Interpretable Wavelet-CNN for Accurate Serum Raman Lung Cancer Diagnosis under Leakage-Safe, Patient-Level Splits
(tryptophan). These spectral features correspond to molecules with established roles in cancer metabolism. This demonstration that CWT-CNN maintains high accuracy under biological variability and leakage-safe, patient-level validation, combined with biochemically meaningful feature attribution, establishes a data-first approach where comprehensive spectral analysis enables both diagnostic accuracy and identification of disease-relevant molecular features.
Authors
- Yusong Peng
- Christopher J. Butch (ORCID: https://orcid.org/0000-0003-3112-0470)
- Shuming Nie (ORCID: https://orcid.org/0000-0002-7328-1144)
- Jinglei Zhang
- Lingyun Gu
- Yong Zhou
- Dong Han
- Bo Dai
- Hong Wang
- Chenmei Li
- Yiqing Wang (ORCID: https://orcid.org/0000-0002-5626-8589)
- Weishu Gao
Institutions
- Singapore University of Technology and Design (SG)
- University of Illinois Urbana-Champaign (US)
- Nanjing Drum Tower Hospital (CN)
- NOAA National Ice Center (US)
- Second Affiliated Hospital of Nanjing Medical University (CN)
- Pillar College (US)
- Nanjing University (CN)
Publication Details
- Journal
- Analytical Chemistry
- Published
- 2026-04-20
- DOI
- https://doi.org/10.1021/acs.analchem.5c06703
- Primary Topic
- Spectroscopy Techniques in Biomedical and Chemical Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Ministry of Science and Technology of the People's Republic of China
- Jiangsu Science and Technology Department
- Fundamental Research Funds for the Central Universities