Publications, papers, and research contributions in AI, healthcare, and representation learning.
Contrastive Siamese localization model disentangling disease labels from bounding boxes to improve generalization.
Semi-supervised U-Net segmentation of non-gated CT scans for cardiovascular risk stratification.
Cost-sensitive analysis of error tradeoffs in binary medical ML tasks.
Image-subtraction-based Mask R-CNN for heterogeneous tumor segmentation.
Attention-augmented CNN to compensate for diagnostic variability in CXR interpretation.
Teacher–student GANs for liver MRI synthesis and segmentation enhancement (6k+ slices).
Developed multimodal latent representations across 6,000+ patient records, comparing feature representations and 2D versus 3D embedding strategies to improve cohort separation and interpretability.
Appliance-level inference from smart-meter time series using shape-based clustering.
Compared LightGBM, LSTM, and Transformer models across 1M+ highly imbalanced credit-card transactions, varying feature representations to maximize fraud recall under a strict false-positive constraint.
Unsupervised clustering of 50k+ patient records to infer medical specializations.