Journal
MEDICAL IMAGE ANALYSIS
Volume 68, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.media.2020.101912
Keywords
Weakly supervised learning; Digital histopathology; Whole slide images; Image segmentation
Categories
Funding
- Canadian Cancer Society [705772]
- NSERC [RGPIN-2016-06283]
Ask authors/readers for more resources
This study proposes an architecture that reduces the time spent on data curation and eases the requirements for segmentation level ground truth by utilizing image-level labels. It also helps unlock the potential of previously acquired image-level datasets for segmentation tasks.
Two of the most common tasks in medical imaging are classification and segmentation. Either task requires labeled data annotated by experts, which is scarce and expensive to collect. Annotating data for segmentation is generally considered to be more laborious as the annotator has to draw around the boundaries of regions of interest, as opposed to assigning image patches a class label. Furthermore, in tasks such as breast cancer histopathology, any realistic clinical application often includes working with whole slide images, whereas most publicly available training data are in the form of image patches, which are given a class label. We propose an architecture that can alleviate the requirements for segmentation level ground truth by making use of image-level labels to reduce the amount of time spent on data curation. In addition, this architecture can help unlock the potential of previously acquired image-level datasets on segmentation tasks by annotating a small number of regions of interest. In our experiments, we show using only one segmentation-level annotation per class, we can achieve performance comparable to a fully annotated dataset. (c) 2020 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available