Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Malignant melanoma and non-malignant melanin nevus classification method based on deep learning

A kind of malignant melanoma, deep learning technology, applied in the field of eye tissue pathological sections classified as malignant and non-malignant, can solve problems such as insufficient medical resources, and achieve the effect of high accuracy

Active Publication Date: 2019-03-19
HANGZHOU DIANZI UNIV
View PDF7 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to address the serious shortage of medical resources at present, and propose a classification method for ocular malignant melanoma and melanoma based on deep learning, which combines deep learning with histopathological image classification to improve the diagnosis of malignant melanoma. Accuracy and efficiency, reducing the burden on doctors

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Malignant melanoma and non-malignant melanin nevus classification method based on deep learning
  • Malignant melanoma and non-malignant melanin nevus classification method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0031] The hardware environment used for implementation is: CPU Intel(R) Xeon(R) CPU E5-2630 v4@ 2.20GHz, GPU is NVIDIA K80, and the operating environment is python2.7 and TensorFlow.

[0032] Using a 16-layer deep convolutional neural network and a random forest classifier in series, the network has 5 sections of convolution, each section has 2 to 3 convolutional layers, and the last layer of each section is the largest pooling layer to reduce the size of the image size. The number of convolution kernels in each segment is the same, and the number of convolution kernels in the later segment is more: 64-128-256-512-512. Two concatenated 3×3 convolutions are equivalent to a 5×5 convolution, and 3 concatenated are equivalent to a 7×7 convolution. At the same time, the small convolution kernel structure in series has fewer parameters than the si...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a malignant melanoma and non-malignant melanin nevus classification method based on deep learning. The method comprises the following steps: firstly, acquiring data; performingdata preprocessing, then, enhancing the processed data; then, performing the malignant and non-malignant tumor classification at a small sliding block level, generating probabilistic thermodynamic diagrams, machine learning feature extraction, and finally, performing random forest classification based on pathological image levels. According to the invention, a very good experiment result of the small slide block level of the pathological image of the eye superpixel tissue is obtained; more importantly, a whole set of process of automatically classifying tissue pathological images as malignantor non-malignant is realized, a computer aided diagnosis (CAD) system which can be directly applied to clinical aided diagnosis is constructed, and the accuracy is very high.

Description

technical field [0001] The invention relates to the field of artificial intelligence, and relates to a deep learning-based method for classifying ocular tissue pathological slices into malignant and non-malignant. Background technique [0002] Melanoma is a common benign tumor of the eye, which is a skin manifestation caused by the increase of melanocytes in the epidermis and dermis. The disease progresses slowly, mostly without symptoms. Individual types of moles have the possibility of turning into malignant, which is life-threatening. [0003] Malignant melanoma is a malignant tumor produced by melanocytes in the skin and other organs. Susceptibility to metastasis is caused by inherited genetic variation and environmental risks. The most important exogenous pathogenic factor is exposure to ultraviolet radiation. Malignant melanoma mostly occurs in the skin, accounting for about 1% of systemic malignant tumors, and can also be found in the mucous membranes of the diges...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/62G06K9/34G06N3/04G06N3/00G06N3/08
CPCG06N3/006G06N3/08G06V10/267G06V2201/03G06N3/045G06F18/241
Inventor 丁隆乾郑先斐孙玲玲
Owner HANGZHOU DIANZI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com