Raman Spectral Feature Enhancement Framework for Complex Multiclassification Tasks

Abstract

Raman spectroscopy enables label-free clinical diagnosis in a single step. However, identifying an individual carrying a specific disease from people with a multi-disease background is challenging. To address this, we developed a Raman spectral implicit feature augmentation with a Raman Intersection, Union, and Subtraction augmentation strategy (RIUS). RIUS expands the data set without requiring additional labeled data by leveraging set operations at the feature level, significantly enhancing model performance across various applications. On a challenging 30-class bacterial classification task, RIUS demonstrated a substantial improvement, increasing the accuracy of ResNet by 2.1% and that of SE-ResNet by 1.4%, achieving accuracies of 85.7% and 87.1%, respectively, on the Bacteria-ID-4 Data set, where RIUS improved ResNet and SE-ResNet accuracies by 13.6% and 14.5%, respectively, with only ten samples per category. When the sample size was reduced, accuracy gains increased to 31.7% and 38.3%, demonstrating the method’s robustness across different sample volumes. Compared to basic augmentation, our method exhibited superior performance across various sample volumes and demonstrated exceptional adaptability to different levels of complexity. RIUS exhibited superior performance, particularly in complex settings. Moreover, cluster analysis validated the effectiveness of the implicit feature augmentation module and the consistency between theoretical design and experimental results. We further validated our approach using clinical serum samples from 70 breast cancer patients and 70 controls, achieving an AUC of 0.94 and a sensitivity of 92.9%. Our approach enhances the potential for precisely identifying diseases in complex settings and offers plug-and-play enhancement for existing classification models.