Baseline correction using a deep-learning model combining ResNet and UNet

2022/01/01 by Tiejun Chen, YoungJae Son, Aaron Park +2 · 13 citations
Biochemistry, Genetics and Molecular Biology · Chemistry · Engineering · #Artificial intelligence #Baseline (sea) #Computer science #Deep learning #Fault Detection and Control Systems #Machine learning #Optics #Pattern recognition (psychology) #Physics #Raman spectroscopy #Spectroscopy Techniques in Biomedical and Chemical Research #Spectroscopy and Chemometric Analyses

paper · doi:10.1039/d2an00868h

openalex publication_date 2022/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/26

Abstract

infrared, Raman, and mass spectroscopy, have baseline drifts due to fluorescence or other reasons, which have an adverse impact on subsequent analyses. Therefore, several researchers have proposed the use of various baseline-correction methods to address the aforementioned issue. However, most baseline-correction methods require manual adjustment of the parameters to achieve desirable performance. In this study, we propose a baseline-correction method based on a deep-learning model that combines ResNet and UNet. The method uses a deep-learning model trained with simulated spectral data to perform baseline corrections and eliminates the need for manual parameter adjustments. Based on the results of the qualitative and quantitative analyses of the simulated spectral data and actual Raman spectra, the proposed method is easier to apply and has better performance compared to the existing methods. As the proposed method can be applied to Raman spectra and other spectra, it is expected to be widely used.

Cited by

• AirNet: A Deep Learning-Driven Auto Baseline Correction Algorithm Balancing Global Smoothness and Local Fidelity
• GLASSR-Net: Glass Substrate Spectral Restoration Neural Network for Fourier Transform Infrared Microspectroscopy in the Fingerprint Region
• Experimental validation result for OASIS software
• Fully Automated Skull Stripping from Brain Magnetic Resonance Images Using Mask RCNN-Based Deep Learning Neural Networks. [europepmc]
• Library-Based Raman Spectral Identification Using Multi-Input Hybrid ResNet. [europepmc]
• CT image segmentation of meat sheep Loin based on deep learning. [europepmc]
• RSPSSL: A novel high-fidelity Raman spectral preprocessing scheme to enhance biomedical applications and chemical resolution visualization. [europepmc]
• Artifacts and Anomalies in Raman Spectroscopy: A Review on Origins and Correction Procedures. [europepmc]
• A review on spectral data preprocessing techniques for machine learning and quantitative analysis. [europepmc]
• U-ResNet, a Novel Network Fusion Method for Image Classification and Segmentation. [europepmc]
• RamEx: an R package for high-throughput microbial ramanome analyses with accurate quality assessment. [europepmc]
• Adaptive Multi-Order Penalty and Dual-Driven Weighting: aisPLS Algorithm for Raman Baseline Correction with Weak Peak Preservation. [europepmc]
• Automated Baseline Correction Evaluation Score for Raman Spectroscopy. [europepmc]

Related

• AirNet: A Deep Learning-Driven Auto Baseline Correction Algorithm Balancing Global Smoothness and Local Fidelity
• Refinement of spectra using a deep neural network: Fully automated removal of noise and background
• Supervised and Penalized Baseline Correction
• One-dimensional Active Contour Models for Raman Spectrum Baseline Correction
• Morphology-Enhanced Rolling Ball Algorithm for Baseline Removal