according to claim 6, characterized in that, The feature acquisition module determines the first set of visual features of the patient in the case of disease deterioration and the second set of visual features of the patient in the case of disease improvement according to the disease type and the degree of illness, including: Determine a number of improved levels and a number of deteriorated levels compared to the degree of illness from all disease levels preset for the disease type according to the degree of illness; Match a number of first visual features of the disease type at each of the deteriorated levels from a preset eye disease feature database according to the disease type, the improved levels, and the deteriorated levels to construct a first set of visual features, and match a number of second visual features of the disease type at each of the improved levels to construct a second set of visual features.

8. The efficacy evaluation device for an ophthalmic disease according to claim 7, characterized in that, The efficacy evaluation module compares the target subjective image with the initial subjective image to generate a comparison result, including: Determine a number of target visual features of the target subjective image and the target disease levels corresponding to the respective target visual features according to the target subjective image; Determine a number of initial visual features of the initial subjective image according to the initial subjective image; Compare the target visual features and the initial visual features, analyze the change trend of the visual features of the patient, and use the target disease level and the change trend of the visual features as the comparison result.

9. A terminal device, characterized in that, Comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements a method for evaluating the efficacy of an ophthalmic disease according to any one of claims 1 to 5.

10. A storage medium, characterized in that, The storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the storage medium is located to execute a method for evaluating the efficacy of an ophthalmic disease according to any one of claims 1 to 5.

Images