# Explainable histomorphology-based survival prediction of glioblastoma, IDH-wildtype

arXiv: https://arxiv.org/abs/2601.11691 · HTML: https://mlsanity.com/paper/2601.11691/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 55 references that are in the map.
- First posted on arXiv 16 Jan 2026.

## Builds on (most cited first, 13 of 13)

- [Scaling and evaluating sparse autoencoders](https://mlsanity.com/paper/2406.04093/) (2024)
- [TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2106.00908/) (2021)
- [Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualization](https://mlsanity.com/paper/2012.04456/) (2020)
- [Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology](https://mlsanity.com/paper/2408.00738/) (2024)
- [A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models](https://mlsanity.com/paper/2503.05613/) (2025)
- [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)
- [Multiple Instance Learning for Digital Pathology: A Review on the State-of-the-Art, Limitations & Future Potential](https://mlsanity.com/paper/2206.04425/) (2022)
- [Benchmarking foundation models as feature extractors for weakly-supervised computational pathology](https://mlsanity.com/paper/2408.15823/) (2024)
- [Do Multiple Instance Learning Models Transfer?](https://mlsanity.com/paper/2506.09022/) (2025)
- [Learning biologically relevant features in a pathology foundation model using sparse autoencoders](https://mlsanity.com/paper/2407.10785/) (2024)
- [Recommendations on test datasets for evaluating AI solutions in pathology](https://mlsanity.com/paper/2204.14226/) (2022)
- [Slideflow: Deep Learning for Digital Histopathology with Real-Time Whole-Slide Visualization](https://mlsanity.com/paper/2304.04142/) (2023)

## Abstract (arXiv)

Glioblastoma, IDH-wildtype (GBM-IDHwt) is the most common malignant brain tumor. While histomorphology is a crucial component of GBM-IDHwt diagnosis, it is not further considered for prognosis. Here, we present an explainable artificial intelligence (AI) framework to identify and interpret histomorphological features associated with patient survival. The framework combines an explainable multiple instance learning (MIL) architecture that directly identifies prognostically relevant image tiles with a sparse autoencoder (SAE) that maps these tiles to interpretable visual patterns. The MIL model was trained and evaluated on a new real-world dataset of 720 GBM-IDHwt cases from three hospitals and four cancer registries across Germany. The SAE was trained on 1,878 whole-slide images from five independent public glioblastoma collections. Despite the many factors influencing survival time, our method showed some ability to discriminate between patients living less than 180 days or more than 360 days solely based on histomorphology (AUC: 0.67; 95% CI: 0.63-0.72). Cox proportional hazards regression confirmed a significant survival difference between predicted groups after adjustment for established prognostic factors (hazard ratio: 1.47; 95% CI: 1.26-1.72). Three neuropathologists categorized the identified visual patterns into seven distinct histomorphological groups, revealing both established prognostic features and unexpected associations, the latter being potentially attributable to surgery-related confounders. The presented explainable AI framework facilitates prognostic biomarker discovery in GBM-IDHwt and beyond, highlighting promising histomorphological features for further analysis and exposing potential confounders that would be hidden in black-box models.