Machine learning using convolutional neural networks for SERS analysis of biomarkers in medical diagnostics

• Published in: Journal of Raman spectroscopy Vol. 53; no. 12; pp. 2044 - 2057
• Main Authors: Li, Joy Qiaoyi, Dukes, Priya Vohra, Lee, Walter, Sarkis, Michael, Vo‐Dinh, Tuan
• Format: Journal Article
• Language: English
• Published: England Wiley Subscription Services, Inc 01.12.2022; John Wiley and Sons Inc
• Subjects: Artificial neural networks; Biomarkers; convolutional neural network; Dyes; Head & neck cancer; Learning algorithms; Least squares method; Machine learning; molecular diagnostics; mRNA; multiplexed spectral analysis; Multiplexing; Neural networks; Raman spectroscopy; Regression; Spectra; Spectrum analysis; Support vector machines; surface‐enhanced Raman spectroscopy; multiplexed spectral analysis; molecular diagnostics; surface‐enhanced Raman spectroscopy; machine learning; convolutional neural network
• ISSN: 0377-0486; 1097-4555; 1097-4555
• DOI: 10.1002/jrs.6447

Surface‐enhanced Raman spectroscopy (SERS) has wide diagnostic applications because of narrow spectral features that allow multiplexed analysis. Machine learning (ML) has been used for non‐dye‐labeled SERS spectra but has not been applied to SERS dye‐labeled materials with known spectral shapes. Here, we compare the performances of spectral decomposition, support vector regression, random forest regression, partial least squares regression, and convolutional neural network (CNN) for SERS “spectral unmixing” from a multiplexed mixture of 7 SERS‐active “nanorattles” loaded with different dyes for mRNA biomarker detection. We showed that CNN most accurately determined relative contributions of each distinct dye‐loaded nanorattle. CNN and comparative models were then used to analyze SERS spectra from a singleplexed, point‐of‐care assay detecting an mRNA biomarker for head and neck cancer in 20 samples. The CNN, trained on simulated multiplexed data, determined the correct dye contributions from the singleplex assay with RMSElabel = 6.42 × 10−2. These results demonstrate the potential of CNN‐based ML to advance SERS‐based diagnostics. We compared the performances of spectral decomposition, support vector regression, random forest regression, partial least squares regression, and convolutional neural network for SERS “spectral unmixing” from a multiplexed mixture of 7 SERS‐active “nanorattles” loaded with different dyes for mRNA biomarker detection. These models were then used to analyze SERS spectra from a singleplexed, point‐of‐care assay detecting an mRNA biomarker for head and neck cancer in 20 samples.