Colonoscopy is regarded as the gold standard in colorectal tumor diagnosis, but it is costly and time-consuming. Raman spectroscopy has shown promise for differentiating cancerous from non-cancerous tissue and is expected to be a new tool for oncological diagnosis. However, traditional Raman spectroscopy analysis requires tedious preprocessing, and the classification accuracy needs to be improved. In this work, a novel Raman spectral qualitative classification method based on convolutional neural network (CNN) is proposed for the identification of three different colon tissue samples, including adenomatous polyp, adenocarcinoma and normal tissues. Experimental results show that this CNN model has superior feature extraction ability. For the spectral data of new individuals, the trained CNN model presents much better classification performance than traditional machine learning methods, such as the k-nearest neighbor, random forest, and support vector machine. Raman spectroscopy combined with CNN can be used as an effective auxiliary tool for the early diagnosis of colon cancer.
Micro/nano hierarchical substrates with different micropillar spacings were designed and prepared for capture of tumor cells. The cell capture efficiency of hierarchical substrates with low-density micropillar arrays was similar to that of nanostructured substrate. Increasing the density of micopillars could significantly improve the capture efficiency. The maximum capture efficiency was achieved on the hierarchical substrate with micropillar spacings of 15 μm, but further reducing the micropillar spacings did not increase the cell capture efficiency. It was also found that hierarchical substrates with appropriate spacing of micropillars appeared more favorable for cell attachment and spreading, and thus enhancing the cell-material interaction. These results suggested that optimizing the micropillar arrays, such as the spacing between adjacent micropillars, could give full play to the synergistic effect of hierarchical hybrid micro/nanostructures in the interaction with cells. This study may provide promising guidance to design and optimize micro/nano hierarchical structures of biointerfaces for biomedical application.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.