Deep cytomorphology identifies erythroid skewing and monocytic morphology to predict TKI sensitivity in CML patients

Katariina Luukkainen; Mikko Purhonen; Mikael Tatun; Kevin Hung; Oda Tafjord; Henri Sundquist; Stina Söderlund; Shady Adnan-Awad; Anni Dohlen; Johanna Heikkinen; Perttu Koskenvesa; Lotta Joutsi-Korhonen; Anna Lempiäinen; Sanna Siitonen; Satu Mustjoki; Naranie Shanmuganathan; Coral Bryce; Signe Danielsson; Henrik Hjorth-Hansen; Ulla Olsson-Strömberg; Takashi Kumagai; Shinya Kimura; David M Ross; Oscar Brück

doi:10.1002/hem3.70319

Deep cytomorphology identifies erythroid skewing and monocytic morphology to predict TKI sensitivity in CML patients

Hemasphere. 2026 Feb 13;10(2):e70319. doi: 10.1002/hem3.70319. eCollection 2026 Feb.

Authors

Katariina Luukkainen^{1

2

3}, Mikko Purhonen^{1

2

3}, Mikael Tatun^{1

2

3}, Kevin Hung⁴, Oda Tafjord⁵, Henri Sundquist^{1

2

3}, Stina Söderlund⁶, Shady Adnan-Awad^{7

8

9

10

11}, Anni Dohlen^{1

2

3}, Johanna Heikkinen^{1

2

3}, Perttu Koskenvesa¹², Lotta Joutsi-Korhonen³, Anna Lempiäinen³, Sanna Siitonen^{1

2

3}, Satu Mustjoki^{7

8

9}, Naranie Shanmuganathan^{4

13}, Coral Bryce¹¹, Signe Danielsson¹⁴, Henrik Hjorth-Hansen^{5

15}, Ulla Olsson-Strömberg⁶, Takashi Kumagai¹⁶, Shinya Kimura¹⁷, David M Ross^{3

4

18}, Oscar Brück^{1

2

3}

Affiliations

¹ Hematoscope Lab Comprehensive Cancer Center, Helsinki University Hospital Helsinki Finland.
² Department of Oncology University of Helsinki Helsinki Finland.
³ Department of Clinical Chemistry HUS Diagnostic Center, University of Helsinki and Helsinki University Hospital Helsinki Finland.
⁴ Royal Adelaide Hospital and SA Pathology, Central Adelaide Local Health Network Adelaide South Australia Australia.
⁵ Department of Hematology St. Olavs Hospital Trondheim Norway.
⁶ Department of Medical Science and Division of Hematology University Hospital Uppsala Sweden.
⁷ Hematology Research Unit Helsinki, Department of Hematology University of Helsinki and Helsinki University Hospital Comprehensive Cancer Center Helsinki Finland.
⁸ ICAN Digital Precision Cancer Medicine Flagship University of Helsinki and Helsinki University Hospital Comprehensive Cancer Center Helsinki Finland.
⁹ Translational Immunology Research Program University of Helsinki Helsinki Finland.
¹⁰ MRC Molecular Haematology Unit, Weatherall Institute of Molecular Medicine, Radcliffe Department of Medicine and National Institute of Health Research (NIHR), Oxford Biomedical Research Centre University of Oxford Oxford United Kingdom.
¹¹ Clinical Pathology Department, National Cancer Institute Cairo University Giza Egypt.
¹² Department of Hematology Helsinki University Hospital Comprehensive Cancer Center Helsinki Finland.
¹³ Precision Medicine Theme South Australian Health and Medical Research Institute Adelaide South Australia Australia.
¹⁴ Department of Medicine, Faculty of Medicine and Health Örebro University Örebro Sweden.
¹⁵ Department of Cancer Research and Molecular Medicine Norwegian University of Science and Technology (NTNU) Trondheim Norway.
¹⁶ Department of Hematology Ome Medical Center Ome-Shi Tokyo Japan.
¹⁷ Division of Hematology, Respiratory Medicine and Oncology, Department of Internal Medicine, Faculty of Medicine Saga University Saga Japan.
¹⁸ Department of Haematology Flinders University and Medical Centre Adelaide South Australia Australia.

Abstract

The cellular composition of the chronic myeloid leukemia (CML) bone marrow (BM) beyond granulocyte enrichment remains poorly understood. We analyzed 1548 routinely stained BM aspirate slides from 598 patients across seven sites using deep learning-based image analysis to identify cytomorphological markers predictive of major molecular response. Erythroid precursor enrichment, monocyte nuclear lobulation, and low peripheral leukocyte count were associated with improved tyrosine kinase inhibitor (TKI) response. These features were validated both visually and computationally in two independent cohorts. We developed a Morphoclinical model integrating these image-derived and clinical variables, outperforming (area under the receiver-operating curve [AUROC] 0.76) the clinically used EUTOS long-term survival score (AUROC 0.53) and BCR::ABL1 halving time (AUROC 0.61). Notably, poor-risk patients treated with second-generation TKIs achieved outcomes similar to favorable-risk patients on imatinib. These results underline the overlooked prognostic value of BM cytomorphology to refine risk stratification and support more personalized frontline therapy in CML.