Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This study introduces CRIL-U-Net, a novel 3D U-Net architecture designed for the automated segmentation of focal cortical dysplasia (FCD) from T1w and FLAIR MRI scans. By integrating a Compact Ratio-Interaction Learning module that enhances cross-modal feature interaction, CRIL-U-Net achieved a mean Dice score of 0.196, significantly outperforming conventional 3D U-Net and attention-based U-Net models. Despite its success, the model still exhibited a 48.2% zero-overlap rate, indicating the necessity for further refinement in segmentation techniques for FCD.
CRIL-U-Net's innovative approach to cross-modal representation learning leads to a significant leap in the accuracy of FCD segmentation, revealing critical insights for epilepsy treatment.
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.