Faisal Mahmood

SCOPE improves AI triage in 3D pathology by using morphology-aware prototypes to identify high-risk 2D slices for pathologist review.

SCALE3D improves prostate cancer risk prediction by analyzing 3D cell interactions through supercell graphs, outperforming traditional features and reducing computational demands.

This study uses spatial multi-omics to compare EBV-positive and EBV-negative cHL, identifying distinct TME features and immunological signatures linked to EBV.

CARP3D uses deep learning to prioritize high-risk 2D sections in 3D pathology data, improving disease detection while reducing pathologist workload.

spEMO integrates histopathology and spatial multi-omic data using foundation models, improving performance in spatial analysis and medical report generation.

This paper introduces TRACE, a deep learning model for automated liver histopathology assessment in preclinical drug safety, achieving higher concordance than pathologists in lesion scoring and dose-response analysis.

This paper introduces GEESE, an AI model that imputes morphomolecular signatures in toxicology data, linking gene expression changes to drug-induced liver injuries.

The paper introduces a deep learning framework for genomic data that aggregates and predicts somatic mutations and other sparse genomic measures using attention-based multiple instance learning.

This study benchmarks AI methods for end-to-end computational pathology, showing ResNet and ViT outperform MIL and CLAM in mutation prediction but not in tumor subtyping.