Deep learning differentiates myeloproliferative neoplasms and predicts JAK2 and CALR mutations from bone marrow smears.

doi:10.1007/s00277-026-07257-w

Loading publication...

Noodle always counts identifier-free feature events for service operation. With your permission, Google Analytics can also estimate audience and engagement. Search text, publication identifiers, cookies, IP addresses and browser fingerprints are never included in Noodle's first-party event counters.

Privacy details

Community

Back to search

Article

Deep learning differentiates myeloproliferative neoplasms and predicts JAK2 and CALR mutations from bone marrow smears.

Annals of hematology - 25 Aug 2026

Eckardt Jan-Niklas, Reddy Chethan Babu V, Hauspurg Holger, Riechert Sebastian, Schmittmann Tim, Srivastava Ishan, Winter Susann, Sockel Katja, Badstübner Markus, Bornhäuser Martin, Tiemann Markus, Middeke Jan Moritz

Abstract excerpt

Accurate differentiation of BCR::ABL1-negative myeloproliferative neoplasms (MPNs) based on bone marrow smear morphology remains challenging. While previous artificial intelligence (AI) approaches have primarily focused on bone marrow core biopsies, the diagnostic potential of routine bone marrow smears has remained largely unexplored. Using 460 digitized bone marrow smear whole-slide images, we developed an...

Read the complete abstract on PubMed