Improved image segmentation training method based on full convolutional neural network

Abstract

The invention provides an improved image segmentation training method based on a full convolutional neural network in allusion to the current situation that the difficulty in melanoma skin lesion segmentation is high and a simple effective rapid image segmentation method is absent. The method comprises the following steps: firstly executing data enhancement to a training sample, executing normalization processing, executing sampling segmentation to the processed sample, and classifying images after the sampling segmentation so as to realize classification and identification training based on the traditional convolutional neural network; and assigning parameters of the classification network to an improved full convolutional network, placing the training sample with the original size in thenetwork, and training to obtain a prediction probability graph to provide segmentation for a skin melanoma lesion picture. The method is capable of effectively improving the supervision of the full convolutional network upon image segmentation training, improving the training efficiency, and increasing segmentation accuracy.

Description

technical field [0001] The invention relates to an improved image segmentation training method based on a fully convolutional neural network, which belongs to the field of medical image processing, and relates to the feature extraction of a fully convolutional neural network (FCN) and a convolutional neural network (CNN). An Improved Image Segmentation Training Method for Neural Networks. Background technique [0002] Melanoma is a highly malignant tumor that can produce melanin, also known as malignant melanoma, which is more common in adults over 30 years old. It is a common skin tumor caused by excessive hyperplasia of abnormal melanocytes. It mostly occurs in the skin or mucous membranes close to the skin, and is also found in pia mater and choroid. Not only that, data show that melanoma is one of the malignant tumors with the fastest growing incidence in recent years, with an annual growth rate of 3%-5%. Another main feature of melanoma is that its late cure rate is e...

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention is to overcome the existing problems of feature extraction for skin image segmentation, such as insufficient feature extraction, strong feature subjectivity, large amount of calculation, poor segmentation efficiency, etc., and provide an improved method based on fully convolutional neural network. The image segmentation training method realizes the automatic segmentation of melanoma images. This method can automatically learn the multi-scale features in the image, and splicing and fusing the features on multiple scales to segment the image. It has the characteristics of rich feature extraction and high segmentation efficiency.

Images