Diagnosis of Leukemia from Bone Marrow Flow Cytometry Data Using Deep Learning and Explainable Artificial Intelligence
The American Journal of Pathology · 2026
DOI: 10.1016/j.ajpath.2026.03.011 ↗Kurz gefasst
Fachartikel in der Zeitschrift The American Journal of Pathology, 2026. Verfasst von Niloofar Reshadfar und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Data Science, Faculty of Interdisciplinary Science and Technology, Tarbiat Modares University, Tehran, Iran. Hauptthemen laut MEDLINE: Leukemia, Deep Learning, Flow Cytometry, Bone Marrow. Die Arbeit nennt 29 Literaturangaben.
Abstract (Originalsprache)
Leukemia is a life-threatening blood cancer requiring rapid and accurate diagnosis to improve patient survival. Although flow cytometry offers powerful multiparametric analysis, manual interpretation remains slow, subjective, and, thus, prone to error. This study presents an automated diagnostic system using deep learning to analyze bone marrow flow cytometry samples from this technology. Three advanced neural network models were developed and evaluated: recurrent, graph-based, and attention-enhanced convolutional networks. The data set comprised >2000 samples from patients with leukemia and healthy individuals. The attention-enhanced Visual Geometry Group 19‑layer (VGG19) architecture convolutional model delivered the highest performance, achieving 96% accuracy and near-perfect discrimination between disease states. Additionally, explainable artificial intelligence techniques enhanced transparency, confirming the model focused on biologically relevant cell clusters. To ensure real-world applicability, the model was rigorously evaluated on completely unseen patients, revealing generalization challenges addressed through careful hyperparameter optimization. Furthermore, standard image augmentation techniques degraded performance significantly, highlighting the need for domain-specific data approaches. Notably, this study focused on newly diagnosed bone marrow specimens with high tumor burden. Consequently, overall reported performance may not directly generalize to low-level disease states or minimal residual disease scenarios. Therefore, this work demonstrates a highly accurate, interpretable, and clinically relevant tool that can ultimately accelerate leukemia diagnosis, significantly reduce human error, and support expert pathologists in their critical clinical work.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Data Science, Faculty of Interdisciplinary Science and Technology, Tarbiat Modares University, Tehran, Iran.
- Department of Data Science, Faculty of Interdisciplinary Science and Technology, Tarbiat Modares University, Tehran, Iran; Department of Medical Informatics, Faculty of Medical Sciences, Tarbiat Modares University, Tehr…
- Department of Data Science, Faculty of Interdisciplinary Science and Technology, Tarbiat Modares University, Tehran, Iran; Department of Statistics, Tarbiat Modares University, Tehran, Iran.
- Department of Pediatrics, Imam Ali Hospital, Alborz University of Medical Sciences, Karaj, Iran.
Zitieren
APA
Reshadfar, N., Safaei, A. A., Golalizadeh, M., & Haghi, S. (2026). Diagnosis of Leukemia from Bone Marrow Flow Cytometry Data Using Deep Learning and Explainable Artificial Intelligence. The American Journal of Pathology. https://doi.org/10.1016/j.ajpath.2026.03.011
Vancouver
Reshadfar N, Safaei AA, Golalizadeh M, Haghi S. Diagnosis of Leukemia from Bone Marrow Flow Cytometry Data Using Deep Learning and Explainable Artificial Intelligence. The American Journal of Pathology. 2026. doi:10.1016/j.ajpath.2026.03.011
BibTeX
@article{Reshadfar2026,
author = {Reshadfar, Niloofar and Safaei, Ali Asghar and Golalizadeh, Mousa and Haghi, Sabahat},
title = {Diagnosis of Leukemia from Bone Marrow Flow Cytometry Data Using Deep Learning and Explainable Artificial Intelligence},
journal = {The American Journal of Pathology},
year = {2026},
doi = {10.1016/j.ajpath.2026.03.011}
}
EUVIMED