Advancing cancer diagnostics with artificial intelligence and spectroscopy: identifying chemical changes associated with breast cancer

Abstract

Background: Artificial intelligence (AI) and machine learning (ML) approaches in combination with Raman spectroscopy (RS) to obtain accurate medical diagnosis and decision-making is a way forward for understanding not only the chemical pathway to the progression of disease, but also for tailor-made personalized medicine. These processes remove unwanted affects in the spectra such as noise, fluorescence and normalization, and help in the optimization of spectral data by employing chemometrics. Methods: In this study, breast cancer tissues have been analyzed by RS in conjunction with principal component (PCA) and linear discriminate (LDA) analyses. Tissue microarray (TMA) breast biopsies were investigated using RS and chemometric methods and classified breast biopsies into luminal A, luminal B, HER2, and triple negative subtypes. Results: Supervised and unsupervised algorithms were applied on biopsy data to explore intra and inter data set biochemical changes associated with lipids, collagen, and nucleic acid content. LDA predicted specificity accuracy of luminal A, luminal B, HER2, and triple negative subtypes were 70%, 100%, 90%, and 96.7%, respectively. Conclusion: It is envisaged that a combination of RS with AI and ML may create a precise and accurate real-time methodology for cancer diagnosis and monitoring. ARTICLE HISTORY

Raman spectral discrimination in human liquid biopsies of oesophageal transformation to adenocarcinoma

“…Ribose sugars are precursors to biosynthetic pathways generated by the Warburg effect, which is responsible for keeping cancer cells alive by generating energy through glycolysis, where glucose is converted to lactose for energy followed by lactate fermentation even when oxygen is available . Amide III vibrations attributed to β‐sheet and α‐helix conformation in proteins are highly associated to cancer ; as well as DNA methylation, which is an enzyme‐induced chemical modification to the DNA structure where a methyl group is covalently bonded to the cytosine base, and abnormalities in this phenomenon are related to carcinogenesis . Shifts in the Amide I peak are known to be associated with transformation to cancer due to alterations in protein backbone conformation .…”

Raman Microscopy: Progress in Research on Cancer Cell Sensing

“…However, the transfer of the “Raman spectral library”, such as those available in FTIR analyses, remains a major challenge that stands in the way of clinical translation for Raman-based technologies, and continued effort is needed to facilitate the transition from benchtop to bedside by developing novel experimental designs and structured protocols for the objective method. The further development of the cell classification methods, the improvement in Raman instrumentations trending toward obtaining data with greater resolution, shorter collection times, and higher accuracy would give additional information, allowing earlier and more accurate diagnosis, reducing the need for human intervention, and increasing the objectivity of assessment [ 11 , 63 ].…”

Clinical applications of infrared and Raman spectroscopy in the fields of cancer and infectious diseases

“…The approach for surgical evaluation and screening, based on label-free SERS using silver nanoparticles coupled with PCA-LDA, achieved 95% and 100% diagnostic accuracies for pre-surgery versus post-surgery and pre-surgery versus normal groups, respectively. Talari et al used Raman spectroscopy with PCA and LDA to identify cancer subgroups [46] . To distinguish between luminal A, luminal B, HER2 and triple negative subtypes, 132 tissue microarray breast biopsies were examined.…”