.png){kind=icon}
返回
E2-MIL: An explainable and evidential multiple instance learning framework for whole slide image classification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.media.2024.103294.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Multiple instance learning (MIL)-based methods have been widely adopted to process the whole slide image (WSI) in the field of computational pathology. Due to the sparse slide-level supervision, these methods usually lack good localization on the tumor regions, leading to poor interpretability. Moreover, they lack robust uncertainty estimation of prediction results, leading to poor reliability. To solve the above two limitations, we propose an explainable and evidential multiple instance learning (E2 2-MIL) framework for whole slide image classification. E2 2-MIL is mainly composed of three modules: a detail-aware attention distillation module (DAM), a structure-aware attention refined module (SRM), and an uncertainty-aware instance classifier (UIC). Specifically, DAM helps the global network locate more detail-aware positive instances by utilizing the complementary sub-bags to learn detailed attention knowledge from the local network. In addition, a masked self-guidance loss is also introduced to help bridge the gap between the slide-level labels and instance-level classification tasks. SRM generates a structure-aware attention map that locates the entire tumor region structure by effectively modeling the spatial relations between clustering instances. Moreover, UIC provides accurate instance-level classification results and robust predictive uncertainty estimation to improve the model reliability based on subjective logic theory. Extensive experiments on three large multi-center subtyping datasets demonstrate both slide-level and instance-level performance superiority of E2 2-MIL.
Keyword:
Histopathology
Whole slide image analysis
Multiple instance learning
Uncertainty estimation
期刊
IF:
11.8
论文数:
3.9K
被引数:
2.4W
机构
引用论文
Uncertainty-informed deep learning models enable high-confidence predictions for digital histopathology基于不确定性的深度学习模型可实现数字组织病理学的高置信度预测.png)
NATURE COMMUNICATIONS
OAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏Whole Slide Image Quality in Digital Pathology: Review and Perspectives数字病理学中的全载玻片图像质量: 回顾和展望IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏Data-efficient and weakly supervised computational pathology on whole-slide images全载玻片图像上的数据高效和弱监督计算病理学OAAI
OAAI分享收藏AdvMIL: Adversarial multiple instance learning for the survival analysis on whole-slide imagesAdvMIL: 用于全幻灯片图像生存分析的对抗性多实例学习MEDICAL IMAGE ANALYSISOAAI
MEDICAL IMAGE ANALYSISIF11.8
OAAI分享收藏分享收藏
查看更多内容