ProsMAE: Multi-Source MAE Pretraining for ISUP Grade Classification
For computational pathology, this work addresses the challenge of limited labeled data and domain variability by leveraging diverse pretraining sources, though the improvement is incremental and requires further validation.
The paper proposes ProsMAE, a multi-source Masked Autoencoder pretraining framework for histopathology, and shows it achieves higher mean validation QWK than vanilla MAE for ISUP grade classification on a disjoint PANDA split.
Whole slide images (WSIs) provide rich diagnostic information for computational pathology, but their gigapixel scale, stain variation, scanner differences, tissue artifacts, and limited expert annotation make robust model training challenging. This paper presents a multi-source Masked Autoencoder (MAE) framework, named ProsMAE, for histopathology representation learning. Tiles from Prostate cANcer graDe Assessment (PANDA), CAncer MEtastases in LYmph nOdes challeNge 2017 (CAMELYON17), and BReAst Carcinoma Subtyping (BRACS) are used for ProsMAE pretraining to expose the encoder to diverse tissue morphology and acquisition conditions. The learned encoder is transferred for International Society of Urological Pathology (ISUP) grade classification through ProsCLS, using a frozen encoder and a linear classification head. ProsMAE achieved a higher mean validation quadratic weighted kappa (QWK) than the vanilla MAE frozen linear-probe baseline under the evaluated disjoint PANDA split. Repeated-split evaluation remains necessary to further establish robustness across split compositions.