Cracking Instance Jigsaw Puzzles: An Alternative to Multiple Instance Learning for Whole Slide Image Analysis
This work addresses a key bottleneck in histopathological image analysis for medical diagnosis, offering a more effective alternative to existing methods, though it is incremental in improving upon MIL approaches.
The authors tackled the limitation of permutation invariance in multiple instance learning for whole slide image analysis by proposing a novel method that learns to restore the order of shuffled instances, termed cracking instance jigsaw puzzles, and demonstrated that it outperforms state-of-the-art MIL competitors on classification and survival prediction tasks.
While multiple instance learning (MIL) has shown to be a promising approach for histopathological whole slide image (WSI) analysis, its reliance on permutation invariance significantly limits its capacity to effectively uncover semantic correlations between instances within WSIs. Based on our empirical and theoretical investigations, we argue that approaches that are not permutation-invariant but better capture spatial correlations between instances can offer more effective solutions. In light of these findings, we propose a novel alternative to existing MIL for WSI analysis by learning to restore the order of instances from their randomly shuffled arrangement. We term this task as cracking an instance jigsaw puzzle problem, where semantic correlations between instances are uncovered. To tackle the instance jigsaw puzzles, we propose a novel Siamese network solution, which is theoretically justified by optimal transport theory. We validate the proposed method on WSI classification and survival prediction tasks, where the proposed method outperforms the recent state-of-the-art MIL competitors. The code is available at https://github.com/xiwenc1/MIL-JigsawPuzzles.