Prostate cancer is one of the most prevalent malignancies among men worldwide, and its diagnosis relies heavily on accurate analysis of whole slide imaging (WSI) in histopathology. However, manual interpretation is time-consuming and prone to inconsistent accuracy. Existing multiple instance learning (MIL)-based studies can assist diagnosis but still suffer from high computational cost, insufficient exploitation of inter-instance relationships, and neglect of tissue heterogeneity. To address these challenges, this paper proposes a feature distillation multiple instance learning method based on sequence reorganization mamba (FDMIL). The proposed approach leveraged the long-sequence modeling capability of SR-Mamba to capture effective inter-instance dependencies and heterogeneity. Meanwhile, a feature distillation mechanism was introduced to remove redundant representations and reduce computational overhead. Additionally, an auxiliary loss function was designed to mitigate pseudo-bag noise interference. We evaluated FDMIL on the Peking Union Medical College Hospital (PUMCH) prostate cancer WSI dataset and the public Camelyon16 dataset. Experimental results demonstrated that FDMIL achieved significant performance improvements on both datasets, reaching an AUC of 93.9%, ACC of 90.1%, and F1-score of 87.3%, outperforming existing state-of-the-art methods. These results verify the effectiveness and clinical applicability of FDMIL in both institutional and public scenarios.
