Intelligent convolution neural network-assisted SERS to realize highly accurate identification of six pathogenic Vibrio .
Hui YuZhilan YangShiying FuYuejiao ZhangRajapandiyan PanneerselvamcBaoqiang LiLin ZhangZehui ChenXin WangJian-Feng LiPublished in: Chemical communications (Cambridge, England) (2023)
Based on label-free SERS technology, the relationship between the Raman signals of pathogenic Vibrio microorganisms and purine metabolites was analyzed in detail. A deep learning CNN model was successfully developed, achieving a high accuracy rate of 99.7% in the identification of six typical pathogenic Vibrio species within 15 minutes, providing a new method for pathogen identification.