4.7 Article

Inter-Slice Context Residual Learning for 3D Medical Image Segmentation

期刊

IEEE TRANSACTIONS ON MEDICAL IMAGING
卷 40, 期 2, 页码 661-672

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2020.3034995

关键词

Image segmentation; Three-dimensional displays; Decoding; Biomedical imaging; Tumors; Task analysis; Solid modeling; 3D context perceiving; inter-slice context residual; 3D medical image segmentation

资金

  1. National Natural Science Foundation of China [61771397]
  2. Science and Technology Innovation Committee of Shenzhen Municipality, China [JCYJ20180306171334997]
  3. Innovation Foundation for Doctoral Dissertation of Northwestern Polytechnical University [CX202010]

向作者/读者索取更多资源

In this paper, we propose the 3D context residual network (ConResNet) for accurate segmentation of 3D medical images, which incorporates context residual modules and context attention mapping to improve segmentation accuracy. Experimental results show that the proposed model outperforms other methods in brain tumor and pancreas segmentation tasks. The network architecture is well-designed and demonstrates high reliability.
Automated and accurate 3D medical image segmentation plays an essential role in assisting medical professionals to evaluate disease progresses and make fast therapeutic schedules. Although deep convolutional neural networks (DCNNs) have widely applied to this task, the accuracy of these models still need to be further improved mainly due to their limited ability to 3D context perception. In this paper, we propose the 3D context residual network (ConResNet) for the accurate segmentation of 3D medical images. This model consists of an encoder, a segmentation decoder, and a context residual decoder. We design the context residual module and use it to bridge both decoders at each scale. Each context residual module contains both context residual mapping and context attention mapping, the formal aims to explicitly learn the inter-slice context information and the latter uses such context as a kind of attention to boost the segmentation accuracy. We evaluated this model on the MICCAI 2018 Brain Tumor Segmentation (BraTS) dataset and NIH Pancreas Segmentation (Pancreas-CT) dataset. Our results not only demonstrate the effectiveness of the proposed 3D context residual learning scheme but also indicate that the proposed ConResNet is more accurate than six top-ranking methods in brain tumor segmentation and seven top-ranking methods in pancreas segmentation.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据