# Graph-Radiomic Learning (GrRAiL) Descriptor to Characterize Imaging Heterogeneity in Confounding Tumor Pathologies

arXiv: https://arxiv.org/abs/2509.19258 · HTML: https://mlsanity.com/paper/2509.19258/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 62 references that are in the map.
- First posted on arXiv 23 Sep 2025.

## Builds on (most cited first, 9 of 9)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Representation Learning on Graphs with Jumping Knowledge Networks](https://mlsanity.com/paper/1806.03536/) (2018)
- [DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning](https://mlsanity.com/paper/2003.06777/) (2020)
- [Lung and Pancreatic Tumor Characterization in the Deep Learning Era: Novel Supervised and Unsupervised Learning Approaches](https://mlsanity.com/paper/1801.03230/) (2018)
- [INN: Inflated Neural Networks for IPMN Diagnosis](https://mlsanity.com/paper/1907.00437/) (2019)
- [Radiomic Deformation and Textural Heterogeneity (R-DepTH) Descriptor to characterize Tumor Field Effect: Application to Survival Prediction in Glioblastoma](https://mlsanity.com/paper/2103.07423/) (2021)

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

- [MRI-based Deep Radiomic Phenotyping of Neuromuscular Disorders: A Topology-driven Characterization](https://mlsanity.com/paper/2608.24415/) (2026)

## Abstract (arXiv)

A significant challenge in solid tumors is reliably distinguishing confounding pathologies from malignant neoplasms on routine imaging. While radiomics methods seek surrogate markers of lesion heterogeneity on CT/MRI, many aggregate features across the region of interest (ROI) and miss complex spatial relationships among varying intensity compositions. We present a new Graph-Radiomic Learning (GrRAiL) descriptor for characterizing intralesional heterogeneity (ILH) on clinical MRI scans. GrRAiL (1) identifies clusters of sub-regions using per-voxel radiomic measurements, then (2) computes graph-theoretic metrics to quantify spatial associations among clusters. The resulting weighted graphs encode higher-order spatial relationships within the ROI, aiming to reliably capture ILH and disambiguate confounding pathologies from malignancy. To assess efficacy and clinical feasibility, GrRAiL was evaluated in n=947 subjects spanning three use cases: differentiating tumor recurrence from radiation effects in glioblastoma (GBM; n=106) and brain metastasis (n=233), and stratifying pancreatic intraductal papillary mucinous neoplasms (IPMNs) into no+low vs high risk (n=608). In a multi-institutional setting, GrRAiL consistently outperformed state-of-the-art baselines - Graph Neural Networks (GNNs), textural radiomics, and intensity-graph analysis. In GBM, cross-validation (CV) and test accuracies for recurrence vs pseudo-progression were 89% and 78% with >10% test-accuracy gains over comparators. In brain metastasis, CV and test accuracies for recurrence vs radiation necrosis were 84% and 74% (>13% improvement). For IPMN risk stratification, CV and test accuracies were 84% and 75%, showing >10% improvement.