# Jigsaw Regularization in Whole-Slide Image Classification

Source: [Jigsaw Regularization in Whole-Slide Image Classification](<https://www.sota2.com/research/paper/69c21a8c0636e5bf4afc485e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-25T05:00:04.214Z

Authors: So Won Jeong, Veronika Ro\\v{c}kov\\'a

Published: 2026-03-20T18:04:25.000Z

## Abstract

Computational pathology involves the digitization of stained tissues into whole-slide images (WSIs) that contain billions of pixels arranged as contiguous patches. Statistical analysis of WSIs largely focuses on classification via multiple instance learning (MIL), in which slide-level labels are inferred from unlabeled patches. Most MIL methods treat patches as exchangeable, overlooking the rich spatial and topological structure that underlies tissue images. This work builds on recent graph-based methods that aim to incorporate spatial awareness into MIL. Our approach is new in two regards: (1) we deploy vision \\emph{foundation-model embeddings} to incorporate local spatial structure within each patch, and (2) achieve across-patch spatial awareness using graph neural networks together with a novel {\\em jigsaw regularization}. We find that a combination of these two features markedly improves classification over state-of-the-art attention-based MIL approaches on benchmark datasets in breast, head-and-neck, and colon cancer.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Whole Slide Image Classification on TCGA BRCA (3-fold cross-validation)](<https://www.sota2.com/research/sota/whole-slide-image-classification-on-tcga-brca-3-fold-cross-validation.md>): Whole Slide Image classification; TCGA BRCA (3-fold cross-validated); ROC-AUC: 95.2.

- [Whole-Slide Image Classification on TCGA HNSC (3-fold cross-validated)](<https://www.sota2.com/research/sota/whole-slide-image-classification-on-tcga-hnsc-3-fold-cross-validated.md>): Whole Slide Image classification; TCGA HNSC (3-fold cross-validated); ROC-AUC: 83.3.

- [Whole-Slide Image Classification on TCGA COAD (3-fold cross-validated)](<https://www.sota2.com/research/sota/whole-slide-image-classification-on-tcga-coad-3-fold-cross-validated.md>): Whole Slide Image classification; TCGA COAD (3-fold cross-validated); ROC AUC: 88.5.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.20386>)

[PDF](<https://arxiv.org/pdf/2603.20386.pdf>)