Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MacNet: An End-to-End Manifold-Constrained Adaptive Clustering Network for Interpretable Whole Slide Image Classification

About

Whole slide images (WSIs) are the gold standard for pathological diagnosis and sub-typing. Current main-stream two-step frameworks employ offline feature encoders trained without domain-specific knowledge. Among them, attention-based multiple instance learning (MIL) methods are outcome-oriented and offer limited interpretability. Clustering-based approaches can provide explainable decision-making process but suffer from high dimension features and semantically ambiguous centroids. To this end, we propose an end-to-end MIL framework that integrates Grassmann re-embedding and manifold adaptive clustering, where the manifold geometric structure facilitates robust clustering results. Furthermore, we design a prior knowledge guiding proxy instance labeling and aggregation strategy to approximate patch labels and focus on pathologically relevant tumor regions. Experiments on multicentre WSI datasets demonstrate that: 1) our cluster-incorporated model achieves superior performance in both grading accuracy and interpretability; 2) end-to-end learning refines better feature representations and it requires acceptable computation resources.

Mingrui Ma, Chentao Li, Pan Huang, Jing Qin• 2026

Related benchmarks

TaskDatasetResultRank
Cancer diagnosisCAMELYON-16
Accuracy91.43
42
Cancer sub-typingAMU-CSCC
ACC92.45
40
Cancer sub-typingDHMC-LUNG
Accuracy0.8222
40
Cancer sub-typingAMU-LSCC
ACC90.58
40
Showing 4 of 4 rows

Other info

Follow for update