Hematopathology deals with the increasing workload and more complex cases that still relies on the microscope examination which takes a lot of time and can vary between observers. This review aims to explore Artificial Intelligence (AI) uses in hematopathology with its current applications, benefits, challenges and future opportunities. Artificial Intelligence (AI) tools—especially Deep Learning (DL) and Convolutional Neural Networks (CNNs)—show strong results, in automatically reading peripheral blood smears and bone marrow aspirates. Beyond morphological classification the review points out AI use in reading flow cytometry data and in predicting blood cancers such as Acute Myeloid Leukemia (AML) and Myelodysplastic Syndromes (MDS). The future of AI in hematopathology depends on combining data types. In that approach AI algorithms merge data, with immunophenotypic data, cytogenetic data and molecular profiles. AI algorithms then give risk grouping and treatment recommendations. However, there are still barriers to using AI in clinics. The black box nature of deep learning models is one barrier. The lack of diverse annotated data sets for training and need, for regulatory rules are another barriers. the review concludes that AI will become a decision support tool and will move the work from microscopy to digital, data driven computational pathology which will improve precision and efficiency.
Noor Hasan Baiee (Sat,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: