Deep Learning Predicts Therapy-Relevant Genetics in Acute Myeloid Leukemia from Pappenheim-stained Bone Marrow Smears.

The detection of genetic aberrations is crucial for early therapy decisions in acute myeloid leukemia (AML) and is recommended for all patients. Since genetic testing is expensive and time-consuming, a need remains for cost-effective, fast, and broadly accessible tests to predict these aberrations in this aggressive malignancy. Here, we developed a novel fully automated end-to-end deep learning pipeline to predict genetic aberrations directly from single-cell images from scans of conventionally stained bone marrow smears already on the day of diagnosis. We used this pipeline to compile a multi-terabyte dataset of over 2,000,000 single-cell images from diagnostic samples of 408 AML patients. These images were then used to train convolutional neural networks for the prediction of various therapy-relevant genetic alterations. We show that the models from our pipeline can significantly predict these subgroups with high AUROCs. Potential genotype-phenotype links were visualized with two different strategies. Our pipeline holds the potential to be used as a fast and inexpensive automated tool to screen AML patients for therapy-relevant genetic aberrations directly from routine, conventionally stained bone marrow smears already on the day of diagnosis. It also creates a foundation to develop similar approaches for other bone marrow disorders in the future.