Automatic detection of leukemia cells by 2D light scattering microfluidic cytometry and deep learning

Jing Sun; Lan Wang; Qiao Liu; Xuantao Su

doi:10.1117/12.2537094

20 November 2019 Automatic detection of leukemia cells by 2D light scattering microfluidic cytometry and deep learning

Jing Sun, Lan Wang, Qiao Liu, Xuantao Su

Proceedings Volume 11190, Optics in Health Care and Biomedical Optics IX; 111901T (2019) https://doi.org/10.1117/12.2537094
Event: SPIE/COS Photonics Asia, 2019, Hangzhou, China

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.

Citation Download Citation

Jing Sun, Lan Wang, Qiao Liu, and Xuantao Su "Automatic detection of leukemia cells by 2D light scattering microfluidic cytometry and deep learning", Proc. SPIE 11190, Optics in Health Care and Biomedical Optics IX, 111901T (20 November 2019); https://doi.org/10.1117/12.2537094

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available