Impact of Synthetic Lesional MR Images in Automated Focal Cortical Dysplasia Detection in Low-Data Scenarios
Researchers have developed a method using conditional generative networks to create synthetic MRI images of focal cortical dysplasia (FCD). These synthetic images were found to be realistic enough that experts could barely distinguish them from real scans. Augmenting detection models with this synthetic data improved sensitivity and confidence, potentially reducing the need for extensive manual annotations. AI
IMPACT Synthetic data generation can significantly reduce the need for manual annotation in medical imaging, accelerating AI development for rare disease detection.