Muhammad Dawood

This paper shows that deep learning models for predicting biomarkers from histology images are confounded by interdependencies among biomarkers, leading to less accurate and less reliable predictions.

This study uses spatial transcriptomic analysis and machine learning to redefine the topology of human bone marrow in health and myeloproliferative neoplasms, revealing new insights into cellular heterogeneity and fibrosis.

Star-Motifs identifies spatial patterns in histology slides to reveal clinically relevant tumor microenvironment features and survival correlations.