Freeze–Thaw Imaging for Microorganism Classification Assisted with Artificial Intelligence

Fast and cost-effective microbial classification is crucial
for
clinical diagnosis, environmental monitoring, and food safety. However,
traditional methods encounter challenges including intricate procedures,
skilled personnel needs, and sophisticated instrumentations. Here,
we propose a cost-effective microbe classification system, also termed
freeze–thaw-induced floating pattern of AuNPs (FTFPA), coupled
with artificial intelligence, which is capable of identifying microbes
at a cost of $0.0023 per sample. Specifically, FTFPA utilizes AuNPs
for coincubation with microbes, resulting in distinct patterns upon
freeze–thawing due to their weak interaction. These patterns
are digitized to train models that distinguish nine microbes in various
tasks. The positive sample detection model achieved an F1 score of
0.976 (n = 194), while the multispecies classification
task reached a macro F1 score of 0.859 (n = 1728).
To address scalability and lightweight requirements across diverse
classification scenarios, we categorized microbes based on species
classification levels. The macro F1 score of the hierarchical model
(n = 5184), order level model (n = 5184), Enterobacteriales level model (n = 2550),
and Bacillales level model (n = 1974) was 0.854,
0.907, 0.958, and 0.843. In summary, our method is user-friendly,
requiring only simple equipment, is easy to operate, and convenient,
providing a platform for microbial identification.