CT Male Pelvic Organ Segmentation via Hybrid Loss Network with Incomplete Annotation

Shuai Wang, Dong Nie, Liangqiong Qu, Yeqin Shao, Jun Lian, Qian Wang, Dinggang Shen

Research output: Contribution to journalArticlepeer-review

12 Citations (Scopus)

Abstract

Sufficient data with complete annotation is essential for training deep models to perform automatic and accurate segmentation of CT male pelvic organs, especially when such data is with great challenges such as low contrast and large shape variation. However, manual annotation is expensive in terms of both finance and human effort, which usually results in insufficient completely annotated data in real applications. To this end, we propose a novel deep framework to segment male pelvic organs in CT images with incomplete annotation delineated in a very user-friendly manner. Specifically, we design a hybrid loss network derived from both voxel classification and boundary regression, to jointly improve the organ segmentation performance in an iterative way. Moreover, we introduce a label completion strategy to complete the labels of the rich unannotated voxels and then embed them into the training data to enhance the model capability. To reduce the computation complexity and improve segmentation performance, we locate the pelvic region based on salient bone structures to focus on the candidate segmentation organs. Experimental results on a large planning CT pelvic organ dataset show that our proposed method with incomplete annotation achieves comparable segmentation performance to the state-of-the-art methods with complete annotation. Moreover, our proposed method requires much less effort of manual contouring from medical professionals such that an institutional specific model can be more easily established.

Original languageEnglish
Article number8957549
Pages (from-to)2151-2162
Number of pages12
JournalIEEE Transactions on Medical Imaging
Volume39
Issue number6
DOIs
Publication statusPublished - 2020 Jun

Keywords

  • CT
  • Image segmentation
  • deep learning
  • incomplete annotation
  • male pelvic organ

ASJC Scopus subject areas

  • Software
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'CT Male Pelvic Organ Segmentation via Hybrid Loss Network with Incomplete Annotation'. Together they form a unique fingerprint.

Cite this