Objectification of evaluation criteria in microscopic agglutination test using deep learning

Risa Nakano; Yuji Oyamada; Ryo Ozuru; Michinobu Yoshimura; Kenji Hiromatsu

doi:10.1016/j.mimet.2024.106955

Objectification of evaluation criteria in microscopic agglutination test using deep learning

J Microbiol Methods. 2024 May 14:222:106955. doi: 10.1016/j.mimet.2024.106955. Online ahead of print.

Authors

Risa Nakano¹, Yuji Oyamada², Ryo Ozuru³, Michinobu Yoshimura⁴, Kenji Hiromatsu⁴

Affiliations

¹ Graduate School of Engineering, Tottori University, Japan.
² Graduate School of Engineering, Tottori University, Japan. Electronic address: oyamada@tottori-u.ac.jp.
³ Department of Microbiology & Immunology, Faculty of Medicine, Fukuoka University, Japan. Electronic address: ozuru@fukuoka-u.ac.jp.
⁴ Department of Microbiology & Immunology, Faculty of Medicine, Fukuoka University, Japan.

PMID: 38754481
DOI: 10.1016/j.mimet.2024.106955

Abstract

We aim to objectify the evaluation criteria of agglutination rate estimation in the Microscopic Agglutination Test (MAT). This study proposes a deep learning method that extracts free leptospires from dark-field microscopic images and calculates the agglutination rate. The experiments show the effect of objectification with real pictures.

Keywords: Agglutination test; Artificial intelligence; Deep learning; Leptospira; Leptospirosis; Machine learning.