发表机构
University of Washington（华盛顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对脑肿瘤分割中多对比度3D MRI分割计算量大的问题，采用部分信息分解框架对输入对排序选最优用于训练，实验表明该方法选出的T1c+T2-FLAIR是强双输入配置，证明了基于PID预训练选择的实用价值。
AI 中文摘要
当使用所有可用序列时，多对比度3D MRI分割在计算上要求很高。我们评估了一个预训练的部分信息分解框架，该框架根据输入对关于区域肿瘤负担的冗余、独特和协同信息对其进行排序，并选择排名最高的对用于下游训练。应用于T1n、T1c、T2w和T2-FLAIR MRI时，该框架选择了T1c+T2-FLAIR。然后，我们使用不同的输入配置训练了11个结构相同的轻量级3D U-Net。在一个独立测试队列中，T1c+T2-FLAIR是最强的双输入配置，在平均Dice中排名第二（所有四个输入为0.676，而所有四个输入为0.687）。对全输入模型的独立Shapley分析也确定T2-FLAIR和T1c是最有影响的输入，它们的成对交互作用最强。这些发现证明了基于PID的预训练选择在昂贵的3D模型开发之前识别紧凑、信息丰富的MRI输入集的实用价值。
英文摘要
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.
