Accurate screening of early‐stage lung cancer based on improved ResNeXt model combined with serum Raman spectroscopy. (26th April 2022)

• Record Type: Journal Article
• Authors: Leng, Hongyong; Chen, Cheng; Si, Rumeng; Chen, Chen; Qu, Hanwen; Lv, Xiaoyi
• Is Part Of: Journal of Raman spectroscopy. Volume 53:Number 7(2022)
• Page Start: 1302
• Page End: 1311
• Publication Date: 2022-04-26
• Subjects: deep learning -- early‐stage lung cancer -- improved ResNeXt model -- serum Raman spectroscopy; Raman spectroscopy -- Periodicals; 535.846
• DOI: 10.1002/jrs.6365
• Languages: English
• ISSNs: 0377-0486

Abstract

Abstract: Screening and diagnosis of early‐stage lung cancer is low worldwide, and when lung cancer progresses to late stage, it will greatly affect the treatment and survival time of patients. Therefore, the development of an affordable and accurate diagnostic technique is critical for lung cancer patients. In this study, we analyzed and verified the changes of substance composition in the serum of early‐stage lung cancer patients and proposed an improved ResNeXt model to achieve accurate classification of serum Raman spectra of lung cancer. The robustness of the model is improved by adding different decibels of Gaussian white noise and spectral offset to augment the data, trying to process the augmented data with various pre‐processing methods, and inputting the pre‐processed data into the improved ResNeXt model, the improved ResNeXt model still shows the optimal performance after sufficient comparison experiments with three other more advanced deep learning models. The experimental results show that the improved ResNeXt model is very suitable for the classification of early‐stage lung cancer serum Raman spectra and may provide a reference for future early screening studies of other cancers. Abstract : In this study, we propose an improved ResNeXt model to achieve accurate classification of serum Raman spectra of lung cancer. We augmented the training set to improve the robustness of the lung cancer diagnostic model. In order to improve the validity of the data, we try to preprocess the augmented data with standard normal variate transformation (SNV), first‐order derivative (1d), and their combination (SNV + 1d) respectively. Then, the above data are imported into the ResNeXt model proposed in this paper and are fully compared with the three deep learning models of AlexNet, SqueezeNet, and ResNet in the experiments. The experimental results show that the improved ResNeXt model combined with serum Raman spectroscopy proposed in this study has great potential for accurate screening of early‐stage lung cancer and has implications for early clinical diagnosis of other cancers.