Skin cancer image recognition method based on attention convolutional neural network

Abstract

The invention discloses a skin cancer image recognition method based on an attention convolutional neural network, and the method comprises the steps: 1) carrying out the preprocessing of an image, which comprises the steps of image overturning, rotation, and affine transformation; 2) performing unbalanced sampling on the image, and performing undersampling on the image; 3) establishing a convolutional neural network framework which comprises a convolutional layer, a pooling layer and a full connection layer; 4) establishing an attention mechanism which comprises a channel attention module anda space attention module; and 5) designing an attention convolutional neural network to identify the skin cancer picture, wherein the network added with the attention module can be positioned in a local area more accurately, and images are mined with distinctive characteristics; and 6) performing transfer learning, and initializing parameters of the convolutional neural network by using the parameters of the pre-training network. Through the method of the invention, the accuracy of skin cancer image recognition can be effectively improved, and the development of artificial intelligence in themedical industry is promoted to a certain extent.

Description

technical field [0001] The invention relates to the technical field of image pattern recognition and medical images, in particular to a skin cancer picture recognition method based on attentional convolutional neural network. Background technique [0002] Skin cancer is the most common cancer among all cancers. Skin cancer is usually caused by ultraviolet rays in the sun. Now the death rate of skin cancer is increasing worldwide, and malignant melanoma is the most deadly. There are 71 cases in every 100,000 people, and if detected and treated in time, the success rate of melanoma cure is as high as 98%. In the detection of skin cancer, it is often done using a dermoscopy, a non-invasive skin imaging technique that magnifies an illuminated picture of an area of ​​skin to increase the clarity of spots in the skin by removing reflections from the skin surface , can increase the visual effect of deep skin, and thus can provide more details of skin damage. This approach removes...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art, and propose a skin cancer picture recognition method based on attentional convolutional neural network, which can effectively solve the problem of inaccurate feature extraction area and low image recognition rate in the existing method question

Images