Dr. Vaanathi Sundaresan
Colleges
Curriculum Vitae
Vaanathi_sundaresan_CV.pdf
- Vaanathi Sundaresan_CV_2022.pdf
- PDF document 191.8 KB
Vaanathi Sundaresan
Honorary Research Fellow
- Assistant Professor, Department of Computational and Data Sciences (CDS), Indian Institute of Science (IISc), Bangalore, India.
Biography
About me
My work with Prof. Mark Jenkinson and Dr. Ludovica Griffanti, at Oxford centre for Functional MRI of the brain (FMRIB), Wellcome Centre for Integrative Neuroimaging (WIN), involves development of deep learning-based tools for domain adaption of segmentation methods and harmonisation of data from various sources.
My DPhil work was on AI-driven automated detection of small vessel disease signs on brain MR images. My postdoctoral research focusses on domain adaptation and harmonisation of neuroimaging data using deep learning methods.
Research
My research interests include domain adaptation of segmentation models for segmentation of dementia signs and harmonisation of structural data as preprocessing step for further robust analyses. My DPhil work was on modelling the distribution of white matter lesions within a population and the detection of white matter pathologies of the brain in MR images.
Key publications
Triplanar ensemble U-Net model for white matter hyperintensities segmentation on MR images
Journal article
Sundaresan V. et al, (2020)
Modelling the distribution of white matter hyperintensities due to ageing on MRI images using Bayesian inference.
Journal article
Sundaresan V. et al, (2019), NeuroImage, 185, 434 - 445
Automated lesion segmentation with BIANCA: impact of population-level features, classification algorithm and locally adaptive thresholding
Journal article
Sundaresan V. et al, (2018)
Automated characterization of the fetal heart in ultrasound images using fully convolutional neural networks
Conference paper
Sundaresan V. et al, (2017), Proceedings - International Symposium on Biomedical Imaging, 671 - 674
BIANCA (Brain Intensity AbNormality Classification Algorithm): A new tool for automated segmentation of white matter hyperintensities.
Journal article
Griffanti L. et al, (2016), Neuroimage, 141, 191 - 205
Recent publications
Automated detection of lacunes in brain MR images using SAM with robust prompts using self-distillation and anatomy-informed priors.
Journal article
Deepika P. et al, (2025), Comput Biol Med, 196
Label-efficient sequential model-based weakly supervised intracranial hemorrhage segmentation in low-data non-contrast CT imaging.
Journal article
Ramananda SH. and Sundaresan V., (2025), Med Phys, 52, 2123 - 2144