Exploring the Effects of Contrastive Learning on Homogeneous Medical Image Data

  • We investigate contrastive learning in a multi-task learning setting classifying and segmenting early Barrett’s cancer. How can contrastive learning be applied in a domain with few classes and low inter-class and inter-sample variance, potentially enabling image retrieval or image attribution? We introduce a data sampling strategy that mines per-lesion data for positive samples and keeps a queue of the recent projections as negative samples. We propose a masking strategy for the NT-Xent loss that keeps the negative set pure and removes samples from the same lesion. We show cohesion and uniqueness improvements of the proposed method in feature space. The introduction of the auxiliary objective does not affect the performance but adds the ability to indicate similarity between lesions. Therefore, the approach could enable downstream auto-documentation tasks on homogeneous medical image data.

Export metadata

Additional Services

Share in Twitter Search Google Scholar Statistics
Metadaten
Author:Robert MendelORCiD, David Rauber, Christoph PalmORCiDGND
DOI:https://doi.org/10.1007/978-3-658-41657-7
Parent Title (German):Bildverarbeitung für die Medizin 2023: Proceedings, German Workshop on Medical Image Computing, July 2– 4, 2023, Braunschweig
Publisher:Springer Vieweg
Place of publication:Wiesbaden
Document Type:conference proceeding (article)
Language:English
Year of first Publication:2023
Release Date:2023/06/19
First Page:128
Last Page:13
Institutes:Fakultät Informatik und Mathematik
Regensburg Center of Biomedical Engineering - RCBE
Fakultät Informatik und Mathematik / Regensburg Medical Image Computing (ReMIC)
Begutachtungsstatus:peer-reviewed
research focus:Lebenswissenschaften und Ethik
Licence (German):Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG