Optical flow reveals motility signatures for inferring pathogenic bacterial mixture compositions via temporal convolutional networks
Yuki Fujita, Yuki Nagase, Sarthak Pathak, Alessandro Moro, Hiroaki Suzuki, Keiichiro Koiwai, Kazunori Umeda
The paper uses temporal convolutional networks to classify bacterial mixture compositions from motion features in microscopy videos, achieving 93.3% accuracy without fluorescent labeling.
bioRxiv · Jun 29, 2026 · PreprintMicrobiology