Details
| Original language | English |
|---|---|
| Title of host publication | Label-Free Biomedical Imaging and Sensing (LBIS) 2025 |
| Editors | Natan T. Shaked, Oliver Hayden |
| Publisher | SPIE |
| Number of pages | 7 |
| ISBN (electronic) | 9781510684102 |
| Publication status | Published - 19 Mar 2025 |
| Event | SPIE Photonics West BiOS 2025 - San Francisco, United States Duration: 25 Jan 2025 → 31 Jan 2025 |
Publication series
| Name | Progress in Biomedical Optics and Imaging - Proceedings of SPIE |
|---|---|
| Volume | 13331 |
| ISSN (Print) | 1605-7422 |
Abstract
The interaction of commensal and pathogenic bacteria and their contribution to oral biofilm maturation is a central aspect in the development of oral disease. For investigation and monitoring of this process correct estimation of species distribution using fast and precise detection methods is essential. Here, we propose FTIR spectroscopy in combination with a deep learning network to assess the species distribution in unknown mixed oral bacteria samples. The network developed in this work is able to correctly predict ratios of two bacterial species that were previously unknown to the network over a wide range of values with high accuracy. The best performing pre-processing method was determined yielding a root mean square error (RMSE) of 0.014 and showing excellent performance over all species distributions.
Keywords
- deep learning, dental plaque, FTIR spectroscopy, mixed samples, model systems
ASJC Scopus subject areas
- Materials Science(all)
- Electronic, Optical and Magnetic Materials
- Physics and Astronomy(all)
- Atomic and Molecular Physics, and Optics
- Materials Science(all)
- Biomaterials
- Medicine(all)
- Radiology Nuclear Medicine and imaging
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Label-Free Biomedical Imaging and Sensing (LBIS) 2025. ed. / Natan T. Shaked; Oliver Hayden. SPIE, 2025. 1333104 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 13331).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Spectroscopic analysis and classification of oral bacteria in mixed samples using FTIR spectroscopy and deep learning
AU - Frings, Katharina Anna
AU - Baumann, Lars
AU - Heine, Nils
AU - Debener, Nicolas
AU - Bahnemann, Janina
AU - Doll-Nikutta, Katharina
AU - Torres-Mapa, Maria Leilani
AU - Heisterkamp, Alexander
N1 - Publisher Copyright: © 2025 SPIE.
PY - 2025/3/19
Y1 - 2025/3/19
N2 - The interaction of commensal and pathogenic bacteria and their contribution to oral biofilm maturation is a central aspect in the development of oral disease. For investigation and monitoring of this process correct estimation of species distribution using fast and precise detection methods is essential. Here, we propose FTIR spectroscopy in combination with a deep learning network to assess the species distribution in unknown mixed oral bacteria samples. The network developed in this work is able to correctly predict ratios of two bacterial species that were previously unknown to the network over a wide range of values with high accuracy. The best performing pre-processing method was determined yielding a root mean square error (RMSE) of 0.014 and showing excellent performance over all species distributions.
AB - The interaction of commensal and pathogenic bacteria and their contribution to oral biofilm maturation is a central aspect in the development of oral disease. For investigation and monitoring of this process correct estimation of species distribution using fast and precise detection methods is essential. Here, we propose FTIR spectroscopy in combination with a deep learning network to assess the species distribution in unknown mixed oral bacteria samples. The network developed in this work is able to correctly predict ratios of two bacterial species that were previously unknown to the network over a wide range of values with high accuracy. The best performing pre-processing method was determined yielding a root mean square error (RMSE) of 0.014 and showing excellent performance over all species distributions.
KW - deep learning
KW - dental plaque
KW - FTIR spectroscopy
KW - mixed samples
KW - model systems
UR - http://www.scopus.com/inward/record.url?scp=105002579303&partnerID=8YFLogxK
U2 - 10.1117/12.3042855
DO - 10.1117/12.3042855
M3 - Conference contribution
AN - SCOPUS:105002579303
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Label-Free Biomedical Imaging and Sensing (LBIS) 2025
A2 - Shaked, Natan T.
A2 - Hayden, Oliver
PB - SPIE
T2 - SPIE Photonics West BiOS 2025
Y2 - 25 January 2025 through 31 January 2025
ER -