Learning from Human Uncertainty by Choquet Integral for Optic Disc Segmentation

Hao Qiu, Pan Su, Shanshan Jiang, Xingyu Yue, Yitian Zhao, Jiang Liu

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

Modern deep neural networks are able to beat human annotators in several medical image processing tasks. In practical manual annotation for medical image segmentation tasks, the labels of annotators often show inter-observer variability (IOV) which is mainly caused by annotators' different understandings of expertise. In order to build a trustworthy segmentation system, robust models should consider how to capture uncertainty in samples and labels. Different from the conventional way of handling IOV with label fusion such as majority voting, a fuzzy integral based ensemble framework of multiple deep learning models for optic disc segmentation is proposed. Each component segmentation model is trained with respect to an annotator. Then, a powerful nonlinear aggregation function, the Choquet integral, is employed in form of a neural network to integrate the segmentation results of multiple annotators. The proposed method is validated on the public RIM-ONE dataset consisting of 169 fundus images and each image is annotated by 5 experts. Compared with conventional segmentation ensemble methods, the proposed methods achieves a higher Dice score (98.69%).

Original languageEnglish
Title of host publicationICCCV 2021 - Proceedings of the 4th International Conference on Control and Computer Vision
PublisherAssociation for Computing Machinery
Pages7-12
Number of pages6
ISBN (Electronic)9781450390477
DOIs
Publication statusPublished - 13 Aug 2021
Externally publishedYes
Event4th International Conference on Control and Computer Vision, ICCCV 2021 - Virtual, Online, China
Duration: 13 Aug 202115 Aug 2021

Publication series

NameACM International Conference Proceeding Series

Conference

Conference4th International Conference on Control and Computer Vision, ICCCV 2021
Country/TerritoryChina
CityVirtual, Online
Period13/08/2115/08/21

Keywords

  • ensemble learning
  • human uncertainty
  • multiple annotations
  • optical disc

ASJC Scopus subject areas

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

Fingerprint

Dive into the research topics of 'Learning from Human Uncertainty by Choquet Integral for Optic Disc Segmentation'. Together they form a unique fingerprint.

Cite this