Classification of Vaginal Cleanliness Grades through Surface‐Enhanced Raman Spectral Analysis via The Deep‐Learning Variational Autoencoder–Long Short‐Term Memory Model

作者：Jia‐Wei Tang, Xin‐Ru Wen, Huimin Chen, Jie Chen, Kevin Hong, Quan Yuan, Muhammad Usman, Liang Wang · 发表于：Advanced Intelligent Systems · 年份：2024 · DOI：10.1002/aisy.202470059 · 被引用次数：5 · 研究领域：Face recognition and analysis、Textile materials and evaluations、Spectroscopy Techniques in Biomedical and Chemical Research

Deep-Learning-Guided Surface-Enhanced Raman Spectroscopy In article number 2400587, Muhammad Usman, Liang Wang, and co-workers present a novel approach combining deep-learning-guided surface-enhanced Raman spectroscopy (SERS) and a variational autoencoder (VAE) with a long short-term memory (LSTM) neural network to classify vaginal cleanliness levels rapidly and accurately. Enhanced spectral quality and an optimized VAE–LSTM model yielded an 85% accuracy on blind test data. This method, which improves signal-to-noise ratios and diagnostic efficiency, shows strong potential for clinical applications in assessing vaginal cleanliness through SERS analysis of vaginal secretions.