Training a neural network based on unreliable human annotation of medical images

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

Abstract

Building classification models from clinical data often requires human experts for example labeling. However, it is difficult to obtain a perfect set of labels due to the complexity of the medical data and the large variability between experts. In this study we present a neural-network training strategy that is more robust to unreliable labeling by explicitly modeling the label noise as part of the network architecture. Our method is demonstrated on breast microcalcifications classification into benign and malignant categories, given multi-view mammograms. We show that the proposed training procedure outperforms standard training methods that ignore the existence of label noise.

Original languageEnglish
Title of host publication2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018
PublisherIEEE Computer Society
Pages39-42
Number of pages4
ISBN (Electronic)9781538636367
DOIs
StatePublished - 23 May 2018
Event15th IEEE International Symposium on Biomedical Imaging, ISBI 2018 - Washington, United States
Duration: 4 Apr 20187 Apr 2018

Publication series

NameProceedings - International Symposium on Biomedical Imaging
Volume2018-April

Conference

Conference15th IEEE International Symposium on Biomedical Imaging, ISBI 2018
Country/TerritoryUnited States
CityWashington
Period4/04/187/04/18

Keywords

  • Deep-learning
  • Mammography
  • Microcalcifications
  • Noisy-labels
  • Robust training

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'Training a neural network based on unreliable human annotation of medical images'. Together they form a unique fingerprint.

Cite this