Vaanathi Sundaresan

This paper introduces a deep-learning method for segmenting fiber bundles in histological tracing data, achieving 80% true positive rate with limited manual labels.

This study compares domain adaptation techniques to improve white matter hyperintensity segmentation across different MRI datasets, finding that unsupervised domain adversarial training performs best.

This paper proposes a triplanar ensemble U-Net model for WMH segmentation on MR images, achieving robust performance comparable to existing methods.

This paper harmonises white matter hyperintensity measurements across two neuroimaging datasets by standardising preprocessing and modelling demographic and physiological differences.

This paper improves the BIANCA tool for WMH segmentation by introducing a locally adaptive thresholding method, LOCATE, which significantly enhances segmentation performance compared to global thresholding.

This paper develops a Bayesian spline method to model the spatio-temporal distribution of white matter hyperintensities with respect to age and validates it on simulated and real datasets.