Researchers from the Institute of Advanced Study in Science and Technology (IASST) in India have developed a fully automated software-based solution for the detection of cervical cancer.
The software uses Pap smear images to detect abnormal growth or development of tissues in the cervix.
Pap Smear is a widely used technique for the early detection of cervical cancer. The diagnosis involves analysing the slides prepared from the smear collections, under a microscope.
The researchers were quoted by Times of India as saying: “We put together a database of two types of indigenous Pap smear images databases, one each for conventional and Liquid Based Cytology (LBC) and used it to create algorithms with the images of different qualities, being prepared by different technicians and captured from different microscopes. The algorithms helped develop robust software to detect cervical cancer.”
The group also employed the Bethesda system for Pap Smear diagnosis and adopted two artificial intelligence (AI) approaches, namely machine learning and deep learning, for the development of the software.
IASST operator The Department of Science and Technology (DST) told the publication: “The team has developed a novel classification algorithm, with 98.8% accuracy, which can identify the precancerous and cancer lesions while precisely localising the cervical cells, removing the debris including overlapping cells and then finally classifying them based on the Bethesda system nomenclature, to maintain uniformity with the current reporting system.”
The researchers intend to launch a pocket-friendly diagnostic kit after conducting substantial field trials. It will be hosted and marketed on a web-based platform.
Cervical cancer is one of the most prevalent cancers among women in India, particularly among women in the north-eastern region of the country.