提出紧凑跨模态学习模块，提升癫痫病变分割精度。
CRIL-U-Net: Compact Ratio-Interaction Learning for Focal Cortical Dysplasia Segmentation from T1w and FLAIR MRI
- 设计紧凑比值交互模块，显式建模T1w与FLAIR图像关系。
- 在85例患者中实现0.196平均Dice分数，优于对比模型。
- 适合神经影像分析、癫痫病灶自动识别的研究者参考。
局灶性皮质发育不良（FCD）II型是难治性局灶性癫痫的重要结构原因，但其体积小、表现异质且MRI特征细微，自动化分割极具挑战。传统多模态网络通常拼接T1加权（T1w）和液体衰减反转恢复（FLAIR）图像，依赖后续层隐式学习跨模态关系。本文提出CRIL-U-Net，一种3D U-Net架构，融合紧凑比值交互学习模块，结合局部空间特征、体素级跨模态混合及双向比值启发的交互机制。在85例FCD患者与25名健康对照上进行五折交叉验证，分别使用Dice-BCE与聚焦Tversky-聚焦（FTF）损失独立训练各架构。采用FTF损失时，CRIL-U-Net取得最高平均Dice分数（0.196 ± 0.262），显著高于标准U-Net（0.136 ± 0.224）与自注意力对比模型（0.135 ± 0.214）。该模型在44例中产生非零病灶重叠，而标准U-Net为36例。经错误发现率校正后，CRIL-U-Net性能显著优于两者。结果表明，在可控的U-Net框架下，结合不平衡感知目标函数，紧凑跨模态表示学习可有效提升FCD分割效果，但仍有48.2%病例无重叠，提示仍需进一步验证与方法优化。
原文摘要 · Abstract (English)
Focal cortical dysplasia (FCD) type II is an important structural cause of drug-resistant focal epilepsy, but its small size, heterogeneous appearance, and subtle MRI characteristics make automated segmentation challenging. Conventional multimodal networks commonly concatenate T1-weighted (T1w) and fluid-attenuated inversion recovery (FLAIR) images, requiring subsequent layers to learn useful cross-modal relationships implicitly. We propose CRIL-U-Net, a 3D U-Net incorporating a Compact Ratio-Interaction Learning module that combines local spatial features, voxel-wise cross-modal mixing, and bidirectional ratio-inspired interactions. CRIL-U-Net was compared with a conventional 3D U-Net and an input self-attention U-Net using five-fold cross-validation on 85 FCD subjects and 25 healthy controls. Each architecture was trained independently using Dice-binary cross-entropy (Dice-BCE) and Focal Tversky-Focal (FTF) losses. With FTF, CRIL-U-Net achieved the highest mean Dice score (0.196 +/- 0.262), compared with 0.136 +/- 0.224 for the U-Net and 0.135 +/- 0.214 for the attention comparator. It produced nonzero lesion overlap in 44 of 85 cases, compared with 36 for the U-Net. Under FTF, CRIL-U-Net significantly outperformed both comparison architectures after false-discovery-rate correction. These findings suggest that compact cross-modal representation learning can improve FCD segmentation within a controlled U-Net setting when combined with an imbalance-aware objective, although the remaining zero-overlap rate of 48.2% highlights the need for further validation and methodological development.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。