泛癌筛查的快速聚焦强化学习策略

Glance and Focus Reinforcement for Pan-cancer Screening

January 27, 2026

作者: Linshan Wu, Jiaxin Zhuang, Hao Chen

cs.AI

摘要

大规模CT扫描中的泛癌筛查对现有AI方法仍具挑战，主要难点在于如何从庞大CT体积中定位多样化的微小病灶。极端的前景-背景不平衡严重阻碍模型聚焦病灶区域，而对健康区域的冗余关注不仅降低效率，更会增加假阳性。受放射科医生"扫视-聚焦"诊断策略启发，我们提出GF-Screen框架——一种基于强化学习的泛癌筛查方法。该框架通过扫视模型定位疑似病灶区域，再由聚焦模型进行精确分割，并利用聚焦模型的分割结果通过强化学习奖励扫视模型。具体而言，扫视模型从完整CT体积中截取一组子体积，学习筛选含病灶的子体积供聚焦模型分割。针对选择操作不可微分的问题，我们创新性地采用分割结果作为扫视模型的奖励信号。为优化扫视模型，提出群体相对学习范式，通过组内相对比较优先选择高价值预测、摒弃低价值预测，既提升效率又降低假阳性。此举首次将前沿强化学习技术有效应用于泛癌筛查的特殊挑战。在涵盖9类病灶的16个内部数据集和7个外部数据集上的实验验证了GF-Screen的有效性。值得注意的是，该方法在MICCAI FLARE25泛癌挑战赛公开验证榜位列第一，较FLARE24冠军方案实现显著提升（DSC提升25.6%，NSD提升28.2%）。

English

Pan-cancer screening in large-scale CT scans remains challenging for existing AI methods, primarily due to the difficulty of localizing diverse types of tiny lesions in large CT volumes. The extreme foreground-background imbalance significantly hinders models from focusing on diseased regions, while redundant focus on healthy regions not only decreases the efficiency but also increases false positives. Inspired by radiologists' glance and focus diagnostic strategy, we introduce GF-Screen, a Glance and Focus reinforcement learning framework for pan-cancer screening. GF-Screen employs a Glance model to localize the diseased regions and a Focus model to precisely segment the lesions, where segmentation results of the Focus model are leveraged to reward the Glance model via Reinforcement Learning (RL). Specifically, the Glance model crops a group of sub-volumes from the entire CT volume and learns to select the sub-volumes with lesions for the Focus model to segment. Given that the selecting operation is non-differentiable for segmentation training, we propose to employ the segmentation results to reward the Glance model. To optimize the Glance model, we introduce a novel group relative learning paradigm, which employs group relative comparison to prioritize high-advantage predictions and discard low-advantage predictions within sub-volume groups, not only improving efficiency but also reducing false positives. In this way, for the first time, we effectively extend cutting-edge RL techniques to tackle the specific challenges in pan-cancer screening. Extensive experiments on 16 internal and 7 external datasets across 9 lesion types demonstrated the effectiveness of GF-Screen. Notably, GF-Screen leads the public validation leaderboard of MICCAI FLARE25 pan-cancer challenge, surpassing the FLARE24 champion solution by a large margin (+25.6% DSC and +28.2% NSD).