Omni-Supervised Domain Adversarial Training for White Matter Hyperintensity Segmentation in the UK Biobank

• Published in: Proceedings (International Symposium on Biomedical Imaging) pp. 1 - 4
• Main Authors: Sundaresan, Vaanathi, Dinsdale, Nicola K, Jenkinson, Mark, Griffanti, Ludovica
• Format: Conference Proceeding
• Language: English
• Published: IEEE 28.03.2022
• Subjects: adversarial training; Biological system modeling; Codes; domain adaptation; Image segmentation; Multitasking; omni-supervised learning; Predictive models; Training; Training data; UK Biobank; white matter hyperintensities

White matter hyperintensities (WMHs, or lesions) appear as hyperintense, localized regions on T2-weighted and FLAIR brain MR images. The heterogeneity in lesion characteristics due to subject-level (e.g., local intensity/contrast) and population-level (e.g., demographic, scanner-related) variations...