Detection of pancreatic cancer by convolutional-neural-network-assisted spontaneous Raman spectroscopy with critical feature visualization

• Published in: Neural networks Vol. 144; pp. 455 - 464
• Main Authors: Li, Zhongqiang, Li, Zheng, Chen, Qing, Ramos, Alexandra, Zhang, Jian, Boudreaux, J. Philip, Thiagarajan, Ramcharan, Bren-Mattison, Yvette, Dunham, Michael E., McWhorter, Andrew J., Li, Xin, Feng, Ji-Ming, Li, Yanping, Yao, Shaomian, Xu, Jian
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.12.2021
• Subjects: Convolutional neural network; Deep learning; Lab-designed hand-held Raman spectroscopic system; Pancreatic cancer; Spontaneous Raman spectroscopy; Deep learning; Spontaneous Raman spectroscopy; Lab-designed hand-held Raman spectroscopic system; Pancreatic cancer; Convolutional neural network
• ISSN: 0893-6080; 1879-2782
• DOI: 10.1016/j.neunet.2021.09.006

Pancreatic cancer is the deadliest cancer type with a five-year survival rate of less than 9%. Detection of tumor margins plays an essential role in the success of surgical resection. However, histopathological assessment is time-consuming, expensive, and labor-intensive. We constructed a lab-designed, hand-held Raman spectroscopic system that could enable intraoperative tissue diagnosis using convolutional neural network (CNN) models to efficiently distinguish between cancerous and normal pancreatic tissue. To our best knowledge, this is the first reported effort to diagnose pancreatic cancer by CNN-aided spontaneous Raman scattering with a lab-developed system designed for intraoperative applications. Classification based on the original one-dimensional (1D) Raman, two-dimensional (2D) Raman images, and the first principal component (PC1) from the principal component analysis on the 2D image, could all achieve high performance: the testing sensitivity, specificity, and accuracy were over 95%, and the area under the curve approached 0.99. Although CNN models often show great success in classification, it has always been challenging to visualize the CNN features in these models, which has never been achieved in the Raman spectroscopy application in cancer diagnosis. By studying individual Raman regions and by extracting and visualizing CNN features from max-pooling layers, we identified critical Raman peaks that could aid in the classification of cancerous and noncancerous tissues. 2D Raman PC1 yielded more critical peaks for pancreatic cancer identification than that of 1D Raman, as the Raman intensity was amplified by 2D Raman PC1. To our best knowledge, the feature visualization was achieved for the first time in the field of CNN-aided spontaneous Raman spectroscopy for cancer diagnosis. Based on these CNN feature peaks and their frequency at specific wavenumbers, pancreatic cancerous tissue was found to contain more biochemical components related to the protein contents (particularly collagen), whereas normal pancreatic tissue was found to contain more lipids and nucleic acid (particularly deoxyribonucleic acid/ribonucleic acid). Overall, the CNN model in combination with Raman spectroscopy could serve as a useful tool for the extraction of key features that can help differentiate pancreatic cancer from a normal pancreas.