RSPSSL: A novel high-fidelity Raman spectral preprocessing scheme to enhance biomedical applications and chemical resolution visualization

Hu，Jiaqi1; Chen，Gina Jinna1; Xue，Chenlong1; Liang，Pei2; Xiang，Yanqun3; Zhang，Chuanlun4; Chi，Xiaokeng5; Liu，Guoying3; Ye，Yanfang6; Cui，Dongyu4; Zhang，De2; yu，Xiaojun7; Dang，Hong1; Zhang，Wen1; Chen，Junfan1; Tang，Quan1; Guo，Penglai1; Ho，Ho Pui8; Li，Yuchao9; Cong，Longqing1; Shum，Perry Ping1

2024-12-01

10.1038/s41377-024-01394-5

Light: Science and Applications   影响因子和分区

2095-5545

2047-7538

Raman spectroscopy has tremendous potential for material analysis with its molecular fingerprinting capability in many branches of science and technology. It is also an emerging omics technique for metabolic profiling to shape precision medicine. However, precisely attributing vibration peaks coupled with specific environmental, instrumental, and specimen noise is problematic. Intelligent Raman spectral preprocessing to remove statistical bias noise and sample-related errors should provide a powerful tool for valuable information extraction. Here, we propose a novel Raman spectral preprocessing scheme based on self-supervised learning (RSPSSL) with high capacity and spectral fidelity. It can preprocess arbitrary Raman spectra without further training at a speed of ~1 900 spectra per second without human interference. The experimental data preprocessing trial demonstrated its excellent capacity and signal fidelity with an 88% reduction in root mean square error and a 60% reduction in infinite norm (L) compared to established techniques. With this advantage, it remarkably enhanced various biomedical applications with a 400% accuracy elevation (ΔAUC) in cancer diagnosis, an average 38% (few-shot) and 242% accuracy improvement in paraquat concentration prediction, and unsealed the chemical resolution of biomedical hyperspectral images, especially in the spectral fingerprint region. It precisely preprocessed various Raman spectra from different spectroscopy devices, laboratories, and diverse applications. This scheme will enable biomedical mechanism screening with the label-free volumetric molecular imaging tool on organism and disease metabolomics profiling with a scenario of high throughput, cross-device, various analyte complexity, and diverse applications.

SCI

英语

第一 ; 通讯

2-s2.0-85185454763

Scopus

1.State Key Laboratory of Optical Fiber and Cable Manufacture Technology,Guangdong Key Laboratory of Integrated Optoelectronics Intellisense,Department of EEE,Southern University of Science and Technology,Shenzhen,518055,China
2.College of Optical and Electronic Technology,China Jiliang University,Hangzhou,310018,China
3.Department of Nasopharyngeal Carcinoma,Sun Yat-sen University Cancer Center,State Key Laboratory of Oncology in South China,Collaborative Innovation Center for Cancer Medicine,Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy,Guangzhou,510060,China
4.Department of Ocean Science and Engineering,Southern University of Science and Technology,Shenzhen,518055,China
5.Department of Nephrology,Chaozhou People’s Hospital,Chaozhou,521011,China
6.Clinical Research Design Division,Sun Yat-sen Memorial Hospital,Guangzhou,Guangdong,510120,China
7.School of Automation,Northwestern Polytechnical University,Xi’an,Shaanxi,710072,China
8.Department of Biomedical Engineering,The Chinese University of Hong Kong,Hong Kong
9.Guangdong Provincial Key Laboratory of Nanophotonic Manipulation,Institute of Nanophotonics,Jinan University,Guangzhou,511443,China

Hu，Jiaqi,Chen，Gina Jinna,Xue，Chenlong,et al. RSPSSL: A novel high-fidelity Raman spectral preprocessing scheme to enhance biomedical applications and chemical resolution visualization[J]. Light: Science and Applications,2024,13(1).

Hu，Jiaqi.,Chen，Gina Jinna.,Xue，Chenlong.,Liang，Pei.,Xiang，Yanqun.,...&Shum，Perry Ping.(2024).RSPSSL: A novel high-fidelity Raman spectral preprocessing scheme to enhance biomedical applications and chemical resolution visualization.Light: Science and Applications,13(1).

Hu，Jiaqi,et al."RSPSSL: A novel high-fidelity Raman spectral preprocessing scheme to enhance biomedical applications and chemical resolution visualization".Light: Science and Applications 13.1(2024).