{"paper":{"title":"Backbone-Conditional Behavior of Modality Gating in Multi-Modal Prostate MRI Segmentation: A 5-Fold Cross-Validation and Gate Mechanism Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Modality-isolated gated fusion with dropout training makes multi-modal prostate MRI segmentation more robust to missing or degraded diffusion sequences.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aijing Luo, Kewen Chen, Luo Lei, Shanhu Yao, Wenzhao Xie, Yongbo Shu, Zirui Xin","submitted_at":"2026-04-12T15:54:21Z","abstract_excerpt":"Robust segmentation of clinically significant prostate cancer (csPCa) on multi-parametric MRI must tolerate frequent degradation of its most informative diffusion sequences. Multi-modal fusion commonly employs learned modality gating under the assumption that gates implement per-sample modality quality routing -- rarely tested directly. We ask how gating behaves across backbone architectures. We systematically analyze modality-isolated gated fusion (MIGF) for csPCa segmentation on two backbones (nnU-Net and Mamba) using PI-CAI (n=1500), with cross-cohort validation on Prostate158 (n=158): a fa"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MIGF improved ideal-scenario Ranking Score for UNet, nnUNet, and Mamba by 2.8%, 4.6%, and 13.4%; the best model (MIGFNet-nnUNet) achieved 0.7304 +/- 0.056. Robustness gains arise from strict modality isolation and dropout-driven compensation rather than adaptive per-sample quality routing.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the observed gains are caused by modality isolation plus dropout rather than other unablated factors such as backbone-specific tuning or the particular choice of seven missing-modality scenarios; the claim that the gate converged to a stable modality prior is presented without showing it generalizes beyond the tested folds and seeds.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MIGF improves multi-modal prostate MRI segmentation robustness via modality-isolated streams and dropout training, yielding ranking score gains of 2.8-13.4% across backbones and better tolerance to degraded diffusion sequences on PI-CAI and Prostate158.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Modality-isolated gated fusion with dropout training makes multi-modal prostate MRI segmentation more robust to missing or degraded diffusion sequences.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"67c7e5213e126645ab0e8ee26ea07312286f8466a80f5b979332d419be3c57e6"},"source":{"id":"2604.10702","kind":"arxiv","version":4},"verdict":{"id":"518eebc2-1d3b-49d0-869f-f3c3e6c50943","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T15:54:13.803368Z","strongest_claim":"MIGF improved ideal-scenario Ranking Score for UNet, nnUNet, and Mamba by 2.8%, 4.6%, and 13.4%; the best model (MIGFNet-nnUNet) achieved 0.7304 +/- 0.056. Robustness gains arise from strict modality isolation and dropout-driven compensation rather than adaptive per-sample quality routing.","one_line_summary":"MIGF improves multi-modal prostate MRI segmentation robustness via modality-isolated streams and dropout training, yielding ranking score gains of 2.8-13.4% across backbones and better tolerance to degraded diffusion sequences on PI-CAI and Prostate158.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the observed gains are caused by modality isolation plus dropout rather than other unablated factors such as backbone-specific tuning or the particular choice of seven missing-modality scenarios; the claim that the gate converged to a stable modality prior is presented without showing it generalizes beyond the tested folds and seeds.","pith_extraction_headline":"Modality-isolated gated fusion with dropout training makes multi-modal prostate MRI segmentation more robust to missing or degraded diffusion sequences."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.10702/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"}