Deep learning predicts therapy-relevant genetics in acute myeloid leukemia from Pappenheim-stained bone marrow smears

Kockwelp, Jacqueline; Thiele, Sebastian; Bartsch, Jannis; Haalck, Lars; Gromoll, Jörg; Schlatt, Stefan; Exeler, Rita; Bleckmann, Annalen; Lenz, Georg; Wolf, Sebastian; Steffen, Björn; Berdel, Wolfgang Eduard; Schliemann, Christoph; Risse, Benjamin; Angenendt, Linus

Forschungsartikel (Zeitschrift) | Peer reviewed

Zusammenfassung

The detection of genetic aberrations is crucial for early therapy decisions in acute myeloid leukemia (AML) and recommended for all patients. Because 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 multiterabyte data set of >2 000 000 single-cell images from diagnostic samples of 408 patients with AML. These images were then used to train convolutional neural networks for the prediction of various therapy-relevant genetic alterations. Moreover, we created a temporal test cohort data set of >444 000 single-cell images from further 71 patients with AML. We show that the models from our pipeline can significantly predict these subgroups with high areas under the curve of the receiver operating characteristic. Potential genotype-phenotype links were visualized with 2 different strategies. Our pipeline holds the potential to be used as a fast and inexpensive automated tool to screen patients with AML 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.

Details zur Publikation

FachzeitschriftBlood Advances
Jahrgang / Bandnr. / Volume8
Ausgabe / Heftnr. / Issue1
Seitenbereich70-79
StatusVeröffentlicht
Veröffentlichungsjahr2024 (09.01.2024)
Sprache, in der die Publikation verfasst istEnglisch
DOI10.1182/bloodadvances.2023011076
Link zum Volltexthttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC10787267/
StichwörterHumans; Bone Marrow; Deep Learning; Leukemia, Myeloid, Acute; Neural Networks, Computer; Bone Marrow Diseases; Acute Myeloid Leukemia; Bone Marrow Smears; Classification; Mutation Prediction; Automatic Extraction Pipeline

Autor*innen der Universität Münster

Angenendt, Linus
Medizinische Klinik A (Med A)
Berdel, Wolfgang Eduard
Medizinische Klinik A (Med A)
Bleckmann, Annalen
Medizinische Klinik A (Med A)
Exeler, Jakoba Rita
Klinik für Medizinische Genetik
Gromoll, Jörg
Institut für Reproduktions- und Regenerationsbiologie
Haalck, Lars
Professur für Geoinformatics for Sustainable Development (Prof. Risse)
Kockwelp, Jacqueline
Institut für Reproduktions- und Regenerationsbiologie
Lenz, Georg
Medizinische Klinik A (Med A)
Risse, Benjamin
Professur für Geoinformatics for Sustainable Development (Prof. Risse)
Schlatt, Stefan
Centrum für Reproduktionsmedizin und Andrologie
Schliemann, Christoph
Medizinische Klinik A (Med A)
Thiele, Sebastian
Professur für Geoinformatics for Sustainable Development (Prof. Risse)