Partial Information Decomposition as a Multi-Contrast 3D MRI Selection Strategy for Resource-Constrained Deep Neural Network Training in Brain Tumor Segmentation
Quick Answer
This paper shows that A Partial Information Decomposition framework was utilized to select T1c+T2-FLAIR MRI inputs for training lightweight 3D U-Nets, achieving a mean Dice score of 0.676, only slightly lower than the full input configuration's 0.687.
Quick Take
This approach demonstrates an effective strategy for optimizing MRI input selection in resource-constrained environments, enhancing brain tumor segmentation performance.
Key Points
- Partial Information Decomposition ranks MRI input pairs by their information contributions.
- T1c+T2-FLAIR was the top-performing input pair for brain tumor segmentation.
- Eleven lightweight 3D U-Nets were trained with varying input configurations.
- The selected input pair achieved a mean Dice score of 0.676.
- Shapley analysis confirmed T2-FLAIR and T1c as the most influential inputs.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Multi-contrast 3D MRI segmentation can be computationally demanding when all available sequences are used. We evaluate a pre-training Partial Information Decomposition framework that ranks input pairs according to their redundant, unique, and synergistic information about regional tumor burden and selects the highest-ranked pair for downstream training. Applied to T1n, T1c, T2w, and T2-FLAIR MRI, the framework selected T1c+T2-FLAIR. We then trained eleven architecturally identical lightweight 3D U-Nets using different input configurations. On an independent test cohort, T1c+T2-FLAIR was the strongest two-input configuration and ranked second overall in mean Dice (0.676 versus 0.687 for all four inputs). Independent Shapley analysis on the full-input model also identified T2-FLAIR and T1c as the most influential inputs and their pairwise interaction as the strongest. These findings demonstrate the practical value of PID based pre-training selection for identifying compact, informative MRI input sets before costly 3D model development.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.15396 [cs.CV] |
| (or arXiv:2607.15396v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2607.15396 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Agamdeep Chopra [view email]
[v1]
Thu, 16 Jul 2026 18:53:41 UTC (358 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.