MPD$^2$-Router:基于掩码的多专家优先正则化双头延迟路由在青光眼筛查与诊断中的应用
MPD$^2$-Router: Mask-aware Multi-expert Prior-regularized Dual-head Deferral Router in Glaucoma Screening and Diagnosis
AI总结:
本文提出MPD$^2$-Router,通过结合双头延迟/分配策略和掩码感知的Gumbel-sigmoid门控,解决青光眼筛查中专家资源分配问题,提升诊断准确率并降低临床成本。
摘要:
本文提出MPD$^2$-Router,通过结合双头延迟/分配策略和掩码感知的Gumbel-sigmoid门控,解决青光眼筛查中专家资源分配问题,提升诊断准确率并降低临床成本。
英文摘要:
Learning-to-defer (L2D) can make glaucoma screening safer by routing difficult/uncertain cases to humans, yet standard formulations overlook expert availability, heterogeneous readers behavior, workload imbalance, asymmetric diagnostic harm, case difficulty from morphology and deployment shift. We introduce MPD$^2$-Router, a mask-aware multi-expert deferral framework that recasts ophthalmic triage as constrained human--AI routing: whether to defer and to which available expert. It couples a dual-head deferral/allocation policy with mask-aware Gumbel--sigmoid gating that strictly enforces per-sample availability, and fuses uncertainty, morphology, image-quality, and OOD signals. Training uses an asymmetric cost-sensitive objective with an augmented-Lagrangian deferral budget, a group-specific distribution prior, and a rank-majorization JS regularizer that jointly prevent expert collapse without forcing uniform allocation. Across three cross-national glaucoma cohorts (REFUGE, CHAKSU, ORIGA) with a frozen REFUGE-trained backbone, MPD$^2$-Router substantially lowers clinical cost and improves MCC over AI-only at a moderate deferral rate. It is Pareto-optimal in F1--MCC--cost, robust under cross-domain shift, and yields balanced expert utilization.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。