Vijaya B. Kolachalama

FourierMIL uses Fourier filtering and multiple instance learning to analyze whole-slide images, outperforming existing methods in tumor classification.

This study identifies the Kyn-AHR-TF axis as a prothrombotic pathway in SARS-CoV-2 infection, showing increased kynurenine and AHR activation in mice and humans.

This paper develops a deep learning method to automate measurement of glomerular basement membrane and podocyte foot process widths in TEM images of podocytopathy mouse models, showing comparable accuracy to manual methods.

This paper develops a graph attention-based framework that fuses pathology images and gene expression data to predict cancer survival, showing improved performance over existing methods.

CellDiffusion improves scRNA-seq data integration by accurately inferring cell-cell associations and correcting batch effects across diverse datasets.

This paper introduces GRAPE-Net, a graph-based model that stratifies bronchial premalignant lesions using histopathology images, showing improved classification accuracy for lung cancer subtypes.

This paper develops a deep learning framework that classifies Alzheimer's disease using MRI, age, gender, and MMSE scores, achieving high accuracy across multiple datasets.