# Seeing Beyond the Lesion: Disease Recognition from Reactive CNS Tissue

arXiv: https://arxiv.org/abs/2609.02390 · HTML: https://mlsanity.com/paper/2609.02390/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 18 references that are in the map.
- First posted on arXiv 2 Sep 2026.

## Builds on (most cited first, 6 of 6)

- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology](https://mlsanity.com/paper/2408.00738/) (2024)
- [A Clinical Benchmark of Public Self-Supervised Pathology Foundation Models](https://mlsanity.com/paper/2407.06508/) (2024)
- [Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathology](https://mlsanity.com/paper/2206.01794/) (2022)
- [Benchmarking Embedding Aggregation Methods in Computational Pathology: A Clinical Data Perspective](https://mlsanity.com/paper/2407.07841/) (2024)

## Abstract (arXiv)

Sampling error yields exclusively reactive, non-lesional brain parenchyma in a significant proportion of intracranial biopsies, leaving the underlying disease undiagnosed. We benchmark four pathology foundation models (UNI2-h, Virchow2, Prov-GigaPath, H-optimus-0) as frozen patch encoders within a shared attention-based multiple-instance learning framework using 245 whole-slide images from 186 patients with confirmed downstream diagnoses. We first show that coarse disease-category prediction can be reproduced largely from slide size alone. After restricting classification to three finer diagnostic distinctions within common tissue categories, this confound no longer explains performance, yet disease labels remain predictable above chance under permutation testing (p ≤ 10-4 throughout). Surprisingly, performance is statistically indistinguishable across all foundation-model encoders, suggesting that recovering these weak morphological signatures is not limited by current patch representations. Signed instance-contribution maps and expert review further test whether predictive evidence localizes to reactive parenchyma rather than sampling-induced bias like blood introduced during tissue sampling. These results position acquisition-shortcut auditing via a provenance-only baseline as a necessary control in computational-pathology benchmarks, and show, once that confound is removed, that weakly supervised models still recover disease signal from tissue conventionally regarded as non-diagnostic.