Soumick Chatterjee

This study identifies three leukaemia stem cell subtypes in paediatric AML and shows that combining CLEC12A and CD84 targets all subtypes while sparing healthy cells.

scINTILLA assesses cell-type annotation quality in single-cell datasets by combining supervised and unsupervised learning to identify label ambiguity and hidden heterogeneity.

This study uses 3D diffusion autoencoders to derive latent cardiac MRI phenotypes, finds they share a genetic basis with cardiometabolic traits, and shows predictive power for disease risk.

VesselBoost is a Python tool for segmenting small blood vessels in human MRA data using deep learning and data augmentation to overcome labeling challenges.

This paper uses self-supervised learning to analyze histology images and predict spatial RNA expression across 23 human tissues, revealing population variability and its impact on gene expression.