Share Email Print
cover

Proceedings Paper

Deep learning enables high-throughput early detection and classification of bacterial colonies using time-lapse coherent imaging (Conference Presentation)

Paper Abstract

We report a highly-sensitive, high-throughput, and cost-effective bacteria identification system which continuously captures and reconstructs holographic images of an agar-plate and analyzes the time-lapsed images with deep learning models for early detection of colonies. The performance of our system was confirmed by detection and classification of Escherichia coli, Enterobacter aerogenes, and Klebsiella pneumoniae in water samples. We detected 90% of the bacterial colonies and their growth within 7-10h (>95% within 12h) with ~100% precision, and correctly identified the corresponding species within 7.6-12h with 80% accuracy, and achieved time savings of >12h as compared to the gold-standard EPA-approved methods.

Paper Details

Date Published: 9 March 2020
PDF
Proc. SPIE 11230, Optics and Biophotonics in Low-Resource Settings VI, 112300E (9 March 2020); doi: 10.1117/12.2547399
Show Author Affiliations
Hongda Wang, Univ. of California, Los Angeles (United States)
Hatice C. Koydemir, Univ. of California, Los Angeles (United States)
Yunzhe Qiu, Univ. of California, Los Angeles (United States)
Bijie Bai, Univ. of California, Los Angeles (United States)
Yibo Zhang, Univ. of California, Los Angeles (United States)
Yiyin Jin, Univ. of California, Los Angeles (United States)
Sabiha Tok, Univ. of California, Los Angeles (United States)
Enis C. Yilmaz, Bahçesehir Univ. (Turkey)
Esin Gumustekin, Univ. of California, Los Angeles (United States)
Yilin Luo, Univ. of California, Los Angeles (United States)
Yair Rivenson, Univ. of California, Los Angeles (United States)
Aydogan Ozcan, Univ. of California, Los Angeles (United States)


Published in SPIE Proceedings Vol. 11230:
Optics and Biophotonics in Low-Resource Settings VI
David Levitz; Aydogan Ozcan, 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