Search

The success of a Raman spectroscopy device in cancer detection lies in its ability to acquire high‐quality Raman signals from samples and to employ efficient classification algorithms in analysing spectral data. Portable Raman systems enabled with artificial intelligence tools are well adaptable to clinical settings and for accuracy for community‐level rapid screening. Here, we developed a robotic Raman device with a high‐efficiency Raman probe, validating it against endometrial cancers detecting high‐grade, low‐grade cancers and normal classes. Algorithms like principal component analysis‐discriminant analysis, and support vector machine were compared against the deep learning methodology; convolutional neural network (CNN) with and without data augmentation. Eventually, the system could classify high‐grade, low‐grade and normal tissues with an F1‐score of 91%, 94% and 97%, respectively. CNN with data augmentation proved to be the most dependable classifier that works well even in the presence of high background noise. Thus, we demonstrate a unique portable Raman device with AI tools for high‐sensitivity Raman analysis of endometrial cancer. [ABSTRACT FROM AUTHOR]

The differentiation of skin melanomas and basal cell carcinomas (BCCs) was demonstrated based on combined analysis of Raman and autofluorescence spectra stimulated by visible and NIR lasers. It was ex vivo tested on 39 melanomas and 40 BCCs. Six spectroscopic criteria utilizing information about alteration of melanin, porphyrins, flavins, lipids, and collagen content in tumor with a comparison to healthy skin were proposed. The measured correlation between the proposed criteria makes it possible to define weakly correlated criteria groups for discriminant analysis and principal components analysis application. It was shown that the accuracy of cancerous tissues classification reaches 97.3% for a combined 6-criteria multimodal algorithm, while the accuracy determined separately for each modality does not exceed 79%. The combined 6-D method is a rapid and reliable tool for malignant skin detection and classification. [ABSTRACT FROM AUTHOR]

Ebony (Diospyros celebica Bakh.) is an endemic plant on Celebes (Sulawesi) island. Extractive compounds within ebony wood cause it to have durability, strength, and beautiful patterns. In this study, we used near-infrared (NIR) spectroscopy to discriminate between ebony wood samples, based on their origins at different growth sites on Celebes island, and to develop quantitative models to predict the extractive content of ebony wood. A total of 45 wood meal samples from 11 sites located in West, Central, and South Celebes were collected in this study. NIR spectral data were acquired from hot water and ethanol–benzene soluble extracts from ebony wood in this study. The extractive content of the ebony was 10.408% and 10.774% based on hot water solubility and treatment with ethanol–benzene solvent, respectively. Multivariate analysis based on principal component analysis–discriminant analysis revealed that ebony wood from West Celebes differed from most of the wood from South Celebes; however, it was only slightly different from ebony wood from Central Celebes based on NIR spectra data. These findings were in line with the extractive contents obtained. Partial least square regression models based on wood meal spectra could potentially be used to estimate the hot water and ethanol–benzene extractive contents from ebony wood. [ABSTRACT FROM AUTHOR]