A 3D coarse-to-fine framework for volumetric medical image segmentation

Zhuotun Zhu, Yingda Xia, Wei Shen, Elliot Fishman, Alan Yuille

Research output: Chapter in Book/Report/Conference proceedingConference contribution

39 Scopus citations

Abstract

In this paper, we adopt 3D Convolutional Neural Networks to segment volumetric medical images. Although deep neural networks have been proven to be very effective on many 2D vision tasks, it is still challenging to apply them to 3D tasks due to the limited amount of annotated 3D data and limited computational resources. We propose a novel 3D-based coarse-to-fine framework to effectively and efficiently tackle these challenges. The proposed 3D-based framework outperforms the 2D counterpart to a large margin since it can leverage the rich spatial information along all three axes. We conduct experiments on two datasets which include healthy and pathological pancreases respectively, and achieve the current state-of-the-art in terms of Dice-Sorensen Coefficient (DSC). On the NIH pancreas segmentation dataset, we outperform the previous best by an average of over 2%, and the worst case is improved by 7% to reach almost 70%, which indicates the reliability of our framework in clinical applications.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 International Conference on 3D Vision, 3DV 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages682-690
Number of pages9
ISBN (Electronic)9781538684252
DOIs
StatePublished - Oct 12 2018
Event6th International Conference on 3D Vision, 3DV 2018 - Verona, Italy
Duration: Sep 5 2018Sep 8 2018

Publication series

NameProceedings - 2018 International Conference on 3D Vision, 3DV 2018

Other

Other6th International Conference on 3D Vision, 3DV 2018
Country/TerritoryItaly
CityVerona
Period9/5/189/8/18

Keywords

  • 3D CNNs
  • Pancreas Segmentation

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'A 3D coarse-to-fine framework for volumetric medical image segmentation'. Together they form a unique fingerprint.

Cite this