{"paper":{"title":"Polygon-mamba: Retinal vessel segmentation using polygon scanning mamba and space-frequency collaborative attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Polygon scanning mamba maintains connectivity of small retinal vessels during segmentation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Juan Zhou, Wen Li, Xiong Li, Yuanyuan Peng","submitted_at":"2026-05-11T13:53:51Z","abstract_excerpt":"Retinal vessel segmentation is crucial for diagnosis and assessment of ocular diseases. Notably, segmentation of small retinal vessels has been consistently recognized as a challenging and complex task. To tackle this challenge, we design a hybrid CNN-Mamba fusion network that integrates polygon scanning mamba and space-frequency collaborative attention mechanism for the detection of small vessels. Considering that the traditional mamba architecture with horizontal-vertical scanning may compromise the topological integrity of target structures and result in local discontinuities in small retin"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We design a hybrid CNN-Mamba fusion network that integrates polygon scanning mamba and space-frequency collaborative attention mechanism for the detection of small vessels... our model demonstrated F1 scores of 0.8283, 0.8282, and 0.8251... on DRIVE, STARE, and CHASE_DB1.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the polygon scanning in PS-VSS and the space-frequency attention in SFCAM will generalize beyond the three tested datasets and actually preserve connectivity for small vessels without introducing new artifacts or requiring extensive hyperparameter tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Polygon-Mamba achieves F1 scores of 0.8283, 0.8282, and 0.8251 on DRIVE, STARE, and CHASE_DB1 by combining polygon scanning Mamba with space-frequency collaborative attention to better detect small retinal vessels.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Polygon scanning mamba maintains connectivity of small retinal vessels during segmentation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a0bc1f052926454d440794a7cc6f4c90aaafa7cc2d69cad11586b394f138575b"},"source":{"id":"2605.10581","kind":"arxiv","version":2},"verdict":{"id":"03f4ffa4-442c-49b8-a35c-5879b8a27642","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T03:48:07.501306Z","strongest_claim":"We design a hybrid CNN-Mamba fusion network that integrates polygon scanning mamba and space-frequency collaborative attention mechanism for the detection of small vessels... our model demonstrated F1 scores of 0.8283, 0.8282, and 0.8251... on DRIVE, STARE, and CHASE_DB1.","one_line_summary":"Polygon-Mamba achieves F1 scores of 0.8283, 0.8282, and 0.8251 on DRIVE, STARE, and CHASE_DB1 by combining polygon scanning Mamba with space-frequency collaborative attention to better detect small retinal vessels.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the polygon scanning in PS-VSS and the space-frequency attention in SFCAM will generalize beyond the three tested datasets and actually preserve connectivity for small vessels without introducing new artifacts or requiring extensive hyperparameter tuning.","pith_extraction_headline":"Polygon scanning mamba maintains connectivity of small retinal vessels during segmentation."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.10581/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T05:42:00.870691Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T14:41:01.041555Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T11:01:17.640403Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T09:10:05.535094Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"14c91030e269aece4ff339cbd9e21d8e9495ef0889a85f9783f32e24c7aeb476"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"fe5c8cc52033bfb134b438183c025db4c39019f72ed447bbf2bea6c2fdd6b1ca"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}