Share Email Print
cover

Proceedings Paper

Automatic detection of leukemia cells by 2D light scattering microfluidic cytometry and deep learning
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Leukemia is a worldwide malignant tumor with high morbidity and mortality. Developing screening methods for leukemia cells is of great significance for clinical diagnosis. Traditional biochemical and immunohistochemical detection methods that usually require fluorescence labeling are time-consuming and labor-intensive. Here we report a deep learning based 2D light scattering cytometric technique for high-precision, automatic and label-free identification of lymphocytic leukemia cells. A deep convolutional neural network (CNN) is used for learning the biological characteristics of 2D light scattering patterns. The Inception V3 network can identify different label-free acute lymphocytic leukemia cells with a high accuracy. The results show that the deep learning based 2D light scattering microfluidic cytometry is promising for early diagnosis of leukemia, and has the advantages of label free, high efficiency and high automation.

Paper Details

Date Published: 20 November 2019
PDF: 7 pages
Proc. SPIE 11190, Optics in Health Care and Biomedical Optics IX, 111901T (20 November 2019); doi: 10.1117/12.2537094
Show Author Affiliations
Jing Sun, Shandong Univ. (China)
Lan Wang, Shandong Univ. (China)
Qiao Liu, Shandong Univ. (China)
Xuantao Su, Shandong Univ. (China)


Published in SPIE Proceedings Vol. 11190:
Optics in Health Care and Biomedical Optics IX
Qingming Luo; Xingde Li; Ying Gu; Yuguo Tang; Dan Zhu, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray