Authors: | Yagi, Y.; Yin, Y.; Bakoglu, N.; Shao, X. |
Editor: | Kansal, R. |
Article/Chapter Title: | Clearing barriers to the application of artificial intelligence in hematopathology |
Title Series: | Cancer Etiology, Diagnosis and Treatments |
Abstract: | Hematology is one of the fields to try using Machine Vision or Machine Learning first in the biological sciences. The most basic and most widely developed examination in Hematology is to do the differential counting for stained blood cells. This examination is the typical expertise area of Machine Learning or Artificial Intelligence. Along with the development of convolutional neural networks, all kinds of processing algorithms have sprouted. Our chapter introduces these algorithms according to their classification and purpose in Hematology. By comparison, the application of artificial intelligence in Hematology lags behind other subjects. In this chapter, we have analyzed the reasons for this lag and proposed possible solutions. © 2025 Elsevier B.V., All rights reserved. |
Keywords: | leukemia; bone marrow; blood; tumors; artificial intelligence; promyelocytic leukemia; bone; cell count; diseases; computer vision; myeloproliferative neoplasm; myelodysplastic syndromes; acute promyelocytic leukemia; cells; residual disease; chronic lymphocytic leukemia; acute myeloid leukemia; myeloproliferative neoplasms; machine learning; learning systems; haematology; machine-learning; chronic lymphocytic leukemias; whole slide images; measurable residual disease; convolutional neural networks; whole slide image; differential cell count; digital hematology; peripheral blood smear; peripheral blood smears |
Book Title: | Acute Myeloid Leukemia: Diagnosis, Prognosis, Treatment and Outcomes |
ISBN: | 979-8-89113-299-3 |
Publisher: | Nova Science Publishers Inc. |
Publication Place: | [Hauppauge, NY] |
Date Published: | 2023-01-01 |
Start Page: | 483 |
End Page: | 527 |
Language: | English |
PROVIDER: | scopus |
DOI/URL: | |
Notes: | Book Chapter: 9 -- Source: Scopus |