Leptospirosis is a zoonosis caused by the pathogenic bacterium Leptospira. The Microscopic Agglutination Test (MAT) is widely used as the gold standard for diagnosis of leptospirosis. In this method, diluted patient serum is mixed with serotype-determined Leptospiras, and the presence or absence of aggregation is determined under a dark-field microscope to calculate the antibody titer. Problems of the current MAT method are 1) a requirement of examining many specimens per sample, and 2) a need of distinguishing contaminants from true aggregates to accurately identify positivity. Therefore, increasing efficiency and accuracy are the key to refine MAT. It is possible to achieve efficiency and standardize accuracy at the same time by automating the decision making process.
We are working on building an automatic identification algorithm of MAT using a machine learning method to determine aggregation within microscopic images.
Please contact me if you want any pre-prints.
Yuji Oyamada, Ryo Ozuru, Toshiyuki Masuzawa, Satoshi Miyahara, Yasuhiko Nikaido, Fumiko Obata, Mitsumasa Saito, Sharon Yvette Angelina M. Villanueva, Jun Fujii, "A Machine Learning Approach Towards Standardizing Microscopic Agglutination Test for Diagnosis of Leptospirosis," bioRxiv, Dec., 2020.
Yuji Oyamada, Yasuhiko Nikaido, Satoshi Miyahara, Mitsumasa Saito, Sharon Villanueva, Toshiyuki Masuzawa, Ryo Ozuru, "サポートベクターマシンを用いた顕微鏡下凝集試験 (MAT) の自動化 ," 日本バイオインフォマティクス学会年会, Sep. 2020.
Yuji Oyamada, Sharon Y.A.M. Villanueva, Ryo Ozuru, "An Artificial Intelligence Approach Towards a Computer-Aided Microscopic Agglutination Test ," International Leptospirosis Conference, Jul., 2019.
尾鶴 亮, 小山田 雄仁, "顕微鏡下凝集試験(MAT)の自動化を目指した機械学習モデルの構築," 第56回レプトスピラ・シンポジウム, Apr., 2019.
ポスター賞 (2020年日本バイオインフォマティクス学会年会・第9回生命医薬情報学連合大会)