CN115147372A

Movatterモバイル変換

Info

Publication number: CN115147372A
Application number: CN202210780260.XA
Authority: CN
Inventors: 冯军; 郝文晖; 刘毅; 张少良
Original assignee: Hainan Rongshujia Information Technology Co ltd
Current assignee: Hainan Rongshujia Information Technology Co ltd
Priority date: 2022-07-04
Filing date: 2022-07-04
Publication date: 2022-10-04
Anticipated expiration: 2042-07-04
Also published as: CN115147372B

Abstract

The invention discloses a traditional Chinese medicine tongue image intelligent treatment method and a system based on medical image segmentation, wherein the method comprises the following steps: acquiring a tongue image of a patient; extracting tongue body characteristics in the tongue body image, wherein the tongue body characteristics comprise a tongue shape characteristic value, a tongue coating color characteristic value and a tongue quality state characteristic value; calculating the weight of each constitution type corresponding to the tongue body characteristics by combining a preset tongue diagnosis and differentiation model; calculating the weight of each zang-fu organ syndrome differentiation corresponding to the tongue body characteristics by combining the tongue diagnosis syndrome differentiation model; and determining the constitutional type and the syndrome differentiation of the viscera of the patient according to the weight of each constitutional type and the weight of each syndrome differentiation of the viscera. The invention can provide more comprehensive diagnosis basis in the tongue diagnosis process, accurately analyze the condition of the patient based on syndrome differentiation, intelligently judge the tongue body information through the image processing technology and assist the diagnosis and treatment of the patient.

Description

Traditional Chinese medicine tongue image intelligent treatment distinguishing method and system based on medical image segmentation

Technical Field

The invention relates to the technical field of medical image processing, in particular to a traditional Chinese medicine tongue image intelligent treatment method and system based on medical image segmentation.

Background

The tongue diagnosis is one of the important methods for diagnosing diseases in traditional Chinese medicine, and meanwhile, the tongue diagnosis can also be used as an important method for auxiliary diagnosis and treatment in the current medical diagnosis system as an important component of a traditional Chinese medicine theoretical system.

The traditional tongue diagnosis scheme is based on tongue image expression analysis of the visceral relation of tongue quality reaction, but cannot specifically analyze the constitutional information of patients according to the tongue quality, because the different tongue image feedback symptoms are different, the diagnosis treatment is carried out by depending on the subjective consciousness of doctors, more comprehensive diagnosis basis is lacked, and the condition of the patients is difficult to accurately analyze according to the syndrome under partial scenes.

Therefore, there is a need for a method for intelligently identifying and treating tongue images in traditional Chinese medicine based on medical image segmentation, which combines artificial intelligence to identify tongue images, avoids time and labor waste and error occurrence in manual tongue diagnosis, and intelligently judges tongue information through an image processing technology to assist diagnosis and treatment of patients.

Disclosure of Invention

In order to solve the technical problems that manual tongue diagnosis is time-consuming and labor-consuming and errors are easy to occur, the invention provides a traditional Chinese medicine tongue image intelligent identification and treatment method and system based on medical image segmentation, and the specific technical scheme is as follows:

the invention provides a traditional Chinese medicine tongue image intelligent treatment method based on medical image segmentation, which comprises the following steps:

acquiring a tongue image of a patient;

extracting tongue features in the tongue image, wherein the tongue features comprise tongue shape feature values, tongue coating color feature values and tongue quality state feature values;

calculating the weight of each constitution type corresponding to the tongue body characteristics by combining a preset tongue diagnosis differentiation model;

calculating the weight of each zang-fu organ syndrome differentiation corresponding to the tongue body characteristics by combining the tongue diagnosis syndrome differentiation model;

and determining the constitutional type and the syndrome differentiation of the viscera of the patient according to the weight of each constitutional type and the weight of each syndrome differentiation of the viscera.

The traditional Chinese medicine tongue image intelligent treatment method based on medical image segmentation provided by the invention automatically judges the physique type and the viscera syndrome differentiation of the patient according to the tongue shape, the tongue fur color, the tongue quality state of the patient and a preset tongue diagnosis syndrome differentiation model by extracting the characteristics of the tongue body image of the patient, accurately differentiates and analyzes the condition of the patient by combining the neural network model in the tongue diagnosis process, avoids the influence of artificial errors on the diagnosis result, and improves the intelligence and the accuracy of the tongue diagnosis process.

In some embodiments, before the acquiring the tongue image of the patient, the method further includes:

pre-collecting the constitution types, the viscera syndrome differentiation and the tongue body images of a plurality of patients;

constructing a tongue picture knowledge graph according to the corresponding constitution types, the corresponding viscera syndrome differentiation and the tongue body images of each patient;

and inputting the tongue image knowledge graph into a neural network model of the image and training to obtain the tongue diagnosis and syndrome differentiation model.

The tongue image intelligent treatment method based on medical image segmentation provided by the invention builds the low latitude representation information of the traditional Chinese medicine constitution identification results such as constitution types, viscera identification and tongue images by establishing the tongue image knowledge graph and extracting the characteristic vector from the knowledge graph through the graph neural network, realizes the extraction of the graph expression relationship among the constitution types, viscera identification and tongue images through the deep learning algorithm of the graph neural network, further determines the effects of the traditional Chinese medicine constitution identification results such as the constitution types and viscera identification of patients, and improves the intellectualization, convenience and accuracy of the tongue diagnosis process.

In some embodiments, after said pre-acquiring said types of constitutions, said differentiation of visceral syndromes, and said tongue image of a plurality of patients, before said inputting said tongue image knowledge map into said neural network model for training to obtain said tongue diagnosis differentiation model, further comprises:

adopting an image segmentation algorithm to segment a first tongue region image in the tongue image;

denoising the first tongue body area image to obtain a second tongue body area image;

carrying out image segmentation on the second tongue body area image through an edge detection algorithm to obtain a third tongue body area image;

and constructing a tongue picture knowledge graph according to the corresponding constitution types, the corresponding internal organ syndrome differentiation and the third tongue region image of each patient.

The tongue image is preprocessed by the traditional Chinese medicine tongue image intelligent discrimination method based on medical image segmentation, so that the processed tongue region image has more representation, and the recognition speed and the recognition accuracy of the recognition process of patient constitution type and viscera discrimination according to the tongue image are improved.

In some embodiments, the extracting tongue features in the tongue image specifically includes:

performing image segmentation on the tongue body image to obtain a tongue shape image, a tongue fur image and a tongue texture image;

generating the tongue shape characteristic value, the tongue coating color characteristic value and the tongue quality state characteristic value according to the tongue shape image, the tongue coating image and the tongue quality image respectively;

and combining the tongue shape characteristic value, the tongue coating color characteristic value and the tongue quality state characteristic value to generate a multi-dimensional tongue body characteristic vector as the tongue body characteristic.

The traditional Chinese medicine tongue image intelligent identification and treatment method based on medical image segmentation provided by the invention has the technical effect of judging the constitution of a patient according to the multi-dimensional characteristics of the tongue shape, the tongue fur color, the tongue proper state and the like of the patient by respectively extracting the tongue shape characteristic value, the tongue fur color characteristic value and the tongue proper state characteristic value and combining the tongue shape characteristic value, the tongue fur color characteristic value and the tongue proper state characteristic value to generate the multi-dimensional tongue proper vector as the tongue proper characteristic.

In some embodiments, said determining the type of constitutions and the syndrome differentiation of the zang-fu organ of said patient according to the weight of each of said types of constitutions and the weight of each of said syndrome differentiation further comprises:

constructing a symptom corresponding relation knowledge graph in advance according to the tongue body characteristics, symptom information and preset symptoms corresponding to each patient;

receiving the symptom information of the patient;

and determining the symptoms of the patient according to the tongue body characteristics, the symptom information and the symptom corresponding relation knowledge graph.

The traditional Chinese medicine tongue image intelligent treatment method based on medical image segmentation can intelligently judge the symptoms of the patient according to the symptom information, the tongue body characteristics and the constitution type of the patient, evaluate the physical condition of the user from multiple angles, comprehensively analyze the symptoms of the patient by combining the symptom information and the tongue body image of the patient, and improve the accuracy of judgment of the symptoms of the patient.

In some embodiments, said determining a symptom of said patient further comprises:

judging whether the confidence of the symptom is greater than a preset confidence threshold;

when the confidence of the symptom is not larger than the confidence threshold, judging the symptom as a suspected symptom;

outputting diagnostic questions corresponding to the suspected symptoms according to a preset question-answer database, wherein the question-answer database is preset with corresponding relations between each suspected symptom and a plurality of diagnostic questions;

and receiving a question and answer result input by the patient, and determining the actual symptoms of the patient according to the question and answer result.

According to the intelligent traditional Chinese medicine tongue image distinguishing method based on medical image segmentation, provided by the invention, after the patient symptoms are judged, the diagnosis problem corresponding to the symptoms of which the symptom confidence coefficient is not greater than the confidence coefficient threshold is output, the actual symptoms are determined according to the question and answer result of the patient, the deviation of the symptom diagnosis result is dynamically adjusted according to the body condition fed back by the user, and the accuracy and the reliability of the intelligent traditional Chinese medicine tongue image distinguishing method based on medical image segmentation are improved.

In some embodiments, after determining the actual symptom of the patient according to the question-answer result, the method further comprises:

and outputting medication advice, diet advice and exercise advice of the patients according to a preset diagnosis advice model, the physique types, the syndrome differentiation of the viscera and the actual symptoms, wherein the diagnosis advice model is generated by deep learning based on the physique types, the syndrome differentiation of the viscera, the actual symptoms, the medication advice, the diet advice and the exercise advice of a plurality of patients acquired in advance.

The traditional Chinese medicine tongue image intelligent discrimination and treatment method based on medical image segmentation can generate the medication suggestion, the diet suggestion and the motion suggestion of a patient in the intelligent tongue diagnosis process, carry out deep learning according to the historical tongue diagnosis result, intelligently generate the treatment schemes of the patient such as the medication suggestion, the diet suggestion and the motion suggestion, and improve the intelligence and the accuracy of the treatment scheme generated according to the tongue diagnosis result of the patient.

In some embodiments, according to another aspect of the present invention, the present invention also provides a system for intelligent diagnosis and treatment of tongue image in traditional Chinese medicine based on medical image segmentation, comprising:

the acquisition module is used for acquiring a tongue body image of a patient;

the extraction module is connected with the acquisition module and is used for extracting tongue body characteristics in the tongue body image, wherein the tongue body characteristics comprise a tongue shape characteristic value, a tongue coating color characteristic value and a tongue quality state characteristic value;

the first calculation module is connected with the extraction module and used for calculating the weight of each constitution type corresponding to the tongue body characteristics by combining a preset tongue diagnosis and differentiation model;

the second calculation module is connected with the extraction module and is used for calculating the weight of each zang-fu organ syndrome differentiation corresponding to the tongue body characteristics by combining the tongue diagnosis syndrome differentiation model;

and the judging module is respectively connected with the first calculating module and the second calculating module and is used for determining the constitution types and the syndrome differentiation of the viscera of the patient according to the weight of each constitution type and the weight of each syndrome differentiation of the viscera.

In some embodiments, according to another aspect of the present invention, the present invention further provides an intelligent device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to execute the computer program stored in the memory, and implement the operations performed by the above intelligent tongue image identification method based on medical image segmentation.

In some embodiments, according to another aspect of the present invention, there is also provided a storage medium having at least one instruction stored therein, which is loaded and executed by a processor to implement the operations performed by the above-mentioned tongue image intelligent discrimination method based on medical image segmentation.

The invention provides a traditional Chinese medicine tongue image intelligent treatment method and system based on medical image segmentation, which at least comprise the following technical effects:

(1) The method has the advantages that the characteristics of the tongue body image of the patient are extracted, the physique type and the viscera syndrome differentiation of the patient are automatically judged according to the tongue shape, the tongue fur color, the tongue quality state and the preset tongue diagnosis syndrome differentiation model of the patient, the condition of the patient is accurately analyzed in a syndrome differentiation manner by combining the neural network model in the tongue diagnosis process, the influence of artificial errors on a diagnosis result is avoided, and the intelligence and the accuracy of the tongue diagnosis process are improved;

(2) By establishing a tongue picture knowledge graph and extracting characteristic vectors from the knowledge graph through a graph neural network, low latitude representation information of traditional Chinese medicine constitution identification results such as constitution types, viscera syndrome differentiation and the like is constructed, the drawing expression relationship among the constitution types, the viscera syndrome differentiation and tongue body images is extracted through a deep learning algorithm of the graph neural network, the effects of the traditional Chinese medicine constitution identification results such as the constitution types, the viscera syndrome differentiation and the like of a patient are further determined, and the intellectualization, the convenience and the accuracy of a tongue diagnosis process are improved;

(3) The tongue body image is preprocessed through an image segmentation algorithm, a denoising process and an edge detection algorithm, so that the processed tongue body region image is more representative, and the recognition speed and the recognition accuracy of the recognition process of the patient constitution type and viscera syndrome differentiation according to the tongue body image are improved;

(4) The technical effect of judging the physique of the patient according to the multi-dimensional characteristics of the tongue shape, the tongue fur color, the tongue quality state and the like of the patient is realized by respectively extracting the tongue shape characteristic value, the tongue fur color characteristic value and the tongue quality state characteristic value and combining the tongue shape characteristic value, the tongue fur color characteristic value and the tongue quality state characteristic value to generate a multi-dimensional tongue body characteristic vector as the tongue body characteristic;

(5) The syndrome of the patient can be intelligently judged according to the symptom information, the tongue characteristic and the constitution type of the patient, the physical condition of the user is evaluated in multiple angles, the symptom of the patient is comprehensively analyzed by combining the symptom information and the tongue image of the patient, and the accuracy of judging the syndrome of the patient is improved;

(6) After the patient's symptoms are judged, the diagnosis problem corresponding to the symptom of which the symptom confidence coefficient is not greater than the confidence coefficient threshold value is output, the actual symptoms are determined according to the question-answer result of the patient, the deviation of the symptom diagnosis result is dynamically adjusted according to the body condition fed back by the user, and the accuracy and the reliability of the traditional Chinese medicine tongue image intelligent treatment method based on medical image segmentation are improved;

(7) In the intelligent tongue diagnosis process, a medication suggestion, a diet suggestion and an exercise suggestion of a patient are generated, deep learning is carried out according to historical tongue diagnosis results, treatment schemes such as the medication suggestion, the diet suggestion and the exercise suggestion of the patient are generated intelligently, and the intelligence and the accuracy of the treatment scheme generated according to the tongue diagnosis results of the patient are improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.

FIG. 1 is a flow chart of an intelligent tongue image identification method based on medical image segmentation in accordance with the present invention;

FIG. 2 is a flow chart of a tongue diagnosis and differentiation model training method for tongue diagnosis and differentiation based on medical image segmentation in the present invention;

FIG. 3 is a flow chart of preprocessing a tongue image in the intelligent tongue image identification method based on medical image segmentation according to the present invention;

FIG. 4 is a flow chart of the method for determining the symptoms of a patient according to the present invention;

FIG. 5 is another flowchart of the method for determining the symptoms of a patient according to the present invention;

FIG. 6 is another flowchart of the intelligent tongue image identification method based on medical image segmentation according to the present invention;

FIG. 7 is a diagram of an example of an intelligent tongue image identification system based on medical image segmentation according to the present invention;

fig. 8 is an exemplary diagram of a smart device of the present invention.

Reference numbers in the figures: an acquisition module-10, an extraction module-20, a first calculation module-30, a second calculation module-40, a judgment module-50, a smart device-100, a processor-110, a memory-120 and a computer program-121.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

For the sake of simplicity, the drawings only schematically show the parts relevant to the present invention, and they do not represent the actual structure as a product. In addition, in order to make the drawings concise and understandable, components having the same structure or function in some of the drawings are only schematically depicted, or only one of them is labeled. In this document, "one" means not only "only one" but also a case of "more than one".

It should be further understood that the term "and/or" as used in this specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items and includes such combinations.

In addition, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not intended to indicate or imply relative importance.

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description will be made with reference to the accompanying drawings. It is obvious that the drawings in the following description are only some examples of the invention, and that for a person skilled in the art, other drawings and embodiments can be derived from them without inventive effort.

The traditional tongue diagnosis tool can only analyze the visceral relation of tongue quality reaction based on tongue image expression, but cannot specifically analyze the principal symptoms and the tongue image expression and significance of a patient according to the tongue quality, and because of thought differences of different prescriptions, most doctors cannot effectively analyze the disease formation and the change after treatment of the patient according to the tongue image in the process of diagnosing and differentiating the symptoms of the patient, the symptoms fed back by different tongue images are different, the diagnosis is differentiated only by subjective consciousness, more comprehensive diagnosis is lacked, and the patient condition cannot be more accurately differentiated and analyzed, so that the invention discloses the following intelligent tongue image differentiation and treatment method based on medical image segmentation in traditional Chinese medicine.

One embodiment of the present invention, as shown in fig. 1, provides a method for intelligently discriminating tongue images in traditional Chinese medicine based on medical image segmentation, comprising the steps of:

s200, tongue body images of the patient are acquired.

S300 extracting tongue features in the tongue image.

S400, calculating the weight of each constitution type corresponding to the tongue body characteristics by combining a preset tongue diagnosis and differentiation model.

Specifically, the tongue diagnosis differentiation model is generated by performing deep learning training in advance according to the patient constitution types, the viscera differentiation and the tongue body characteristics in the historical diagnosis data, and after inputting the tongue body characteristics such as the tongue shape characteristic value, the tongue coating color characteristic value and the tongue quality state characteristic value into the tongue diagnosis differentiation model, the tongue diagnosis differentiation model generates corresponding weights of the differentiation directions of viscera differentiation, qi and blood differentiation, body fluid differentiation, six excesses differentiation and the like.

S500, calculating the corresponding weight of the tongue body characteristics according to the syndrome differentiation of each zang-fu organ by combining the tongue diagnosis and syndrome differentiation model.

Specifically, after the tongue body characteristics such as the tongue shape characteristic value, the tongue coating color characteristic value, and the tongue proper state characteristic value are input into the tongue diagnosis and differentiation model, the tongue diagnosis and differentiation model generates corresponding weights for each body type such as qi deficiency, mild nature, and yang deficiency.

S600, determining the constitutional type and the syndrome differentiation of the viscera of the patient according to the weight of each constitutional type and the weight of each syndrome differentiation of the viscera.

Specifically, a weight threshold of the constitutional type and a weight threshold of the differentiation of syndromes of the zang-fu organs are preset, when the weight is greater than the weight threshold of the constitutional type, the constitutional type is determined as the constitutional type of the patient, when the weight is greater than the weight threshold of the differentiation of syndromes of the zang-fu organs, the differentiation of syndromes of the zang-fu organs is determined as the differentiation of syndromes of the zang-fu organs of the patient, the constitutional type and the differentiation of syndromes of the zang-fu organs of the patient can be various, for example, the patient can be both of the plastid type with qi deficiency and the plastid type with yang deficiency.

The intelligent traditional Chinese medicine tongue image treatment method based on medical image segmentation provided by the embodiment automatically judges the physique type and the internal organs of a patient according to the tongue shape, the tongue fur color, the tongue quality state of the patient and a preset tongue diagnosis model by extracting the characteristics of the tongue body image of the patient, accurately analyzes the patient condition by combining the neural network model in the tongue diagnosis process, avoids the influence of artificial errors on the diagnosis result, and improves the intelligence and the accuracy of the tongue diagnosis process.

In one embodiment, as shown in fig. 2, before acquiring the tongue image of the patient in step S200, the method further includes:

s110, the constitutional types, the zang-fu organs syndrome differentiation and the tongue body images of a plurality of patients are collected in advance.

S120, constructing a tongue image knowledge map according to the corresponding constitution types, the corresponding zang-fu organ syndrome differentiation and the tongue body images of each patient.

S130, inputting the tongue image knowledge graph into a neural network model of the image and training to obtain a tongue diagnosis and syndrome differentiation model.

The tongue image intelligent treatment distinguishing method based on medical image segmentation provided by the embodiment establishes the tongue image knowledge base and extracts the characteristic vector from the knowledge base through the neural network to construct the low-latitude representation information of the traditional Chinese medicine constitution identification results such as the constitution types, the internal organ syndrome differentiation and the like, realizes the extraction of the graph expression relationship among the constitution types, the internal organ syndrome differentiation and the tongue image through the deep learning algorithm of the neural network, further determines the effects of the traditional Chinese medicine constitution identification results such as the constitution types, the internal organ syndrome differentiation and the like of patients, and improves the intellectualization, the convenience and the accuracy of the tongue diagnosis process.

In one embodiment, as shown in fig. 3, before acquiring the tongue image of the patient in step S200, the method further includes:

S121, segmenting the first tongue region image in the tongue image by adopting an image segmentation algorithm.

Specifically, the tongue image is subjected to image segmentation through an OpenCV image segmentation algorithm.

S122, denoising the first tongue body area image to obtain a second tongue body area image.

Specifically, a second tongue region image is obtained by performing denoising preprocessing by a wavelet transform technique.

And S123, carrying out image segmentation on the second tongue body area image through an edge detection algorithm to obtain a third tongue body area image.

S124, constructing a tongue picture knowledge graph according to the corresponding constitution types, the viscera syndrome differentiation and the third tongue region images of the patients.

Specifically, the steps S121 to S124 may be used for preprocessing the tongue image of the patient during the tongue image knowledge base generation process, or may be applied to the segmentation and denoising processing and the like on the tongue image to be detected after the tongue image of the patient is acquired in step S200 and before the tongue features in the tongue image are extracted in step S300.

S130, inputting the tongue image knowledge map into the neural network model of the map for training to obtain a tongue diagnosis syndrome differentiation model.

In one embodiment, in the execution process of extracting the tongue feature in the tongue image in step S300, after the tongue shape, the tongue fur color and the tongue proper state are recognized through the U2NET, the tongue shape feature value, the tongue fur color feature value and the tongue proper state feature value may be generated according to the tongue shape image, the tongue fur image and the tongue proper image, respectively, and the tongue shape feature value, the tongue fur color feature value and the tongue proper state feature value are combined to generate a multi-dimensional tongue feature vector as the tongue feature to be input to the tongue diagnosis and treatment model.

In one embodiment, as shown in fig. 4, after determining the constitutional type and the syndrome differentiation of the zang-fu organs according to the weight of each constitutional type and the weight of each zang-fu organ syndrome differentiation in step S600, the method further comprises:

s710, constructing a symptom corresponding relation knowledge graph in advance according to tongue body characteristics, symptom information and preset symptoms corresponding to each patient.

Specifically, the symptom corresponding relation knowledge graph stores the corresponding relation between the tongue body characteristics, the symptom information and the physique type of the patient, for example, when the tongue body characteristics of the patient are pale tongue or white, fat and tender tongue, and the patient is accompanied with symptoms information such as listlessness, pale complexion, shortness of breath and no speaking, cough and asthma weakness, sweating on exertion, and weak pulse, the symptom of the patient is judged to be the qi-deficiency syndrome; when the tongue body of the patient is characterized by pale tongue or withered and white tongue, and is accompanied by symptom information such as pale and lusterless complexion or sallow complexion, pale nail and white lip, dizziness, palpitation, insomnia, hypomenorrhea, delayed periods or amenorrhea, thready pulse and weakness, the symptom of the patient is judged to be blood deficiency syndrome.

S720 receives symptom information of the patient.

S730, according to the tongue body characteristics, the symptom information and the symptom corresponding relation knowledge graph, the symptoms of the patient are determined.

The intelligent traditional Chinese medicine tongue image treatment method based on medical image segmentation can intelligently judge the symptoms of a patient according to the symptom information, the tongue body characteristics and the constitution type of the patient, evaluate the physical condition of a user from multiple angles, comprehensively analyze the symptoms of the patient by combining the symptom information and the tongue body image of the patient, and improve the accuracy of judgment of the symptoms of the patient.

In one embodiment, as shown in fig. 5, after determining the symptom of the patient according to the tongue body characteristics, the symptom information, the type of the body constitution of the patient and the symptom correspondence knowledge graph in step S730, the method further includes:

s810, judging whether the confidence of the symptom is larger than a preset confidence threshold.

S820, when the confidence of the syndrome is not larger than the threshold of the confidence, the syndrome is judged to be a suspected syndrome.

Specifically, when the confidence of a symptom is greater than the confidence threshold, the symptom is judged to be an actual symptom.

Illustratively, the confidence threshold is set to 95%, when the confidence of the symptom is lower than 95%, interactive question answering is carried out according to the question answering database, and the confidence of the suspected symptom is further determined.

S830, according to the preset question-answer database, the diagnosis question corresponding to the suspected symptom is output.

Specifically, the question-answer database is preset with the corresponding relation between each suspected symptom and a plurality of diagnostic questions.

S840, receiving the question and answer result input by the patient, and determining the actual symptom of the patient according to the question and answer result.

Illustratively, when the suspected symptom of the patient is the heart-yin deficiency syndrome, the diagnosis question of whether the patient is palpitation, vexation, insomnia, dreaminess, dry mouth and throat, emaciation, flushed cheeks or feverish palms and soles, tidal fever and night sweat, red tongue with little coating and poor fluid, thready and rapid pulse and the like is set, and when the question and answer result input by the user exceeds 80 percent, the heart-yin deficiency syndrome is judged as the actual symptom of the patient.

After the patient's symptoms are judged, the intelligent traditional Chinese medicine tongue image treatment method based on medical image segmentation outputs diagnosis problems corresponding to symptoms of which the symptom confidence coefficient is not greater than the confidence coefficient threshold, determines actual symptoms according to the question and answer results of the patient, dynamically adjusts deviation of the symptom diagnosis results according to the body conditions fed back by the user, and improves the accuracy and the reliability of the intelligent traditional Chinese medicine tongue image treatment method based on medical image segmentation.

In one embodiment, as shown in fig. 6, after step S840 receives the question-answer result input by the patient and determines the actual symptom of the patient according to the question-answer result, the method further includes:

s900, according to the preset diagnosis suggestion model, the constitution types, the visceral syndrome differentiation and the actual symptoms, the medication suggestion, the diet suggestion and the exercise suggestion of the patient are output.

Specifically, the diagnosis suggestion model is generated based on the constitution types, the organ syndrome differentiation, the actual symptoms, the medication suggestion, the diet suggestion and the exercise suggestion of a plurality of patients collected in advance, and deep learning is performed.

The intelligent traditional Chinese medicine tongue image identification method based on medical image segmentation provided by the embodiment can generate medication suggestions, diet suggestions and motion suggestions of a patient in the intelligent tongue diagnosis process, perform deep learning according to historical tongue diagnosis results, intelligently generate treatment schemes such as the medication suggestions, the diet suggestions and the motion suggestions of the patient, and improve the intelligence and the accuracy of the treatment scheme generated according to the tongue diagnosis results of the patient.

In one embodiment, according to another aspect of the present invention, as shown in fig. 7, the present invention further provides a system for intelligent tongue image identification and treatment in traditional Chinese medicine based on medical image segmentation, which comprises an obtaining module 10, an extracting module 20, a first calculating module 30, a second calculating module 40 and a judging module 50.

Wherein the acquisition module 10 is used for acquiring tongue images of a patient.

Specifically, the in-process of obtaining the patient tongue body image can be through the real-time collection patient tongue body image of camera, also can receive the tongue body image that the patient uploaded, and the display content of tongue body image need not only contain the tongue body part, also can include patient oral cavity image, partial facial image and environment image, to the requirement of tongue body image for including the clear tongue body characteristic of patient can, be convenient for follow-up carry out the segmentation of tongue body characteristic according to the tongue body image.

The extraction module 20 is connected to the acquisition module 10, and is configured to extract tongue features in the tongue image.

The first calculating module 30 is connected to the extracting module 20, and is configured to calculate the weight of each body type corresponding to the tongue body characteristics by combining a preset tongue diagnosis and differentiation model.

Specifically, the tongue diagnosis differentiation model is generated by performing deep learning training according to the constitutional types, the zang-fu organ differentiation and the tongue body characteristics of the patients in the historical diagnosis data in advance, and after inputting the tongue body characteristics such as the tongue shape characteristic value, the tongue fur color characteristic value, the tongue nature state characteristic value and the like into the tongue diagnosis differentiation model, the tongue diagnosis differentiation model can generate the corresponding weights of each differentiation direction such as zang-fu organ differentiation, qi-blood differentiation, body fluid differentiation, six-excesses differentiation and the like.

The second calculating module 40 is connected to the extracting module 20 and is configured to calculate the weight of each zang-fu organ syndrome differentiation corresponding to the tongue body characteristics by combining the tongue diagnosis syndrome differentiation model.

Specifically, after the tongue body characteristics such as the tongue shape characteristic value, the tongue coating color characteristic value, and the tongue quality state characteristic value are input into the tongue diagnosis and differentiation model, the tongue diagnosis and differentiation model generates corresponding weights of each body type such as qi deficiency, peace and yang deficiency.

The judging module 50 is respectively connected to the first calculating module 30 and the second calculating module 40, and is used for determining the constitutional type and the syndrome differentiation of the viscera of the patient according to the weight of each constitutional type and the weight of each syndrome differentiation of the viscera.

Specifically, a weight threshold of the constitutional type and a weight threshold of the differentiation of syndromes of the zang-fu organs are preset, when the weight is greater than the weight threshold of the constitutional type, the constitutional type is determined as the constitutional type of the patient, when the weight is greater than the weight threshold of the differentiation of syndromes of the zang-fu organs, the differentiation of syndromes of the zang-fu organs is determined as the differentiation of syndromes of the zang-fu organs of the patient, the constitutional type and the differentiation of syndromes of the zang-fu organs of the patient can be various, for example, the patient can be both of the constitutional type of deficiency of qi and the constitutional type of deficiency of yang.

The traditional Chinese medicine tongue image intelligent diagnosis and treatment system based on medical image segmentation provided by the embodiment automatically judges the physique type and the viscera diagnosis of a patient according to the tongue shape, the tongue fur color, the tongue quality state and the preset tongue diagnosis model of the patient by extracting the characteristics of the tongue body image of the patient, accurately analyzes the patient condition by combining the neural network model in the tongue diagnosis process, avoids the influence of artificial errors on the diagnosis result, and improves the intelligence and the accuracy of the tongue diagnosis process.

In one embodiment, as shown in fig. 8, the present invention further provides a smart device 100, which comprises a processor 110, a memory 120, wherein the memory 120 is used for storing a computer program 121; the processor 110 is configured to execute the computer program 121 stored in the memory 120 to implement the above-mentioned tongue image intelligent identification and treatment method based on medical image segmentation in the corresponding method embodiment.

In one embodiment, the present invention further provides a storage medium, in which at least one instruction is stored, and the instruction is loaded and executed by a processor to implement the operations performed in the above embodiment of the intelligent Chinese medical tongue image identification and treatment method based on medical image segmentation, for example, the storage medium may be a read-only memory (ROM), a Random Access Memory (RAM), a compact disc read-only memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.

In the foregoing embodiments, the descriptions of the respective embodiments have their respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or recited in detail in a certain embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiments provided in the present application, it should be understood that the disclosed method and system for intelligent tongue image identification based on medical image segmentation can be implemented in other ways. For example, the above-described embodiment of the tongue image intelligent discrimination method and system based on medical image segmentation is merely illustrative, for example, the division of the modules or units is only a logical functional division, and there may be other division ways in actual implementation, for example, a plurality of units or modules may be combined or may be integrated into another system, or some features may be omitted, or not executed. In another aspect, the communication links shown or discussed with respect to each other may be electrical, mechanical or other forms through some interfaces, device or unit communication links or integrated circuits.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.

It should be noted that the above-mentioned embodiments are only preferred embodiments of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims

1. A traditional Chinese medicine tongue image intelligent treatment method based on medical image segmentation is characterized by comprising the following steps:

acquiring a tongue image of a patient;

extracting tongue body characteristics in the tongue body image, wherein the tongue body characteristics comprise a tongue shape characteristic value, a tongue coating color characteristic value and a tongue quality state characteristic value;

calculating the weight of each constitution type corresponding to the tongue body characteristics by combining a preset tongue diagnosis and differentiation model;

2. The intelligent tongue image diagnosis and treatment method based on medical image segmentation as claimed in claim 1, wherein before obtaining the tongue image of the patient, it further comprises:

and inputting the tongue image knowledge graph into a graph neural network model for training to obtain the tongue diagnosis syndrome differentiation model.

3. The method according to claim 2, wherein said tongue image knowledge graph is inputted into a neural network model for training to obtain said tongue diagnosis differentiation model after said pre-collecting said body constitution types, said zang-fu organs differentiation and said tongue body images of a plurality of patients, further comprising:

4. The method according to claim 1, wherein the extracting tongue features in the tongue image comprises:

5. The method as claimed in claim 1, wherein the method for intelligently differentiating and treating tongue manifestation in traditional Chinese medicine based on medical image segmentation further comprises, after determining the type of constitutions and the syndrome differentiation of the zang-fu organs of the patient according to the weight of each type of constitutions and the weight of each syndrome differentiation of the zang-fu organs, the steps of:

receiving the symptom information of the patient;

and determining the symptom of the patient according to the tongue body characteristics, the symptom information and the symptom corresponding relation knowledge graph.

6. The method of claim 5, wherein after determining the patient's symptoms, the method further comprises:

7. The method as claimed in claim 5, wherein after determining the actual symptom of the patient based on the question and answer result, the method further comprises:

8. A traditional Chinese medicine tongue image intelligent treatment distinguishing system based on medical image segmentation is characterized by comprising:

the acquisition module is used for acquiring a tongue body image of a patient;

the extraction module is connected with the acquisition module and is used for extracting the tongue body characteristics in the tongue body image, wherein the tongue body characteristics comprise a tongue shape characteristic value, a tongue coating color characteristic value and a tongue quality state characteristic value;

9. An intelligent device, comprising a processor, a memory and a computer program stored in the memory and operable on the processor, wherein the processor is configured to execute the computer program stored in the memory to implement the operations performed by the intelligent tongue image identification method based on medical image segmentation according to any one of claims 1 to 7.

10. A storage medium having stored therein at least one instruction, which is loaded and executed by a processor to implement the operations of the method for intelligent tongue image discrimination based on medical image segmentation according to any one of claims 1 to 7.