Kolkata, Dec 28 (IANS): A computer-based optical method, developed by Indian scientists, can pin-point precancerous cervical cells and healthy cells, thereby providing early indications of cervical cancer.

The optical method, devised by scientists from Indian Institute of Science Education and Research (IISER), Kolkata, and Indian Institute of Technology, Kanpur, taps into machine learning algorithms to classify healthy and abnormal tissues.

"By using a light-based probe to identify certain complex repeating patterns (called multifractals), present on developing cancer cells, we can get early indications of the disease," Sabyasachi Mukhopadhyay, from IISER-Kolkata, told IANS.

The study documenting the method is published in Journal of Biomedical Optics.

The basis of this technology is that cells which are progressing towards cancer show more of these complex geometric patterns than the normal, unaffected and healthy ones.

"Based on this correlation, we created a novel light-scattering based method to identify these unique patterns for detecting cancer progression," Mukhopadhyay said.

This algorithm could be used in clinical set-ups for screening cervical and other types of cancers, the researcher said about the low cost technology.