Abstract: Recognition of AML Blast Cells in a Curated Single-Cell Dataset of Leukocyte Morphologies Using Deep Convolutional Neural Networks
- 55 Downloads
Reliable recognition and microscopic differentiation of malignant and non-malignant leukocytes from peripheral blood smears is a key task of cytological diagnostics in hematology . Having been practised for well over a century, cytomorphological analysis is still today routinely performed by human examiners using optical microscopes, a process that can be tedious, time-consuming, and suffering from considerable intra-and inter-rater variability . Our work aims to provide a more quantitative and robust decision-aid for the differentiation of single blood cells in general and recognition of blast cells characteristic for Acute Myeloid Leukemia (AML) in particular.
- 1.Bain BJ. Diagnosis from the blood smear. N Eng J Med. 2005;353:498–507.Google Scholar
- 2.Fuentes-Arderiu X, Dot-Bach D. Measurement uncertainty in manual differential leukocyte counting. Clin Chem Lab Med. 2009;47:112–115.Google Scholar
- 3.Matek C, Schwarz S, Marr C, et al.. A Single-cell morphological dataset of leukocytes from AML patients and non-malignant controls.; 2019. Cancer Imaging Archive.Google Scholar
- 4.Matek C, Schwarz S, Spiekermann ea. Human-level recognition of blast cells in acute myeloid leukemia with convolutional neural networks. Nature Mach Intell. 2019;(1):538–544.Google Scholar
- 5.Xie S, Girshick R, Dollár P, et al. Aggregated residual transformations for deep neural networks. Proc IEEE CVPR. 2017;.Google Scholar