Incorporating artificial intelligence into morphological diagnosis of acute leukemias: Current landscape, challenges and prospects (Review)
Clinical Snapshot
PICO Framework
| P — Population | Patients with suspected acute leukemias requiring morphological diagnosis |
| I — Intervention | Artificial intelligence and machine learning applications for cell morphology analysis |
| C — Comparator | Manual microscopic examination and traditional morphological assessment |
| O — Outcomes | Diagnostic accuracy, efficiency, and reduction of subjective bias in acute leukemia diagnosis |
Bottom Line
This narrative review examines the potential for machine learning to improve morphological diagnosis of acute leukemias by addressing inefficiencies and subjective bias in manual microscopy. While the technology shows promise for enhancing diagnostic accuracy and workflow efficiency, the review appears to lack systematic methodology for evidence synthesis. The clinical application remains promising but requires rigorous validation studies and regulatory approval before implementation. Australian hematology services could benefit from such technology, particularly in resource-limited settings, but careful evaluation of diagnostic performance against current gold standards would be essential. The review highlights an important emerging field but provides limited quantitative evidence for clinical decision-making at this stage.
Key Findings
Effect Size: Not quantified in abstract
Primary Outcome: Overview of current AI applications in acute leukemia morphological diagnosis
Nnt Or Sensitivity: Specific diagnostic performance metrics not provided in abstract
Confidence Interval: Not applicable for narrative review
Clinical Application
Implementation would require significant infrastructure investment and validation studies Relevant to Australian pathology services, though TGA approval would be required for diagnostic AI tools. Could support rural and remote diagnostic capabilities where specialist hematopathologists are limited Hematology laboratories and clinicians involved in acute leukemia diagnosis
Abstract
Acute leukemias (ALs) are a diverse group of hematological malignancies characterized by the abnormal proliferation of immature cells. Microscopic observation of cell morphology based on the French‑American‑British classification remains a fundamental diagnostic method for ALs. However, manual screening from bone marrow smear images is often inefficient, laborious and prone to subjective bias, leading to potential misdiagnosis or missed diagnosis. Artificial intelligence (AI), particularly machine learning (ML), has expanded human capabilities in analyzing complex datasets, leading to breakthroughs in multiple fields, including medical research and clinical practice. Increasingly, ML applications are being developed to diagnose hematological diseases by extracting and aggregating morphological characteristics from peripheral blood and bone marrow smears. However, applying ML methods to recognize cell morphology in hematological diseases presents unique challenges compared with other pathology subspecialties. The present review provided an overview of AI and ML applications in ALs diagnosis, focusing on cell segmentation and data mining methods from microscopy images, and highlights their advantages over manual microscopy.
References
- 1.Cheng, H., Zheng, G., Yang, Y., Xu, C., Tang, G., & Huang, C. (2026). Incorporating artificial intelligence into morphological diagnosis of acute leukemias: Current landscape, challenges and prospects (Review). Oncology Reports. https://doi.org/10.3892/or.2026.9120
Related Research
Blood advances
Phase 1b study of ABBV-744, a novel, selective BET inhibitor, as monotherapy for patients with myelofibrosis
27 May 2026
European journal of pediatrics
Safety and efficacy of liposomal iron for iron deficiency anemia in pediatric population: A systematic review and meta-analysis of randomized controlled trials
26 May 2026
The Cochrane database of systematic reviews
Early erythropoiesis-stimulating agents in preterm or low-birthweight infants
25 May 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service