Benchmarking MRI Representations for Deep Learning-Based Focal Cortical Dysplasia Segmentation
Quick Answer
This study benchmarks MRI representations for deep learning-based segmentation of focal cortical dysplasia (FCD) using the nnU-Net framework.
Quick Take
It finds that FLAIR images outperform T1-weighted images in performance, and combining both with ratio-derived representations enhances lesion delineation, achieving a Dice score of 0.376, a 5% improvement over conventional methods.
Key Points
- Evaluated eight MRI input configurations for FCD segmentation.
- FLAIR images showed the strongest performance among single-modality representations.
- Ratio-derived representations alone were insufficient for reliable FCD identification.
- Four-channel multimodal configuration achieved the highest Dice score of 0.376.
- Study emphasizes the need to optimize MRI representation alongside network architecture.
Paper Resources
Source Excerpt
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
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.