PGR-Net: Prior-Guided ROI Reasoning Network for Brain Tumor MRI Segmentation

2026-03-23

AI Summary

This work addresses the challenges of spatial sparsity of lesions and the absence of clinical priors in brain tumor MRI segmentation, which often lead to redundant computation and localization inaccuracies. To this end, the authors propose an explicit ROI-aware framework that leverages data-driven spatial priors to guide the network toward potential lesion regions. Key innovations include a hierarchical Top-K ROI decision mechanism, a WinGS-ROI module, and multi-scale spatially attenuated Gaussian templates, all integrated with a windowed RetNet backbone for efficient feature learning. The method achieves Whole Tumor Dice scores of 89.02%, 91.82%, and 89.67% on BraTS-2019, BraTS-2023, and MSD Task01, respectively, with only 8.64 million parameters, demonstrating an excellent balance between accuracy and computational efficiency.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs

Abstract

Brain tumor MRI segmentation is essential for clinical diagnosis and treatment planning, enabling accurate lesion detection and radiotherapy target delineation. However, tumor lesions occupy only a small fraction of the volumetric space, resulting in severe spatial sparsity, while existing segmentation networks often overlook clinically observed spatial priors of tumor occurrence, leading to redundant feature computation over extensive background regions. To address this issue, we propose PGR-Net (Prior-Guided ROI Reasoning Network) - an explicit ROI-aware framework that incorporates a data-driven spatial prior set to capture the distribution and scale characteristics of tumor lesions, providing global guidance for more stable segmentation. Leveraging these priors, PGR-Net introduces a hierarchical Top-K ROI decision mechanism that progressively selects the most confident lesion candidate regions across encoder layers to improve localization precision. We further develop the WinGS-ROI (Windowed Gaussian-Spatial Decay ROI) module, which uses multi-window Gaussian templates with a spatial decay function to produce center-enhanced guidance maps, thus directing feature learning throughout the network. With these ROI features, a windowed RetNet backbone is adopted to enhance localization reliability. Experiments on BraTS-2019/2023 and MSD Task01 show that PGR-Net consistently outperforms existing approaches while using only 8.64M Params, achieving Dice scores of 89.02%, 91.82%, and 89.67% on the Whole Tumor region. Code is available at https://github.com/CNU-MedAI-Lab/PGR-Net.

Problem

• brain tumor segmentation
• spatial sparsity
• spatial prior
• MRI
• ROI localization

Innovation

• Prior-Guided ROI Reasoning
• Spatial Prior
• Top-K ROI Selection
• WinGS-ROI
• Brain Tumor Segmentation