Learning to Detect Brain Lesions from Noisy Annotations

Davood Karimi, Jurriaan M. Peters, Abdelhakim Ouaalam, Sanjay P. Prabhu, Mustafa Sahin, Darcy A. Krueger, Alexander Kolevzon, Charis Eng, Simon K. Warfield, Ali Gholipour

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

6 Scopus citations


Supervised training of deep neural networks in medical imaging applications relies heavily on expert-provided annotations. These annotations, however, are often imperfect, as voxel-by-voxel labeling of structures on 3D images is difficult and laborious. In this paper, we focus on one common type of label imperfection, namely, false negatives. Focusing on brain lesion detection, we propose a method to train a convolutional neural network (CNN) to segment lesions while simultaneously improving the quality of the training labels by identifying false negatives and adding them to the training labels. To identify lesions missed by annotators in the training data, our method makes use of the 1) CNN predictions, 2) prediction uncertainty estimated during training, and 3) prior knowledge about lesion size and features. On a dataset of 165 scans of children with tuberous sclerosis complex from five centers, our method achieved better lesion detection and segmentation accuracy than the baseline CNN trained on the noisy labels, and than several alternative techniques.

Original languageEnglish
Title of host publicationISBI 2020 - 2020 IEEE International Symposium on Biomedical Imaging
PublisherIEEE Computer Society
Number of pages5
ISBN (Electronic)9781538693308
StatePublished - Apr 2020
Event17th IEEE International Symposium on Biomedical Imaging, ISBI 2020 - Iowa City, United States
Duration: 3 Apr 20207 Apr 2020

Publication series

NameProceedings - International Symposium on Biomedical Imaging
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452


Conference17th IEEE International Symposium on Biomedical Imaging, ISBI 2020
Country/TerritoryUnited States
CityIowa City


  • brain lesion detection
  • deep learning
  • imperfect labels
  • noisy labels
  • tuberous sclerosis complex


Dive into the research topics of 'Learning to Detect Brain Lesions from Noisy Annotations'. Together they form a unique fingerprint.

Cite this