RamanNet: a lightweight convolutional neural network for bacterial identification based on Raman spectra.

Autor:	Zhou B; School of Science, Beijing University of Posts and Telecommunications Beijing 100876 China ruzhang@bupt.edu.cn.; Key Laboratory for the Physics and Chemistry of Nanodevices, School of Electronics, Peking University Beijing 100871 China yap@pku.edu.cn., Tong YK; Key Laboratory for the Physics and Chemistry of Nanodevices, School of Electronics, Peking University Beijing 100871 China yap@pku.edu.cn., Zhang R; School of Science, Beijing University of Posts and Telecommunications Beijing 100876 China ruzhang@bupt.edu.cn., Ye A; Key Laboratory for the Physics and Chemistry of Nanodevices, School of Electronics, Peking University Beijing 100871 China yap@pku.edu.cn.
Jazyk:	angličtina
Zdroj:	RSC advances [RSC Adv] 2022 Sep 16; Vol. 12 (40), pp. 26463-26469. Date of Electronic Publication: 2022 Sep 16 (Print Publication: 2022).
DOI:	10.1039/d2ra03722j
Abstrakt:	Raman spectroscopy combined convolutional neural network (CNN) enables rapid and accurate identification of the species of bacteria. However, the existing CNN requires a complex hyperparameters model design. Herein, we propose a new simple network architecture with less hyperparameter design and low computation cost, RamanNet, for rapid and accurate identifying of bacteria at the species level based on its Raman spectra. We verified that compared with the previous CNN methods, the RamanNet reached comparable results on the Bacteria-ID Raman spectral dataset and PKU-bacterial Raman spectral datasets, but using only about 1/45 and 1/297 network parameters, respectively. RamanNet achieved an average isolate-level accuracy of 84.7 ± 0.3%, antibiotic treatment identification accuracy of 97.1 ± 0.3%, and distinguished accuracy of 81.6 ± 0.9% for methicillin-resistant and -susceptible Staphylococcus aureus (MRSA and MSSA) on the Bacteria-ID dataset, respectively. Moreover, it achieved an average accuracy of 96.04% on the PKU-bacterial dataset. The RamanNet model benefited from fewer model parameters that can be quickly trained even using CPU. Therefore, our method has the potential to rapidly and accurately identify bacterial species based on their Raman spectra and can be easily extended to other classification tasks based on Raman spectra. Competing Interests: There are no conflicts to declare. (This journal is © The Royal Society of Chemistry.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu