Minimally Invasive, Label-Free, Point-of-Care Histopathological Diagnostic Platform of Malignant Tumors of the Female Reproductive System Based on Raman Spectroscopy and Machine Learning

The Journal of Physical Chemistry Letters 2026

View at publisher
Authors: Liangliang Jiang, Siqi Gong, Zibo Gao, Xinyu Yao, Chaochao Ma, Yaowen Xing, Liping Zhou, Jin Sun, Jing Wu, Yingji Wang, Jing Wang, Jian‐An Huang
+3 more Yanli Wu, Sijia Liu, Yang Li
DOI: 10.1021/acs.jpclett.5c03704
Cited by: 0
References: 52

Abstract

Fast intraoperative histopathology is critical for optimal surgery in ovarian, endometrial and cervical cancers, yet frozen-section pathology is slow and resource-intensive. We obtained 4750 Raman spectra from 85 human gynecological tissue specimens spanning 19 histopathological classes. Spectra were preprocessed and classified with five machine-learning algorithms; performance was assessed by stratified train-test splits (70%:30%). Support-vector machines achieved 100% accuracy (AUC = 1.00) across all classes, outperforming random forest (96-99%) and k-nearest-neighbor (97-99%). Single-spectra acquisition required 30 s and automated prediction

Fields of Study & Subjects

Spectroscopy Techniques in Biomedical and Chemical Research AI in cancer detection Molecular Biology Techniques and Applications

Publication details

Journal / source
The Journal of Physical Chemistry Letters
Volume
17
Issue
2
Pages
587–597
Publication date
5 January 2026
Language
EN