CN114431836A - Artificial intelligence-based benign and malignant onychomycosis line prediction system - Google Patents
Artificial intelligence-based benign and malignant onychomycosis line prediction system Download PDFInfo
- Publication number
- CN114431836A CN114431836A CN202210370765.9A CN202210370765A CN114431836A CN 114431836 A CN114431836 A CN 114431836A CN 202210370765 A CN202210370765 A CN 202210370765A CN 114431836 A CN114431836 A CN 114431836A
- Authority
- CN
- China
- Prior art keywords
- image
- black line
- prediction
- nail
- benign
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000003211 malignant effect Effects 0.000 title claims abstract description 34
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 29
- 208000010195 Onychomycosis Diseases 0.000 title claims description 28
- 201000005882 tinea unguium Diseases 0.000 title claims description 28
- 238000012549 training Methods 0.000 claims abstract description 40
- 238000003745 diagnosis Methods 0.000 claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims abstract description 5
- 206010028980 Neoplasm Diseases 0.000 claims abstract description 4
- 201000011510 cancer Diseases 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 28
- 238000000605 extraction Methods 0.000 claims description 27
- 230000037380 skin damage Effects 0.000 claims description 13
- 238000010276 construction Methods 0.000 claims description 8
- 230000003902 lesion Effects 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 6
- 208000014674 injury Diseases 0.000 claims description 4
- 230000008733 trauma Effects 0.000 claims description 4
- 238000011161 development Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 2
- 230000036210 malignancy Effects 0.000 abstract description 3
- 210000000282 nail Anatomy 0.000 description 30
- 201000001441 melanoma Diseases 0.000 description 14
- 210000002752 melanocyte Anatomy 0.000 description 9
- 206010027145 Melanocytic naevus Diseases 0.000 description 7
- 208000007256 Nevus Diseases 0.000 description 5
- 210000003491 skin Anatomy 0.000 description 5
- 208000009077 Pigmented Nevus Diseases 0.000 description 3
- 230000004913 activation Effects 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 230000035755 proliferation Effects 0.000 description 3
- 208000017520 skin disease Diseases 0.000 description 3
- 206010040882 skin lesion Diseases 0.000 description 3
- 231100000444 skin lesion Toxicity 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- XUMBMVFBXHLACL-UHFFFAOYSA-N Melanin Chemical compound O=C1C(=O)C(C2=CNC3=C(C(C(=O)C4=C32)=O)C)=C2C4=CNC2=C1C XUMBMVFBXHLACL-UHFFFAOYSA-N 0.000 description 2
- 238000001574 biopsy Methods 0.000 description 2
- 206010024217 lentigo Diseases 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 206010048768 Dermatosis Diseases 0.000 description 1
- 206010061218 Inflammation Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000004195 computer-aided diagnosis Methods 0.000 description 1
- 208000035250 cutaneous malignant susceptibility to 1 melanoma Diseases 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 210000004905 finger nail Anatomy 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- VMGAPWLDMVPYIA-HIDZBRGKSA-N n'-amino-n-iminomethanimidamide Chemical compound N\N=C\N=N VMGAPWLDMVPYIA-HIDZBRGKSA-N 0.000 description 1
- 208000026721 nail disease Diseases 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 230000004962 physiological condition Effects 0.000 description 1
- BOLDJAUMGUJJKM-LSDHHAIUSA-N renifolin D Natural products CC(=C)[C@@H]1Cc2c(O)c(O)ccc2[C@H]1CC(=O)c3ccc(O)cc3O BOLDJAUMGUJJKM-LSDHHAIUSA-N 0.000 description 1
- 238000002271 resection Methods 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
- 210000004906 toe nail Anatomy 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/44—Detecting, measuring or recording for evaluating the integumentary system, e.g. skin, hair or nails
- A61B5/449—Nail evaluation, e.g. for nail disorder diagnosis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30096—Tumor; Lesion
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Veterinary Medicine (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Heart & Thoracic Surgery (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Evolutionary Computation (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Dermatology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a nail black line benign and malignant prediction system based on artificial intelligence, which constructs a training set by acquiring nail black line medical images, medical history data and corresponding benign and malignant diagnosis results of a plurality of different nail black line patients; constructing a prediction component based on a multi-mode deep neural network, and training the prediction component by adopting a training set; and acquiring the medical image and medical history data of the nail black line of the target patient, and inputting the medical image and medical history data of the nail black line of the target patient into the prediction component, so as to obtain an accurate prediction result of the nail black line quality and malignancy of the target patient. Compared with the prior art, the prediction component simultaneously takes the clinical picture, the dermatoscope image and the medical history data as input items, provides final decision by unified artificial intelligence with better specialty, and has more scientificity and rationality.
Description
Technical Field
The invention relates to the field of computer-aided diagnosis, in particular to a system for predicting benign and malignant onychomycosis based on artificial intelligence.
Background
The nail is one of the appendages of the skin, and lesions that occur in the nail differ significantly from lesions that occur in the skin, in relation to the specific anatomical and histological characteristics of the nail. The longitudinal black nail is the line of the nail black, and the pathological mechanisms are various, mainly the activation of melanocyte function and the proliferation of melanocyte.
(1) Melanocyte activation: under physiological conditions, melanocytes in the nail matrix region are in a stable state, the melanocytes in the nail matrix are stimulated by trauma, inflammation, infection, physical or chemical factor stimulation, systemic diseases or other partial skin diseases, and the black nails caused by the activation of the melanocytes usually involve a plurality of nails.
(2) Melanocyte proliferation: another is that the proliferation of melanocytes under the nail leads to the formation of melanocyte nest, which causes the accumulation and increase of local melanin to dye the nail plate, namely a female nevus unguiculatus which is the same disease with pigmented nevus in other parts of the body, but the part is different, and is not rare in children and teenagers. Both meibomian and lentigo are benign, but there is still a risk of malignancy of the part to formazan melanoma.
The existing judgment of the benign and malignant onychomycosis (namely the resolution of female onychomycosis, lentigo and melanoma) mainly depends on the visual sense of the naked eyes of a doctor, and the judgment based on the visual sense of the naked eyes has the limitations of strong subjectivity, greater dependence on the experience and professional skills of a clinician, and easy occurrence of false positive and false negative. And empirically derived conclusions cannot be drawn to ensure that the expression of each melanoma is completely consistent with it, which would result in omission if diagnosis was made only according to this method.
Disclosure of Invention
The invention provides a system for predicting the benign and malignant onychomycosis line based on artificial intelligence, which is used for solving the technical problems of strong subjectivity and low accuracy of the existing method for judging the benign and malignant onychomycosis line by visual sense of doctors.
In order to solve the technical problems, the technical scheme provided by the invention is as follows:
an artificial intelligence-based onychomycosis benign and malignant prediction system, comprising:
the collection assembly: the prediction component is used for acquiring the medical image and medical history data of the target patient and inputting the medical image and medical history data of the target patient into the prediction component;
a prediction component: the device is used for comprehensively predicting the good and malignant prediction result of the nail black line of the target patient according to the medical image and the medical history data of the nail black line of the target patient; the prediction component is a multi-mode deep neural network and is obtained by training through a training set; the training set is constructed by the medical image of the onychomycosis of a plurality of different onychomycosis patients, medical history data and corresponding benign and malignant diagnosis results.
Preferably, the prediction component comprises an image feature extraction module, a text feature extraction module and a prediction module;
the image feature extraction module is used for identifying a skin damage area in an input first black line medical image, positioning the boundary of the skin damage area, extracting an image feature matrix of the skin damage area based on the boundary of the skin damage area and inputting the image feature matrix into the prediction module;
the text feature extraction module is used for identifying the A-black line focus information of the input medical history data, extracting a text feature matrix in the A-black line focus information and inputting the text feature matrix into the prediction module;
the prediction module is used for predicting whether the nail black line of the corresponding patient is benign or malignant according to the image feature matrix and the text feature matrix.
Preferably, the method further comprises a training set construction component, wherein the training set construction component comprises:
an image training set construction module: the system comprises an image characteristic extraction module, a boundary detection module and a parameter setting module, wherein the image characteristic extraction module is used for extracting a medical image of a soft nail black line;
a text training set construction module: marking a black line focus keyword sentence in each medical history data to form a text training set of the image feature extraction module;
a marking module: the method is used for constructing the incidence relation among the medical image of the nail black line of the same patient, medical history data and the corresponding benign and malignant diagnosis result.
Preferably, the first black line focus keyword sentence includes: age, time of onset, cause of development, course of change, rate of change, presence or absence of trauma or other treatment.
Preferably, the training system further comprises a training component for: training the image feature extraction module using the image training set; training the text feature extraction module using the text training set; based on the constructed incidence relation, carrying out incidence matching on the image feature matrix output by the image feature extraction module, the text feature matrix output by the text feature extraction module and the corresponding benign and malignant diagnosis result; and then training the prediction module by using the image feature matrix, the text feature matrix and the corresponding benign and malignant diagnosis result of the same patient with successful correlation matching.
Preferably, the nail-black-line medical image comprises a clinical image and a corresponding dermatoscope image.
The invention has the following beneficial effects:
1. the system for predicting benign and malignant onychomycosis based on artificial intelligence constructs a training set by acquiring the onychomycosis medical images, medical history data and corresponding benign and malignant diagnosis results of a plurality of different onychomycosis patients; constructing a prediction component based on a multi-mode deep neural network, and training the prediction component by adopting a training set; and acquiring the medical image and medical history data of the nail black line of the target patient, and inputting the medical image and medical history data of the nail black line of the target patient into the prediction component, so as to obtain an accurate prediction result of the nail black line quality and malignancy of the target patient. Compared with the prior art, the prediction component simultaneously takes the clinical picture, the dermatoscope image and the medical history data as input items, and provides a final decision by a uniform decision maker (artificial intelligence) with better specialty, so that the prediction component is more scientific and reasonable.
In addition to the objects, features and advantages described above, other objects, features and advantages of the present invention are also provided. The present invention will be described in further detail below with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a flow chart of the work flow of the artificial intelligence-based nail black line benign and malignant prediction system in the invention.
Detailed Description
Embodiments of the invention will be described in detail below with reference to the drawings, but the invention can be implemented in many different ways as defined and covered by the claims.
The first embodiment is as follows:
as shown in fig. 1, in the present embodiment, an artificial intelligence-based system for predicting benign and malignant onychomycosis is disclosed, which includes:
the collection assembly: the prediction component is used for acquiring the medical image and medical history data of the target patient and inputting the medical image and medical history data of the target patient into the prediction component;
a prediction component: the device is used for comprehensively predicting the good and malignant prediction result of the nail black line of the target patient according to the medical image and the medical history data of the nail black line of the target patient; the prediction component is a multi-mode deep neural network and is obtained by training through a training set; the training set is constructed by the medical image of the onychomycosis of a plurality of different onychomycosis patients, medical history data and corresponding benign and malignant diagnosis results.
The prediction component in the invention simultaneously takes the clinical picture, the dermatoscope image and the medical history data as input items, and provides a final decision by a uniform decision maker (artificial intelligence) with better specialty, thereby having more scientificity and rationality.
Example two:
the second embodiment is a preferred embodiment of the first embodiment, and is different from the first embodiment in that the construction of the artificial intelligence-based nail black line benign and malignant prediction system is described:
1. establishment of A-Heiselin case database
Collect first female nevus and first melanoma clinical image and corresponding dermatoscope image, medical history information 1 ten thousand sets that show as first black line respectively and regard as the training set for the machine carries out the degree of depth study to the image characteristic of first female nevus and first melanoma, carries out the label to every picture, marks out the skin damage region, supplies the machine to carry out the feature extraction. Wherein if one dermoscope cannot photograph the entire fingernail or toenail damaged area, all consecutively photographed dermoscope images are pieced together.
2. Artificial intelligence model building
A model suitable for identifying the characteristics of the item of nevus onychomycosis and melanoma onychomycosis is selected from the existing models and used for characteristic analysis, firstly skin lesion images are accurately extracted from training set clinical images and skin mirror images, boundaries of the skin lesion images are located, items (namely, onychomycosis lesion key words and sentences) which are meaningful for lesion classification are extracted from medical history information and input into an artificial intelligence system, and the artificial intelligence system is led to obtain the capability of classifying and predicting unknown onychomycosis lesions through machine learning. Wherein items that make sense to the classification of lesions include: age, time of onset, cause of development, course of change, rate of change, presence or absence of trauma or other treatment.
Wherein, the artificial intelligence system is a prediction component, and comprises: the system comprises an image feature extraction module, a text feature extraction module and a prediction module;
the image feature extraction module is used for identifying a skin damage area in an input first black line medical image, positioning the boundary of the skin damage area, extracting an image feature matrix of the skin damage area based on the boundary of the skin damage area and inputting the image feature matrix into the prediction module;
the text feature extraction module is used for identifying the A-black line focus information of the input medical history data, extracting a text feature matrix in the A-black line focus information and inputting the text feature matrix into the prediction module;
the prediction module is used for predicting whether the nail black line of the corresponding patient is benign or malignant according to the image feature matrix and the text feature matrix.
3. Model validation
After the model is trained by the training set, a batch of a female onychomycosis clinical image and a melanoma clinical image which are not identified and learned by a machine are arranged as a verification set, clinical application is simulated, a patient and a system interact, and the system gives a classification prediction result to be compared with an actual diagnosis result. The evaluation indexes are as follows: the skin lesion image of a diagnosed melanoma alphapatient can be evaluated as high-risk melanomas, and the focus of clinical diagnosis melanoma alphanevus which is confirmed by biopsy and evaluated by doctors without biopsy is evaluated as low-risk melanomas.
The artificial intelligence system can be used after being successfully verified, namely, the collection component is used for collecting the medical image and medical history data of the nail black line of the target patient, and the medical image and medical history data of the nail black line of the target patient are input into the prediction component to obtain the prediction result of the nail black line benign and malignant of the target patient.
4. Effects or features of the invention
1) Although there are a number of models for classifying and predicting benign pigmented nevi and malignant melanoma based on artificial intelligence, the majority of cases involve classified diagnosis of onychomycosis in all skin diseases, and are not listed. The disease of the nail has obvious difference with the pigmented nevus and melanoma on the skin due to the unique anatomical characteristics of the nail, and the accuracy of the nail disease prediction by using a conventional classification dermatosis model is probably obviously reduced.
2) The classification accuracy of the model for a mother's nevus and a melanoma may be higher than that of a clinician, and the artificial intelligence technique is obviously a good news of patients who are uncertain in nature and need to be diagnosed by a total nail resection. Can avoid unnecessary operation damage and improve the life quality of patients.
3) The existing ABCDEF diagnosis criteria and the identification of the dermatoscope have certain limitations, and generally doctors who are accurate in judging clinical images and doctors who are accurate in judging the dermatoscope images are not the same group of people (generally doctors who are specialized in seeing the dermatoscope), so that the identification of the clinical images and the identification of the dermatoscope images cannot be well made up for the deficiencies in clinical practice. The artificial intelligence system takes the clinical picture, the skin mirror image and the medical history data as input items, and a uniform decision maker (artificial intelligence) with better specialty provides a final decision, so that the artificial intelligence system is more scientific and reasonable.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. An artificial intelligence-based onychomycosis benign and malignant prediction system, comprising:
the collection assembly: the prediction component is used for acquiring the medical image and medical history data of the target patient and inputting the medical image and medical history data of the target patient into the prediction component;
a prediction component: the device is used for comprehensively predicting the good and malignant prediction result of the nail black line of the target patient according to the medical image and the medical history data of the nail black line of the target patient; the prediction component is a multi-mode deep neural network and is obtained by training through a training set; the training set is constructed by the medical image of the onychomycosis of a plurality of different onychomycosis patients, medical history data and corresponding benign and malignant diagnosis results.
2. The artificial intelligence based onychomycosis benign and malignant prediction system of claim 1, wherein the prediction component comprises an image feature extraction module, a text feature extraction module, and a prediction module;
the image feature extraction module is used for identifying a skin damage area in an input first black line medical image, positioning the boundary of the skin damage area, extracting an image feature matrix of the skin damage area based on the boundary of the skin damage area and inputting the image feature matrix into the prediction module;
the text feature extraction module is used for identifying the A-black line focus information of the input medical history data, extracting a text feature matrix in the A-black line focus information and inputting the text feature matrix into the prediction module;
the prediction module is used for predicting whether the nail black line of the corresponding patient is benign or malignant according to the image feature matrix and the text feature matrix.
3. The artificial intelligence based onychomycosis benign and malignant prediction system of claim 2, further comprising a training set construction component comprising:
an image training set construction module: the system comprises an image characteristic extraction module, a boundary detection module and a parameter setting module, wherein the image characteristic extraction module is used for extracting a medical image of a soft nail black line;
a text training set construction module: marking a black line focus keyword sentence in each medical history data to form a text training set of the image feature extraction module;
a marking module: the method is used for constructing the incidence relation among the medical image of the nail black line of the same patient, medical history data and the corresponding benign and malignant diagnosis result.
4. The artificial intelligence based alpha-scholar line benign-malignancy prediction system according to claim 3, wherein said alpha-scholar line lesion keyword sentences comprise: age, time of onset, cause of development, course of change, rate of change, presence or absence of trauma or other treatment.
5. The artificial intelligence based onychomycosis benign and malignant prediction system of claim 4, further comprising a training component to: training the image feature extraction module using the image training set; training the text feature extraction module using the text training set; based on the constructed incidence relation, carrying out incidence matching on the image feature matrix output by the image feature extraction module, the text feature matrix output by the text feature extraction module and the corresponding benign and malignant diagnosis result; and then training the prediction module by using the image feature matrix, the text feature matrix and the corresponding benign and malignant diagnosis result of the same patient with successful correlation matching.
6. The artificial intelligence based nail black line benign-malignant prediction system of claim 1, wherein the nail black line medical image comprises a clinical image and a corresponding dermoscopic image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210370765.9A CN114431836A (en) | 2022-04-11 | 2022-04-11 | Artificial intelligence-based benign and malignant onychomycosis line prediction system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210370765.9A CN114431836A (en) | 2022-04-11 | 2022-04-11 | Artificial intelligence-based benign and malignant onychomycosis line prediction system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114431836A true CN114431836A (en) | 2022-05-06 |
Family
ID=81360338
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210370765.9A Pending CN114431836A (en) | 2022-04-11 | 2022-04-11 | Artificial intelligence-based benign and malignant onychomycosis line prediction system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114431836A (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107909566A (en) * | 2017-10-28 | 2018-04-13 | 杭州电子科技大学 | A kind of image-recognizing method of the cutaneum carcinoma melanoma based on deep learning |
| CN109003679A (en) * | 2018-06-28 | 2018-12-14 | 众安信息技术服务有限公司 | A kind of cerebrovascular hemorrhage and ischemic prediction technique and device |
| CN109166105A (en) * | 2018-08-01 | 2019-01-08 | 中国人民解放军南京军区南京总医院 | The malignancy of tumor risk stratification assistant diagnosis system of artificial intelligence medical image |
| CN110322962A (en) * | 2019-07-03 | 2019-10-11 | 重庆邮电大学 | A kind of method automatically generating diagnostic result, system and computer equipment |
| CN110755045A (en) * | 2019-10-30 | 2020-02-07 | 湖南财政经济学院 | Skin disease comprehensive data analysis and diagnosis auxiliary system and information processing method |
| CN111612752A (en) * | 2020-05-15 | 2020-09-01 | 江苏省人民医院（南京医科大学第一附属医院） | Ultrasonic image thyroid nodule intelligent detection system based on fast-RCNN |
| US20200311939A1 (en) * | 2017-05-25 | 2020-10-01 | Waseda University | Method for analyzing longitudinal pigmented band on nail plate or skin color hue for diagnosing skin disease, and diagnostic device and computer program therefor |
| CN112786129A (en) * | 2020-03-19 | 2021-05-11 | 中国医学科学院北京协和医院 | Case data analysis method and device, electronic device and storage medium |
| CN112801168A (en) * | 2021-01-25 | 2021-05-14 | 江苏大学 | Tumor image focal region prediction analysis method and system and terminal equipment |
| CN112991320A (en) * | 2021-04-07 | 2021-06-18 | 德州市人民医院 | System and method for predicting hematoma expansion risk of cerebral hemorrhage patient |
| CN113012138A (en) * | 2021-03-26 | 2021-06-22 | 华南理工大学 | Method and system for analyzing nail black line skin mirror image |
| CN113077894A (en) * | 2021-04-26 | 2021-07-06 | 中南大学湘雅三医院 | System, method, apparatus and medium for skin diagnosis based on graph convolution neural network |
| US20210209754A1 (en) * | 2020-01-02 | 2021-07-08 | Nabin K. Mishra | Fusion of deep learning and handcrafted techniques in dermoscopy image analysis |
| CN114219755A (en) * | 2021-11-02 | 2022-03-22 | 佛山市第四人民医院(佛山市结核病防治所) | Intelligent pulmonary tuberculosis detection method and system based on images and clinical data |
| CN114242196A (en) * | 2021-12-13 | 2022-03-25 | 中南大学湘雅医院 | Automatic generation method and device for clinical medical record |
-
2022
- 2022-04-11 CN CN202210370765.9A patent/CN114431836A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200311939A1 (en) * | 2017-05-25 | 2020-10-01 | Waseda University | Method for analyzing longitudinal pigmented band on nail plate or skin color hue for diagnosing skin disease, and diagnostic device and computer program therefor |
| CN107909566A (en) * | 2017-10-28 | 2018-04-13 | 杭州电子科技大学 | A kind of image-recognizing method of the cutaneum carcinoma melanoma based on deep learning |
| CN109003679A (en) * | 2018-06-28 | 2018-12-14 | 众安信息技术服务有限公司 | A kind of cerebrovascular hemorrhage and ischemic prediction technique and device |
| CN109166105A (en) * | 2018-08-01 | 2019-01-08 | 中国人民解放军南京军区南京总医院 | The malignancy of tumor risk stratification assistant diagnosis system of artificial intelligence medical image |
| CN110322962A (en) * | 2019-07-03 | 2019-10-11 | 重庆邮电大学 | A kind of method automatically generating diagnostic result, system and computer equipment |
| CN110755045A (en) * | 2019-10-30 | 2020-02-07 | 湖南财政经济学院 | Skin disease comprehensive data analysis and diagnosis auxiliary system and information processing method |
| US20210209754A1 (en) * | 2020-01-02 | 2021-07-08 | Nabin K. Mishra | Fusion of deep learning and handcrafted techniques in dermoscopy image analysis |
| CN112786129A (en) * | 2020-03-19 | 2021-05-11 | 中国医学科学院北京协和医院 | Case data analysis method and device, electronic device and storage medium |
| CN111612752A (en) * | 2020-05-15 | 2020-09-01 | 江苏省人民医院（南京医科大学第一附属医院） | Ultrasonic image thyroid nodule intelligent detection system based on fast-RCNN |
| CN112801168A (en) * | 2021-01-25 | 2021-05-14 | 江苏大学 | Tumor image focal region prediction analysis method and system and terminal equipment |
| CN113012138A (en) * | 2021-03-26 | 2021-06-22 | 华南理工大学 | Method and system for analyzing nail black line skin mirror image |
| CN112991320A (en) * | 2021-04-07 | 2021-06-18 | 德州市人民医院 | System and method for predicting hematoma expansion risk of cerebral hemorrhage patient |
| CN113077894A (en) * | 2021-04-26 | 2021-07-06 | 中南大学湘雅三医院 | System, method, apparatus and medium for skin diagnosis based on graph convolution neural network |
| CN114219755A (en) * | 2021-11-02 | 2022-03-22 | 佛山市第四人民医院(佛山市结核病防治所) | Intelligent pulmonary tuberculosis detection method and system based on images and clinical data |
| CN114242196A (en) * | 2021-12-13 | 2022-03-25 | 中南大学湘雅医院 | Automatic generation method and device for clinical medical record |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Salido et al. | Using deep learning to detect melanoma in dermoscopy images | |
| CN109492711B (en) | Malignant melanoma and non-malignant melanoma classification system based on deep learning | |
| CN110472629B (en) | Pathological image automatic identification system based on deep learning and training method thereof | |
| Mandache et al. | Basal cell carcinoma detection in full field OCT images using convolutional neural networks | |
| CN114299068A (en) | Intelligent decision-making system for evaluating psoriasis severity degree based on skin image | |
| Guru et al. | Brain tumor identification and classification using a novel extraction method based on adapted alexnet architecture | |
| Kia et al. | Computer-aided diagnosis (CAD) of the skin disease based on an intelligent classification of sonogram using neural network | |
| Trokielewicz et al. | Perception of image features in post-mortem iris recognition: Humans vs machines | |
| Caroprese et al. | Features for melanoma lesions: Extraction and classification | |
| Ortiz-Rodriguez et al. | Breast cancer detection by means of artificial neural networks | |
| CN113627483A (en) | Cervical OCT image classification method and device based on self-supervision texture contrast learning | |
| CN116230198A (en) | Multidimensional Tibetan medicine AI intelligent auxiliary decision-making device and system | |
| Sujaini et al. | Comparing the performance of linear regression versus deep learning on detecting melanoma skin cancer using apple core ML | |
| Noronha et al. | Deep Learning-based Dermatological Condition Detection: A Systematic Review with Recent Methods, Datasets, Challenges and Future Directions | |
| CN114431836A (en) | Artificial intelligence-based benign and malignant onychomycosis line prediction system | |
| Nivedita et al. | DBN with a Developed Version of Thermal Exchange Optimization (TEO) Model for Skin Cancer Detection and Classification | |
| Aktürk et al. | Classification of eye images by personal details with transfer learning algorithms | |
| Masood | Developing improved algorithms for detection and analysis of skin cancer | |
| Nagaraj et al. | Skin Cancer Detection and Control Techniques Using Hybrid Deep Learning Techniques | |
| Millenia et al. | Melanoma Detection using Convolutional Neural Network with Transfer Learning on Dermoscopic and Macroscopic Images | |
| CN115526888A (en) | Eye pattern data identification method and device, storage medium and electronic equipment | |
| Raut et al. | Skin Lesion Detection Using MobileNet CNN | |
| Al Shabibi et al. | Detection of Skin Diseases Using Matlab | |
| Kuan et al. | A comparative study of segmentation algorithms in the classification of human skin burn depth | |
| Praveen et al. | Analysis of Algorithms for Effective Skin Cancer Detection Model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |