3D Graph Attention Networks for High Fidelity Pediatric Glioma Segmentation

TL;DR

This paper introduces a novel 3D UNet with spatial attention for pediatric glioma segmentation, improving accuracy in neuroimaging analysis to aid clinical diagnosis and treatment planning.

Contribution

It presents a new 3D UNet architecture with spatial attention tailored for pediatric glioma segmentation, enhancing feature capture and segmentation accuracy.

Findings

Improved Dice similarity coefficient scores.

Reduced segmentation errors around tumor boundaries.

Enhanced delineation of complex glioma structures.

Abstract

Pediatric brain tumors, particularly gliomas, represent a significant cause of cancer related mortality in children with complex infiltrative growth patterns that complicate treatment. Early, accurate segmentation of these tumors in neuroimaging data is crucial for effective diagnosis and intervention planning. This study presents a novel 3D UNet architecture with a spatial attention mechanism tailored for automated segmentation of pediatric gliomas. Using the BraTS pediatric glioma dataset with multiparametric MRI data, the proposed model captures multi-scale features and selectively attends to tumor relevant regions, enhancing segmentation precision and reducing interference from surrounding tissue. The model's performance is quantitatively evaluated using the Dice similarity coefficient and HD95, demonstrating improved delineation of complex glioma structured. This approach offers a promising advancement in automating pediatric glioma segmentation, with the potential to improve clinical decision making and outcomes.