Medical image segmentation method based on improved convolutional neural network

Abstract

The invention provides a medical image segmentation method based on an improved convolutional neural network, and belongs to the field of image processing. According to the method, an improved convolutional neural network is constructed, and a multi-channel fusion module, a multi-channel dense connection module, a down-sampling module and an up-sampling module are designed on the basis of an original framework of a standard U-Net network. The depth of the network is increased while the network training calculation amount is controlled, and redundant calculation is reduced. Gradient disappearance is avoided by improving the internal structure of the network while the network is deepened. The experimental result is that the segmentation DICE coefficient of the output prediction graph of thetrained neural network is 98.57%, the DICE coefficient segmented by the original network is 98.26%, and the effectiveness of the method is reflected.

Description

technical field [0001] The invention belongs to the field of image processing, and relates to the U-Net network model based on the convolutional neural network in the field of deep learning and the concept of the "Inception" module in GoogLeNet and the concept of densely connected layers in DenseNet, and specifically relates to the application in medical CT images. Lung contour segmentation and eye vessel segmentation. Background technique [0002] Image segmentation has played a very important role in the field of medical image processing, and has attracted the attention of more and more researchers. Compared with traditional segmentation methods, segmentation algorithms based on deep learning have higher segmentation accuracy and high efficiency, and have been widely used. [0003] Fully convolutional networks have shown better performance than other deep network models in medical image segmentation. Among the various architectures derived from full convolution, the U-Ne...

AI Technical Summary

Problems solved by technology

[0005] In view of the fact that the current U-Net network is not deep enough to better meet the accuracy requirements of medical image segmentation, and at the same time deepening the network may cause problems such as gradient disappearance or redundant calculations, the present invention improves the U-Net network model to avoid In the case of redundant calculation and gradient disappearance, make the network deeper to learn more and more complex image features, and improve the segmentation accuracy of the image

Images