arXiv · cs.AI · Nheng Vanchhay, Ali Hussain, Khan Ziaullah, Moon-Il Joo, Md Ariful Islam Mozumder, Rashedul Islam Sumon, Won-Ae Lee, Min-Sun Cho, Hyeong-Chan Shin, Yujun Park, Baek Hwan Cho, Nam-Hoon Cho, Heejung An, Heung-Kook Choi, Haeyoun Kang, Hyunki Kim, Hee Cheol Kim · 11 小时前模型评分38
研究：基于基础模型特征时，更复杂的聚合器未能提升胃癌全切片图像跨医院判别力
With foundation-model features, aggregator complexity does not improve cross-hospital discrimination in gastric whole-slide image classification
导读
一项研究用五家韩国医院的 5,036 张胃癌全切片图像，在留一医院验证下比较多种多实例学习聚合器。带站点对齐和双尺度融合的 CHIME-MIL 平均 AUC 为 0.837，但在匹配配方下未超过注意力池化，全局最大池化反而更高（AUC 0.855）。对齐方法仅用十张无标签切片即可接入新医院，代价是 0.002 AUC，但精度提升小且不稳定。
分类置信度
中 · 待人工复核
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
应用领域：医疗与生命科学
事件类型：研究发布
证据摘录
- “We assembled 5,036 haematoxylin-and-eosin-stained gastric slides from five Korean hospitals, scanned at 20x and 40x, and compared multiple-instance learning aggregators under leave-one-hospital-out validation on frozen pathology foundation-model features.”
- “The alignment, which subtracts each hospital's mean feature vector without labels, onboarded a new hospital from ten unlabelled slides and cost 0.002 AUC without held-out-hospital data, but its accuracy gains were small and inconsistent.”
来源：arXiv · cs.AI · arxiv.org