{"paper":{"title":"retinalysis-vascx: An explainable software toolbox for the extraction of retinal vascular biomarkers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"VascX is an open-source Python toolbox that extracts reproducible retinal vascular biomarkers by building graphs from artery-vein segmentations.","cross_cats":["cs.CV"],"primary_cat":"q-bio.TO","authors_text":"Bart Liefers, Caroline C.W. Klave, EyeNED Reading Center, Jose D. Vargas Quiros, Michael J. Beyeler, Sofia Ortin Vela, Sven Bergmann, VascX Research Consortium","submitted_at":"2026-02-09T12:19:33Z","abstract_excerpt":"Automatic extraction of retinal vascular biomarkers from color fundus images (CFI) is crucial for large-scale studies of the retinal vasculature. We present VascX, an open-source Python toolbox that extracts biomarkers from CFI artery-vein segmentations. VascX starts from vessel segmentation masks, extracts their skeletons, builds undirected and directed vessel graphs, and resolves vessel segments into longer vessels. A comprehensive set of biomarkers is derived, including vascular density, central retinal equivalents (CREs), and tortuosity. Spatially localized biomarkers may be calculated ove"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"VascX provides an explainable and easily modifiable feature-extraction toolbox that complements segmentation to produce reliable retinal vascular biomarkers. Our graph-based biomarker computation stages support reproducible, region-aware measurements suited for large-scale clinical and epidemiological research.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The input artery-vein segmentation masks are accurate enough for downstream graph construction, and the heuristic rules for resolving vessel segments and computing biomarkers remain robust across different imaging devices, image qualities, and parameter choices.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"VascX is an open-source toolbox that computes retinal vascular biomarkers including vascular density, central retinal equivalents, and tortuosity from artery-vein segmentations, with moderate to excellent test-retest reproducibility on multi-device repeat imaging.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"VascX is an open-source Python toolbox that extracts reproducible retinal vascular biomarkers by building graphs from artery-vein segmentations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"db385cad6776f987cde393ff9a824d350edd12587bf9a87479d896032250a330"},"source":{"id":"2602.08580","kind":"arxiv","version":3},"verdict":{"id":"fd4bf1f7-e76c-4b46-a713-5c49b6e51eda","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T03:52:39.853978Z","strongest_claim":"VascX provides an explainable and easily modifiable feature-extraction toolbox that complements segmentation to produce reliable retinal vascular biomarkers. Our graph-based biomarker computation stages support reproducible, region-aware measurements suited for large-scale clinical and epidemiological research.","one_line_summary":"VascX is an open-source toolbox that computes retinal vascular biomarkers including vascular density, central retinal equivalents, and tortuosity from artery-vein segmentations, with moderate to excellent test-retest reproducibility on multi-device repeat imaging.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The input artery-vein segmentation masks are accurate enough for downstream graph construction, and the heuristic rules for resolving vessel segments and computing biomarkers remain robust across different imaging devices, image qualities, and parameter choices.","pith_extraction_headline":"VascX is an open-source Python toolbox that extracts reproducible retinal vascular biomarkers by building graphs from artery-vein segmentations."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.08580/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}