Deep learning predicts IDH1 mutation status in acute myeloid leukemia from bone marrow smears
Related Experiment Video
Updated: Oct 31, 2026
Workflow for Automated Digital Peripheral Blood and Bone Marrow Cytomorphology, With Consideration of Critical Cellular Misclassifications
Published on: July 28, 2026
Jan-Niklas Eckardt1,2,3,4, Chethan Babu V Reddy5, Andrew Srisuwananukorn6
1Department of Internal Medicine I, University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany. Jan-Niklas.Eckardt@ukdd.de.
Abstract:
Acute myeloid leukemia (AML) with IDH1 mutations is amenable to targeted therapy, highlighting the need for reliable identification. We developed an attention-based multiple-instance learning model to predict IDH1 mutation status using bone marrow smear whole-slide images from 436 AML patients across four centers in Germany and the US, achieving a mean single pooled ROC-AUC of 0.81. In top tile analysis, model predictions for IDH1 were associated with immature leukemia phenotypes.
