1
|
Zhou B, Tong YK, Zhang R, Ye A. RamanNet: a lightweight convolutional neural network for bacterial identification based on Raman spectra. RSC Adv 2022; 12:26463-26469. [PMID: 36275115 PMCID: PMC9478993 DOI: 10.1039/d2ra03722j] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/16/2022] [Accepted: 08/25/2022] [Indexed: 11/21/2022] Open
Abstract
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. We propose a novel CNN model named RamanNet for rapid and accurate identification of bacteria at the species-level based on Raman spectra. Compared to previous CNN methods, the RamanNet reached comparable results on the Bacteria-ID Raman spectral dataset.![]()
Collapse
Affiliation(s)
- Bo Zhou
- School of Science, Beijing University of Posts and Telecommunications, Beijing 100876, China
- Key Laboratory for the Physics and Chemistry of Nanodevices, School of Electronics, Peking University, Beijing 100871, China
| | - Yu-Kai Tong
- Key Laboratory for the Physics and Chemistry of Nanodevices, School of Electronics, Peking University, Beijing 100871, China
| | - Ru Zhang
- School of Science, Beijing University of Posts and Telecommunications, Beijing 100876, China
| | - Anpei Ye
- Key Laboratory for the Physics and Chemistry of Nanodevices, School of Electronics, Peking University, Beijing 100871, China
| |
Collapse
|
5
|
Evangelista EE, França CM, Veni P, de Oliveira Silva T, Gonçalves RM, de Carvalho VF, Deana AM, Fernandes KPS, Mesquita-Ferrari RA, Camacho CP, Bussadori SK, Alvarenga LH, Prates RA. Antimicrobial photodynamic therapy combined with periodontal treatment for metabolic control in patients with type 2 diabetes mellitus: study protocol for a randomized controlled trial. Trials 2015; 16:229. [PMID: 26013003 PMCID: PMC4453758 DOI: 10.1186/s13063-015-0757-3] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/04/2014] [Accepted: 05/13/2015] [Indexed: 01/02/2023] Open
Abstract
Background The relationship between diabetes mellitus (DM) and periodontal disease is bidirectional. DM is a predisposing and modifying factor of periodontitis, which, in turn, worsens glycemic control and increases proteins found in the acute phase of inflammation, such as C-reactive protein. The gold standard for the treatment of periodontal disease is oral hygiene orientation, scaling and planing. Moreover, systemic antibiotic therapy may be employed in some cases. In an effort to minimize the prescription of antibiotics, photodynamic therapy (PDT) has been studied as an antimicrobial technique and has demonstrated promising results. The aim of the proposed study is to determine whether PDT as a complement to periodontal therapy (PT) is helpful in the metabolic control of individuals with type 2 diabetes and the reduction of acute-phase inflammatory markers. Methods/Design The patients will be randomized using a proper software program into two groups: 1) PT + placebo PDT or 2) PT + active PDT. All patients will first be examined by a specialist, followed by PT performed by two other healthcare professionals. At the end of each session, PDT (active or placebo) will be administered by a fourth healthcare professional. The following will be the PDT parameters: diode laser (660 nm); power output = 110 mW; exposure time = 90 s per point (9 J/point); and energy density = 22 J/cm2. The photosensitizer will be methylene blue (50 μg/mL). The patients will be re-evaluated 15, 30, 90 and 180 days after treatment. Serological examinations with complete blood count, fasting glucose, glycated hemoglobin and salivary examinations to screen for tumor necrosis factor alpha, interleukin 1, interleukin 6, ostelocalcin, and osteoprotegerin/RANKL will be performed at each evaluation. The data will be statistically evaluated using the most appropriate tests. Discussion The results of this study will determine the efficacy of photodynamic therapy as an adjuvant to periodontal treatment in diabetic patients. Trial registration The protocol for this trial was registered with Clinical Trials registration number NCT01964833 on 14 October 2013.
Collapse
Affiliation(s)
- Erika Elisabeth Evangelista
- Program in Biophotonics Applied to Health Sciences, University Nove de Julho, UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil.
| | - Cristiane Miranda França
- Program in Biophotonics Applied to Health Sciences, University Nove de Julho, UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil. .,School of Medicine, Nove de Julho University UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil. .,Program in Rehabilitation Science, Nove de Julho University - UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil.
| | - Priscila Veni
- Program in Biophotonics Applied to Health Sciences, University Nove de Julho, UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil. .,School of Dentistry, Nove de Julho University UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil.
| | - Tamires de Oliveira Silva
- Program in Biophotonics Applied to Health Sciences, University Nove de Julho, UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil.
| | - Rafael Moredo Gonçalves
- Program in Biophotonics Applied to Health Sciences, University Nove de Julho, UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil.
| | - Verônica Franco de Carvalho
- School of Dentistry, Nove de Julho University UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil.
| | - Alessandro Melo Deana
- Program in Biophotonics Applied to Health Sciences, University Nove de Julho, UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil.
| | - Kristianne P S Fernandes
- Program in Biophotonics Applied to Health Sciences, University Nove de Julho, UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil. .,School of Dentistry, Nove de Julho University UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil. .,Program in Rehabilitation Science, Nove de Julho University - UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil.
| | - Raquel A Mesquita-Ferrari
- Program in Biophotonics Applied to Health Sciences, University Nove de Julho, UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil. .,School of Medicine, Nove de Julho University UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil. .,Program in Rehabilitation Science, Nove de Julho University - UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil.
| | - Cleber P Camacho
- School of Medicine, Nove de Julho University UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil. .,Medical Sciences, Nove de Julho University - UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil.
| | - Sandra Kalil Bussadori
- Program in Biophotonics Applied to Health Sciences, University Nove de Julho, UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil. .,School of Dentistry, Nove de Julho University UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil. .,Program in Rehabilitation Science, Nove de Julho University - UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil.
| | - Letícia Heineck Alvarenga
- Program in Biophotonics Applied to Health Sciences, University Nove de Julho, UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil.
| | - Renato Araujo Prates
- Program in Biophotonics Applied to Health Sciences, University Nove de Julho, UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil. .,School of Dentistry, Nove de Julho University UNINOVE, Rua Vergueiro 235/249 - Liberdade, São Paulo, SP, 01504-001, Brazil.
| |
Collapse
|