Benchmarking MRI Representations for Deep Learning-Based Focal Cortical Dysplasia Segmentation
Computer Vision and Pattern Recognition
Summary
The authors studied how different types of MRI images help a deep learning model find brain lesions caused by focal cortical dysplasia (FCD), a condition linked to epilepsy. They tested various MRI image combinations on the same model setup to see which worked best. They found that using FLAIR images alone worked better than T1-weighted images or certain ratio images by themselves. However, combining traditional images with these ratio-derived images gave the best results for detecting the lesions. The authors conclude that choosing the right MRI image types is important for improving automated FCD detection.
Authors
Soumen Ghosh, John Phamnguyen, Amit Soni Arya, Subhojit Mandal, Tilottama Goswami, Rajat Vashistha
Abstract
Focal cortical dysplasia (FCD) is one of the leading structural causes of drug-resistant focal epilepsy, yet its subtle and heterogeneous imaging characteristics make accurate identification and delineation challenging on conventional magnetic resonance imaging (MRI). Although T1-weighted (T1w) and fluid-attenuated inversion recovery (FLAIR) images are routinely acquired for presurgical evaluation, the contribution of different MRI representations to deep learning-based FCD segmentation remains poorly understood. In this study, we present a systematic benchmark of MRI representations for automated FCD segmentation using the nnU-Net framework. A publicly available presurgical MRI dataset comprising 85 FCD subjects and 25 healthy controls was used to evaluate eight input configurations, including conventional MRI contrasts (T1w and FLAIR), ratio-derived representations, and their multimodal combinations. To isolate the effect of MRI representation, all experiments employed identical preprocessing, network architecture, optimization strategy, and five-fold cross-validation. Among the evaluated single-modality representations, FLAIR achieved the strongest overall performance, whereas ratio-derived representations alone were insufficient for reliable identification of subtle FCD. Incorporating ratio-derived representations with conventional T1w and FLAIR images consistently improved lesion delineation, with the four-channel multimodal configuration achieving the highest overall Dice score (0.376), representing a 5.0% relative improvement over the conventional T1w+FLAIR representation. These findings demonstrate that MRI representation design is an important yet underexplored component of deep learning-based FCD segmentation and should be optimized alongside network architecture.