Role of artificial intelligence and vibrational spectroscopy in cancer diagnostics

ABSTRACT

Introduction

Raman and Infrared spectroscopic techniques are being used for the analysis of different types of cancers and other biological molecules. It is possible to identify cancers from normal tissues both in fresh and fixed tissues. These techniques can be used not only for the early diagnosis of cancer but also for monitoring the progression of the disease. Furthermore, chemical pathways to the progression of the disease process can be understood and followed.

Areas covered

More recently, Artificial Intelligence (AI), Neural Network (NN), and Machine Learning are being combined with spectroscopy, which is making it easier to understand the chemical structural details of cancers and biological molecules more precisely and accurately. In this report, these aspects are being outlined by using breast cancer as a specific example.

Expert opinion

A pathway showing to combine vibrational spectroscopy with AI and ML has immense potential in predicting various stages of different disease processes, in particular, in cancer diagnosis, staging, and designing treatment. This will result in improved patient care pathways.

KEYWORDS:

• Raman spectroscopy
• breast cancer
• artificial intelligence
• machine learning
• neural network
• principal component analysis

Article highlights

• Analysis of breast cancer using Raman spectroscopy

• Principal Component Analysis of spectral data of breast cancer

• Cluster analysis of normal and cancerous normal breast tissue

• Role of artificial intelligence and machine learning.

• Early diagnosis and monitoring of the progression of cancer.

Acknowledgments

Use of spectra data from the thesis of my PhD student, Daniela Lazaro Pacheco, is greatly acknowledged.

Declaration of interest

The authors have no relevant affiliations or financial involvement with any organization or entity with a financial interest in or financial conflict with the subject matter or materials discussed in the manuscript. This includes employment, consultancies, honoraria, stock ownership or options, expert testimony, grants or patents received or pending, or royalties.

Reviewer disclosures

Peer reviewers on this manuscript have no relevant financial or other relationships to disclose.

Additional information

Funding

This paper was not funded.