Self-supervised learning improves robustness of deep learning lung tumor segmentation to CT imaging differences

arXiv:2405.08657v1 Announce Type: cross
Abstract: Self-supervised learning (SSL) is an approach to extract useful feature representations from unlabeled data, and enable fine-tuning on downstream tasks with limited labeled examples. Self-pretraining is a SSL approach that uses the curated task dataset for both pretraining the networks and fine-tuning them. Availability of large, diverse, and uncurated public medical image sets provides the opportunity to apply SSL in the "wild" and potentially extract features robust to imaging variations. However, the benefit of wild- …

abstract arxiv cs.cv data dataset deep learning differences eess.iv examples extract feature fine-tuning imaging networks pretraining robustness segmentation self-supervised learning ssl supervised learning tasks type