# FoundBioNet: A Foundation-Based Model for IDH Genotyping of Glioma from Multi-Parametric MRI

arXiv: https://arxiv.org/abs/2508.06756 · HTML: https://mlsanity.com/paper/2508.06756/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 33 references that are in the map.
- First posted on arXiv 9 Aug 2025.

## Builds on (most cited first, 7 of 7)

- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification](https://mlsanity.com/paper/2107.02314/) (2021)
- [A Comprehensive Survey of Foundation Models in Medicine](https://mlsanity.com/paper/2406.10729/) (2024)
- [BrainSegFounder: Towards 3D Foundation Models for Neuroimage Segmentation](https://mlsanity.com/paper/2406.10395/) (2024)
- [MediAug: Exploring Visual Augmentation in Medical Imaging](https://mlsanity.com/paper/2504.18983/) (2025)
- [Style Curriculum Learning for Robust Medical Image Segmentation](https://mlsanity.com/paper/2108.00402/) (2021)
- [Integrative Imaging Informatics for Cancer Research: Workflow Automation for Neuro-oncology (I3CR-WANO)](https://mlsanity.com/paper/2210.03151/) (2022)

## Built on by (most cited first, 1 of 1)

- [Hierarchical Perfusion Graphs for Tumor Heterogeneity Modeling in Glioma Molecular Subtyping](https://mlsanity.com/paper/2605.07156/) (2026)

## Abstract (arXiv)

Accurate, noninvasive detection of isocitrate dehydrogenase (IDH) mutation is essential for effective glioma management. Traditional methods rely on invasive tissue sampling, which may fail to capture a tumor's spatial heterogeneity. While deep learning models have shown promise in molecular profiling, their performance is often limited by scarce annotated data. In contrast, foundation deep learning models offer a more generalizable approach for glioma imaging biomarkers. We propose a Foundation-based Biomarker Network (FoundBioNet) that utilizes a SWIN-UNETR-based architecture to noninvasively predict IDH mutation status from multi-parametric MRI. Two key modules are incorporated: Tumor-Aware Feature Encoding (TAFE) for extracting multi-scale, tumor-focused features, and Cross-Modality Differential (CMD) for highlighting subtle T2-FLAIR mismatch signals associated with IDH mutation. The model was trained and validated on a diverse, multi-center cohort of 1705 glioma patients from six public datasets. Our model achieved AUCs of 90.58%, 88.08%, 65.41%, and 80.31% on independent test sets from EGD, TCGA, Ivy GAP, RHUH, and UPenn, consistently outperforming baseline approaches (p <= 0.05). Ablation studies confirmed that both the TAFE and CMD modules are essential for improving predictive accuracy. By integrating large-scale pretraining and task-specific fine-tuning, FoundBioNet enables generalizable glioma characterization. This approach enhances diagnostic accuracy and interpretability, with the potential to enable more personalized patient care.