{"id":32384,"date":"2026-01-21T17:01:51","date_gmt":"2026-01-21T17:01:51","guid":{"rendered":"https:\/\/lamarr-institute.org\/publication\/weakly-supervised-segmentation-of-hyper-reflective-foci-with-compact-convolutional-transformers-and-sam-2\/"},"modified":"2026-09-17T11:23:56","modified_gmt":"2026-09-17T11:23:56","slug":"weakly-supervised-segmentation-of-hyper-reflective-foci-with-compact-convolutional-transformers-and-sam-2","status":"publish","type":"publication","link":"https:\/\/lamarr-institute.org\/de\/publication\/weakly-supervised-segmentation-of-hyper-reflective-foci-with-compact-convolutional-transformers-and-sam-2\/","title":{"rendered":"Weakly Supervised Segmentation of Hyper-Reflective Foci with Compact Convolutional Transformers and {SAM} 2"},"content":{"rendered":"<p>Weakly supervised segmentation has the potential to greatly reduce the annotation effort for training segmentation models for small structures such as hyper-reflective foci (HRF) in optical coherence tomography (OCT). However, most weakly supervised methods either involve a strong downsampling of input images, or only achieve localization at a coarse resolution, both of which are unsatisfactory for small structures. We propose a novel framework that increases the spatial resolution of a traditional attention-based Multiple Instance Learning (MIL) approach by using Layer-wise Relevance Propagation (LRP) to prompt the Segment Anything Model (SAM 2), and increases recall with iterative inference. Moreover, we demonstrate that replacing MIL with a Compact Convolutional Transformer (CCT), which adds a positional encoding, and permits an exchange of information between different regions of the OCT image, leads to a further and substantial increase in segmentation accuracy.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Weakly supervised segmentation has the potential to greatly reduce the annotation effort for training segmentation models for small structures such as hyper-reflective foci (HRF) in optical coherence tomography (OCT). However, most weakly supervised methods either involve a strong downsampling of input images, or only achieve localization at a coarse resolution, both of which are unsatisfactory for small structures. We propose a novel framework that increases the spatial resolution of a [&hellip;]<\/p>\n","protected":false},"author":14,"featured_media":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"publication-type":[32],"class_list":["post-32384","publication","type-publication","status-publish","hentry","publication-type-inproceedings"],"acf":[],"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/32384","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/types\/publication"}],"author":[{"embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/users\/14"}],"version-history":[{"count":0,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/32384\/revisions"}],"wp:attachment":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/media?parent=32384"}],"wp:term":[{"taxonomy":"publication-type","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-type?post=32384"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}