High-Resolution Encoder-Decoder Networks for Low-Contrast Medical Image Segmentation

Sihang Zhou, Dong Nie, Ehsan Adeli, Jianping Yin, Jun Lian, Dinggang Shen

Research output: Contribution to journalArticlepeer-review

140 Citations (Scopus)


Automatic image segmentation is an essential step for many medical image analysis applications, include computer-aided radiation therapy, disease diagnosis, and treatment effect evaluation. One of the major challenges for this task is the blurry nature of medical images (e.g., CT, MR, and microscopic images), which can often result in low-contrast and vanishing boundaries. With the recent advances in convolutional neural networks, vast improvements have been made for image segmentation, mainly based on the skip-connection-linked encoder-decoder deep architectures. However, in many applications (with adjacent targets in blurry images), these models often fail to accurately locate complex boundaries and properly segment tiny isolated parts. In this paper, we aim to provide a method for blurry medical image segmentation and argue that skip connections are not enough to help accurately locate indistinct boundaries. Accordingly, we propose a novel high-resolution multi-scale encoder-decoder network (HMEDN), in which multi-scale dense connections are introduced for the encoder-decoder structure to finely exploit comprehensive semantic information. Besides skip connections, extra deeply supervised high-resolution pathways (comprised of densely connected dilated convolutions) are integrated to collect high-resolution semantic information for accurate boundary localization. These pathways are paired with a difficulty-guided cross-entropy loss function and a contour regression task to enhance the quality of boundary detection. The extensive experiments on a pelvic CT image dataset, a multi-modal brain tumor dataset, and a cell segmentation dataset show the effectiveness of our method for 2D/3D semantic segmentation and 2D instance segmentation, respectively. Our experimental results also show that besides increasing the network complexity, raising the resolution of semantic feature maps can largely affect the overall model performance. For different tasks, finding a balance between these two factors can further improve the performance of the corresponding network.

Original languageEnglish
Article number8741187
Pages (from-to)461-475
Number of pages15
JournalIEEE Transactions on Image Processing
Publication statusPublished - 2020

Bibliographical note

Funding Information:
Manuscript received October 27, 2018; revised May 2, 2019; accepted May 24, 2019. Date of publication June 19, 2019; date of current version September 23, 2019. The work of S. Zhou and J. Yin was supported in part by the National Key R&D Program of China under Grant 2018YFB1003203 and in part by the National Science Foundation of China under Grant 61672528. The work of E. Adeli was supported in part by the NIH under Grant AA026762. The work of J. Lian and D. Shen was supported in part by NIH under Grant CA206100. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Denis Kouame. (Corresponding authors: Jianping Yin; Dinggang Shen.) S. Zhou is with the School of Computer, National University of Defense Technology, Changsha 410073, China, also with the Department of Radiology, University of North Carolina, Chapel Hill, NC 27599 USA, and also with the Biomedical Research Imaging Center (BRIC), University of North Carolina, Chapel Hill, NC 27599 USA.

Publisher Copyright:
© 1992-2012 IEEE.


  • Image segmentation
  • high-resolution pathway
  • low-contrast image

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'High-Resolution Encoder-Decoder Networks for Low-Contrast Medical Image Segmentation'. Together they form a unique fingerprint.

Cite this