Tasting the cake: evaluating self-supervised generalization on out-of-distribution multimodal MRI data [article]

Alex Fedorov, Eloy Geenjaar, Lei Wu, Thomas P. DeRamus, Vince D. Calhoun, Sergey M. Plis
<span title="2022-05-23">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Self-supervised learning has enabled significant improvements on natural image benchmarks. However, there is less work in the medical imaging domain in this area. The optimal models have not yet been determined among the various options. Moreover, little work has evaluated the current applicability limits of novel self-supervised methods. In this paper, we evaluate a range of current contrastive self-supervised methods on out-of-distribution generalization in order to evaluate their
more &raquo; ... y to medical imaging. We show that self-supervised models are not as robust as expected based on their results in natural imaging benchmarks and can be outperformed by supervised learning with dropout. We also show that this behavior can be countered with extensive augmentation. Our results highlight the need for out-of-distribution generalization standards and benchmarks to adopt the self-supervised methods in the medical imaging community.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.15914v3">arXiv:2103.15914v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rre34oatsjhcjmpk2xw7ftjcua">fatcat:rre34oatsjhcjmpk2xw7ftjcua</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220525113032/https://arxiv.org/pdf/2103.15914v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a5/4f/a54f01496aa8316b138a7080ade3f95b2c34f5e9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.15914v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>