CRIL-U-Net: Compact Ratio-Interaction Learning for Focal Cortical Dysplasia Segmentation from T1w and FLAIR MRI

2026-08-04

AI Summary

This study addresses the challenge of automated segmentation of focal cortical dysplasia (FCD) type II lesions in T1-weighted and FLAIR MRI, which is hindered by their small size, heterogeneous appearance, and subtle imaging features. To tackle this, the authors propose CRIL-U-Net, a 3D U-Net architecture incorporating a compact ratio-based interactive learning module. This approach explicitly models the nonlinear complementary relationships between multimodal MRI sequences through voxel-level cross-modal fusion and bidirectional ratio-inspired interaction. The method further mitigates class imbalance by combining Dice-BCE and Focal Tversky-Focal loss functions. Evaluated via five-fold cross-validation on 85 FCD patients and 25 healthy controls, CRIL-U-Net achieved a Dice score of 0.196—significantly outperforming baseline methods—and detected non-zero lesion overlap in 44 cases (FDR-corrected p<0.05), demonstrating its efficacy in segmenting subtle FCD lesions.

Abstract

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.

Problem

• Focal cortical dysplasia
• MRI segmentation
• multimodal imaging
• drug-resistant epilepsy
• lesion detection

Innovation

• Compact Ratio-Interaction Learning
• Multimodal MRI Segmentation
• Focal Cortical Dysplasia
• 3D U-Net
• Cross-modal Interaction