doi:10.1038/nindia.2017.148 Published online 30 November 2017
Researchers have developed a computer-based optical method that can distinguish precancerous cervical cells from healthy cells, making it a potentially useful tool for diagnosing cervical cancer long before its onset1.
Precancerous cells are not a sign of cancer, but they can potentially grow into cancer cells. Optical methods are sensitive and potentially capable of discriminating various stages of the disease’s progression. However, tissues possess complex patterns, making it difficult to identify disease-markers using optical methods.
In search of an efficient optical method for assessing the risks of cervical cancer, scientists from the Indian Institute of Science Education and Research in Kolkata and the Indian Institute of Technology in Kanpur invented an optical method that uses two integrated computer models to detect optical signals specific to precancerous and healthy tissues isolated from the cervix of patients.
When white light was shone on the samples of precancerous and healthy tissues, the precancerous and healthy tissues scattered light differently, generating tissue-specific optical signals that the models deciphered with great accuracy.
The new method was able to exclude noise generated along with the optical signals, producing better classification results than other computer-based optical methods.
This method could be used in clinical set-ups for screening cervical and other types of cancers, says lead researcher Sabyasachi Mukhopadhyay.
1. Mukhopadhyay, S. et al. Tissue multifractality and hidden Markov model based integrated framework for optimum precancer detection. J. Biomed. Opt. 22, 105005 (2017)