In a groundbreaking research carried out by Indian Researchers, an Artificial Intelligence (AI) based algorithm, will be instrumental in diagnosing Cervical Cancer. Indian Institute of Science Education and Research (IISR) and Indian Institute of Technology Kanpur (IIT-K) have conducted the research.
Professor Nirmalya Ghosh from IISER Kolkata said, “Superficial cancers such as oral and cervical cancers can be studied using this technique. And by integrating it with an endoscopic probe that uses optical fibre to deliver white light and surrounding fibres to collect the scattered light we can study cancers inside the body.”
ABOUT THE RESEARCH
- The research is based on the principle that the refractive index of a tissue, in case of a precancerous cell is different from that of a healthy cell. This means that the light refracted from both the tissues will be different. This, in turn will help in detecting cancer cells.
- However, human eye cannot detect the difference between the refractive index of both the tissues . Therefore, Artificial Intelligence (AI) will be used to detect the differences.
- It can further reveal the different stages of a Cervical Cancer.
- Furthermore, the researchers claim that it can provide results within a few minutes.
- At present, it has an accuracy rate of 95%.
- The team studied ‘in vitro’ samples for its investigation. However, further advancements are being made to replicate the study on ‘in vivo’ samples.
- The study used white light spectroscopy (340-800nm).
Sabyasachi Mukhopadhyay from IISER Kolkata said, “The microstructure of normal tissue is uniform but as disease progresses the tissue microstructure becomes complex and different. Based on this correlation, we created a novel light scattering-based method. This helped to identify these unique microstructures for detecting cancer progression.”
Professor Prasanta K. Panigrahi from IISER Kolkata said, “The classification of healthy and precancerous cells becomes robust by converting the information obtained from the scattered light into characteristic tissue-specific signature. The signature captures the variations in tissue morphology.”
Multifractal Detrended Fluctuation Analysis (MFDFA) is a statistical biomarker that helped the team, quantify the changes in tissue refractive index.