Comparative evaluation of training strategies using partially labelled datasets for segmentation of white matter hyperintensities and stroke lesions in FLAIR MRI
Researchers have developed and evaluated six strategies for training deep learning models to segment white matter hyperintensities and stroke lesions in MRI scans, particularly when dealing with partially labeled datasets. Their analysis, conducted on a large cohort of 2,052 MRI volumes, found that pseudolabeling was the most effective method for improving model performance. This approach demonstrates the potential for creating reliable automated segmentation tools to aid in monitoring cerebral small vessel disease and extracting biomarkers for clinical research. AI
IMPACT Demonstrates a viable method for training AI models on limited labeled data, potentially accelerating clinical research and disease monitoring.