计算机工程与应用2017，Vol.53Issue(18)：126-131,6.DOI:10.3778/j.issn.1002-8331.1611-0523
基于全卷积神经网络的肝脏CT影像分割研究
Fully convolutional neural network for liver segmentation in CT image
摘要
Abstract
Abdominal CT images cover problems such as low contrast in adjacent organs and various performance in shape. A liver segmentation model based on fully convolutional neural network is proposed. Firstly, the deep and abstract features of the image are extracted by convolutional neural network. Then interpolated reconstruction is performed through deconvolution operation on the extracted feature map to obtain segmentation results. Due to the simple deconvolu-tion acquiring segmentation results are usually rough. Before deconvolution, it applies characteristics mergence to upper and lower layers, increases the deconvolution-layer amount and reduces deconvolution-step size on the model, then gets accurate segmentation results. Compared to convolution neural network, this model can fully use the spatial information of CT images. Experimental results demonstrate, this model can segment abdominal liver region in CT images and reach much higher accuracy.关键词
深度学习/全卷积神经网络/医学图像分割Key words
deep learning/fully convolutional neural network/medical image segmentation分类
信息技术与安全科学引用本文复制引用
郭树旭,马树志,李晶,张惠茅,孙长建,金兰依,刘晓鸣,刘奇楠,李雪妍..基于全卷积神经网络的肝脏CT影像分割研究[J].计算机工程与应用,2017,53(18):126-131,6.基金项目
吉林省自然科学基金(No.20140101175JC). （No.20140101175JC）
