Regularized UNet for automated pancreas segmentation

Fan Jia, Xue-Cheng Tai

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

3 Citations (Scopus)


Leading other traditional methods by a large margin, convolutional neural networks (CNNs) become the first choice for dense classification problems such as semantic segmentation. However, when given few training images, CNNs often could not deal with details well. Coarse edges and isolated points often appear in the segmentation results provided by CNNs. Since medical datasets usually contain dozens to hundreds training samples, the segmentation results need further refinement. In this paper, we implement regularized UNet (RUNet) with multi-step primal-dual block which is an end-to-end framework to regularize the segmentation results. The proposed framework could produce smooth edges and eliminate isolated points. Comparing to other post-processing methods, our method needs little extra computation thus is effective and efficient.

Original languageEnglish
Title of host publicationISICDM 2019 - Conference Proceedings
Subtitle of host publication3rd International Symposium on Image Computing and Digital Medicine
PublisherAssociation for Computing Machinery (ACM)
Number of pages5
ISBN (Electronic)9781450372626
Publication statusPublished - 24 Aug 2019
Event3rd International Symposium on Image Computing and Digital Medicine, ISICDM 2019 - Xi'an, China
Duration: 24 Aug 201926 Aug 2019

Publication series

NameACM International Conference Proceeding Series


Conference3rd International Symposium on Image Computing and Digital Medicine, ISICDM 2019

Scopus Subject Areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

User-Defined Keywords

  • Image segmentation
  • Pancreas segmentation
  • Regularized UNet


Dive into the research topics of 'Regularized UNet for automated pancreas segmentation'. Together they form a unique fingerprint.

Cite this