arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2607.02569cs.CVcs.LG

数据集偏移下用于可参考糖尿病视网膜病变筛查的RETFound不确定性感知最后一层自适应

Uncertainty-Aware Last-Layer Adaptation of RETFound for Referable Diabetic Retinopathy Screening Under Dataset Shift

University of Colorado Boulder（科罗拉多大学博尔德分校）

Karim Mardhani

备注：
12 pages, 8 tables, 6 figures. Code available at https://github.com/kmardhani/uncertainty-aware-retfound
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

用RETFound对糖尿病视网膜病变筛查的不确定性感知最后一层自适应进行以安全为中心的实证评估，比较多种方法，在APTOS上不确定性感知操作点改善了敏感性等，在DDR上结果有差异，强调安全评估的价值。

摘要：

本文提出了一种以安全为中心的实证评估，用于使用RETFound进行可参考糖尿病视网膜病变筛查的不确定性感知最后一层自适应，RETFound是一种自监督视觉Transformer视网膜基础模型，用作冻结特征编码器，并使用公共APTOS 2019和DDR糖尿病视网膜病变眼底图像数据集。我们比较了缓存特征softmax头、事后温度缩放、变分贝叶斯最后一层头、对角拉普拉斯最后一层近似和SNGP风格的缓存特征头。在APTOS上，不确定性感知操作点提高了敏感性和选择性转诊行为。最强的APTOS选择性转诊结果推迟了大约20%的病例，并将接受病例的假阴性降低到零，同时保持高接受病例特异性。然而，阈值调整也以高假阳性成本降低了假阴性，因此仅假阴性降低并非贝叶斯建模所独有。在DDR上，原生贝叶斯头定性地再现了APTOS方向，但权衡较弱，而在APTOS上训练的SNGP检查点转移不佳，未能提供有用的外部选择性转诊行为。这些结果突出了以安全为中心的评估超越总体准确性的价值：不确定性感知最后一层头可以改善内部以安全为导向的操作点，但可靠的视网膜筛查声明需要在偏移下进行明确的安全覆盖评估和第二数据集验证。

英文摘要：

This paper presents a safety-centered empirical evaluation of uncertainty-aware last-layer adaptation for referable diabetic retinopathy screening using RETFound, a self-supervised vision-transformer retinal foundation model used here as a frozen feature encoder, and the public APTOS 2019 and DDR diabetic retinopathy fundus image datasets. We compare a cached-feature softmax head, post-hoc temperature scaling, variational Bayesian last-layer heads, a diagonal Laplace last-layer approximation, and an SNGP-style cached-feature head. On APTOS, uncertainty-aware operating points improved sensitivity and selective-referral behavior. The strongest APTOS selective-referral result deferred approximately 20 percent of cases and reduced accepted-case false negatives to zero while preserving high accepted-case specificity. However, threshold tuning also reduced false negatives at high false-positive cost, so false-negative reduction alone was not unique to Bayesian modeling. On DDR, native Bayesian heads qualitatively reproduced the APTOS direction but with weaker tradeoffs, while the APTOS-trained SNGP checkpoint transferred poorly and failed to provide useful external selective-referral behavior. These results highlight the value of safety-centered evaluation beyond aggregate accuracy: uncertainty-aware last-layer heads can improve internal safety-oriented operating points, but trustworthy retinal screening claims require explicit safety-coverage evaluation and second-dataset validation under shift.

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。

↑