Biochemical differentiation between cancerous and normal human colorectal tissues by micro-Raman spectroscopy

• Published in: Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy Molecular and biomolecular spectroscopy, 2023-10, Vol.299, p.122852, Article 122852
• Main Authors: Karnachoriti, M., Stathopoulos, I., Kouri, M., Spyratou, E., Orfanoudakis, S., Lykidis, D., Lambropoulou, Μ., Danias, N., Arkadopoulos, N., Efstathopoulos, E.P., Raptis, Y.S., Seimenis, I., Kontos, A.G.
• Format: Article
• Language: English
• Subjects: Colorectal cancer; Human colon tissues; K-means clustering; Machine learning; Principal component analysis; Raman spectroscopy
• ISSN: 1386-1425
• DOI: 10.1016/j.saa.2023.122852

[Display omitted] •785 nm micro-Raman analysis of colorectal tissues from ten cancer patients.•Clustering in 5 Tissue Spectral Profiles: typical, fat, lipid/blood/collagen-rich.•Cancer tissues present uniform spectroscopic characteristics and normal diverse.•81% accuracy in normal/cancerous tissues classification by tree-based ML algorithm.•Biochemical changes evidenced in cancer by Raman are due to collagen and proteins. Human colorectal tissues obtained by ten cancer patients have been examined by multiple micro-Raman spectroscopic measurements in the 500–3200 cm−1 range under 785 nm excitation. Distinct spectral profiles are recorded from different spots on the samples: a predominant ‘typical’ profile of colorectal tissue, as well as those from tissue topologies with high lipid, blood or collagen content. Principal component analysis identified several Raman bands of amino acids, proteins and lipids which allow the efficient discrimination of normal from cancer tissues, the first presenting plurality of Raman spectral profiles while the last showing off quite uniform spectroscopic characteristics. Tree-based machine learning experiment was further applied on all data as well as on filtered data keeping only those spectra which characterize the largely inseparable data clusters of ‘typical’ and ‘collagen-rich’ spectra. This purposive sampling evidences statistically the most significant spectroscopic features regarding the correct identification of cancer tissues and allows matching spectroscopic results with the biochemical changes induced in the malignant tissues.