1. Deep Learning-Based Nuclear Lobe Count Method for Differential Count of Neutrophils
- Author
-
Yabuta, Mayu, Nakamura, Iori, Ida, Haruhi, Masauzi, Hiromi, Okada, Kazunori, 1000060630978, Kaga, Sanae, 1000090630476, Miwa, Keiko, Masauzi, Nobuo, Yabuta, Mayu, Nakamura, Iori, Ida, Haruhi, Masauzi, Hiromi, Okada, Kazunori, 1000060630978, Kaga, Sanae, 1000090630476, Miwa, Keiko, and Masauzi, Nobuo
- Abstract
Differentiating neutrophils based on the count of nuclear lobulation is useful for diagnosing various hematological disorders, including megaloblastic anemia, myelodysplastic syndrome, and sepsis. It has been reported that one-fifth of sepsis-infected patients worldwide died between 1990 and 2017. Notably, fewer nuclear-lobed and stab-formed neutrophils develop in the peripheral blood during sepsis. This abnormality can serve as an early diagnostic criterion. However, testing this feature is a complex and time-consuming task that is rife with human error. For this reason, we apply deep learning to automatically differentiate neutrophil and nuclear lobulation counts and report the world's first small-scale pilot. Blood films are prepared using venous peripheral blood taken from four healthy volunteers and are stained with May Grunwald Giemsa stain. Six-hundred 360 x 363-pixel images of neutrophils having five different nuclear lobulations are automatically captured by Cellavision DM-96, an automatic digital microscope camera. Images are input to an original architecture with five convolutional layers built on a deep learning neural-network platform by Sony, Neural Network Console. The deep learning system distinguishes the four groups (i.e., band-formed, two-, three-, and four- and five-segmented) of neutrophils with up to 99% accuracy, suggesting that neutrophils can be automatically differentiated based on their count of segmented nuclei using deep learning.
- Published
- 2021