MCMA-Net++: Topology-Aware and Graph-Driven Glioma Segmentation in 3D MRI

Jihan Alameddin, Céline Thomarat, Rémy Guillevin, Christine Fernandez-Maloigne, Carole Guillevin
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:1178-1192, 2026.

Abstract

Glioma segmentation in 3D MRI remains challenging due to tumor heterogeneity, intensity variability, and hierarchical anatomical structure. We propose MCMA-Net++, which synergistically combines hybrid CNN-Transformer encoding, graph-based spatial reasoning with anatomical priors, and a practical multi-component topology-aware refinement loss tailored for nested tumor subregions. Our framework integrates: (1) Topology-Aware Refinement Loss (TAR-Loss), enforcing consistency across nested subregions (ET, TC, WT), and (2) Multi-Scale Anatomical Graph Reasoning (MSAGR), modeling spatial dependencies through learnable graphs with anatomical priors. Combined with dual-stream CNN-Swin Transformer encoding and Multi-Class Multi-Attention, MCMA-Net++ achieves Dice scores of 0.970$\pm$0.003 (WT), 0.943$\pm$0.005 (TC), 0.926$\pm$0.008 (ET), reducing HD95 from 5.48 mm to 3.21 mm compared to MCMA-Net. Graph reasoning contributes +1.3% Dice for ET and TAR-Loss reduces topology violations by 41%. These results demonstrate the effectiveness of combining topology-guided refinement and anatomical graph reasoning for clinical-grade glioma segmentation.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-alameddin26a, title = {MCMA-Net++: Topology-Aware and Graph-Driven Glioma Segmentation in 3D MRI}, author = {Alameddin, Jihan and Thomarat, C{\'e}line and Guillevin, R{\'e}my and Fernandez-Maloigne, Christine and Guillevin, Carole}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {1178--1192}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/alameddin26a/alameddin26a.pdf}, url = {https://proceedings.mlr.press/v315/alameddin26a.html}, abstract = {Glioma segmentation in 3D MRI remains challenging due to tumor heterogeneity, intensity variability, and hierarchical anatomical structure. We propose MCMA-Net++, which synergistically combines hybrid CNN-Transformer encoding, graph-based spatial reasoning with anatomical priors, and a practical multi-component topology-aware refinement loss tailored for nested tumor subregions. Our framework integrates: (1) Topology-Aware Refinement Loss (TAR-Loss), enforcing consistency across nested subregions (ET, TC, WT), and (2) Multi-Scale Anatomical Graph Reasoning (MSAGR), modeling spatial dependencies through learnable graphs with anatomical priors. Combined with dual-stream CNN-Swin Transformer encoding and Multi-Class Multi-Attention, MCMA-Net++ achieves Dice scores of 0.970$\pm$0.003 (WT), 0.943$\pm$0.005 (TC), 0.926$\pm$0.008 (ET), reducing HD95 from 5.48 mm to 3.21 mm compared to MCMA-Net. Graph reasoning contributes +1.3% Dice for ET and TAR-Loss reduces topology violations by 41%. These results demonstrate the effectiveness of combining topology-guided refinement and anatomical graph reasoning for clinical-grade glioma segmentation.} }
Endnote
%0 Conference Paper %T MCMA-Net++: Topology-Aware and Graph-Driven Glioma Segmentation in 3D MRI %A Jihan Alameddin %A Céline Thomarat %A Rémy Guillevin %A Christine Fernandez-Maloigne %A Carole Guillevin %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-alameddin26a %I PMLR %P 1178--1192 %U https://proceedings.mlr.press/v315/alameddin26a.html %V 315 %X Glioma segmentation in 3D MRI remains challenging due to tumor heterogeneity, intensity variability, and hierarchical anatomical structure. We propose MCMA-Net++, which synergistically combines hybrid CNN-Transformer encoding, graph-based spatial reasoning with anatomical priors, and a practical multi-component topology-aware refinement loss tailored for nested tumor subregions. Our framework integrates: (1) Topology-Aware Refinement Loss (TAR-Loss), enforcing consistency across nested subregions (ET, TC, WT), and (2) Multi-Scale Anatomical Graph Reasoning (MSAGR), modeling spatial dependencies through learnable graphs with anatomical priors. Combined with dual-stream CNN-Swin Transformer encoding and Multi-Class Multi-Attention, MCMA-Net++ achieves Dice scores of 0.970$\pm$0.003 (WT), 0.943$\pm$0.005 (TC), 0.926$\pm$0.008 (ET), reducing HD95 from 5.48 mm to 3.21 mm compared to MCMA-Net. Graph reasoning contributes +1.3% Dice for ET and TAR-Loss reduces topology violations by 41%. These results demonstrate the effectiveness of combining topology-guided refinement and anatomical graph reasoning for clinical-grade glioma segmentation.
APA
Alameddin, J., Thomarat, C., Guillevin, R., Fernandez-Maloigne, C. & Guillevin, C.. (2026). MCMA-Net++: Topology-Aware and Graph-Driven Glioma Segmentation in 3D MRI. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:1178-1192 Available from https://proceedings.mlr.press/v315/alameddin26a.html.

Related Material