Quantitative Evaluation of MILs' Reliability For WSIs Classification

Reliable models are dependable and provide predictions acceptable given basic domain knowledge. Therefore, it is critical to develop and deploy reliable models, especially for healthcare applications. However, Multiple Instance Learning (MIL) models designed for Whole Slide Images (WSIs) classification in computational pathology are not evaluated in terms of reliability. Hence, in this paper we compare the reliability of MIL models with three suggested metrics and use three region-wise annotated datasets. We find the mean pooling instance (MEAN-POOL-INS) model more reliable than other networks despite its naive architecture design and computation efficiency. The code to reproduce the results is accessible at https://github.com/tueimage/MILs'R .