Publications

My research focuses on building domain-enriched, ante-hoc interpretable ML algorithms for biomedical image analysis. I embed disease etiology and modality priors directly into model architecture - yielding interpretable, robust, state-of-the-art performance, especially in scarce, noisy, and imperfect clinical conditions.

GLAPAL-H: Global, Local And Parts Aware Learner for Hydrocephalus Infection Diagnosis in Low-Field MRI — The study aims to develop a method for differentiating between healthy, post-infectious hydrocephalus (PIH), and non-post-infectious hydrocephalus (NPIH) in infants using low-field MRI, which is a safer, low-cost alternative to CT scans. The study develops a custom approach that captures hydrocephalus etiology while simultaneously addressing quality issues encountered in low-field MRI.