Researchers at the Indian Institute of Technology, Mandi in collaboration with Bengaluru-based Aindra Systems have developed an artificial intelligence-powered point-of-care device to screen for cervical cancer by analyzing microscopy images with high accuracy.
The research was initiated by a team led by Anil Sao and Arnav Bhavsar Associate Professors, School of Computing and Electrical Engineering, IIT Mandi with their research scholars Srishti Gautam and Krati Gupta. The team of researchers developed AI-based algorithms that enable the device to undertake automatic screening for cervical cancer.
Firstly, the team analyzed Pap smear images provided by the industrial partner, Aindra, and characterized them into normal and potentially cancerous and then differentiated the two with the help of a computer program. Moreover, the developed algorithm is based on the recent deep learning paradigm of artificial intelligence and can be used in situations where one can encounter a large amount and variability in data.
“The difference between a conventional system and Aindra’s Aindra’s point-of-care system is that the latter is portable and can be taken to the potential patients. In the conventional system, people have to visit the pathology laboratory to get themselves screened,” Bhavsar said.
In order to classify cervical cells, the researchers have developed an efficient pre-processing technique to detect cells in images and were subjected to the Convolution Neural Network algorithm, for accurate classification of cancer cells.
“We could demonstrate performance improvements over some of the contemporary methods, with relatively simpler, and arguably more efficient methods”, said Bhavsar.
Further, Adarsh Natrajan, Harinarayanan and Nirmal Jith from Aindra Systems Pvt Ltd collaborated on the design and the development of the device. Also, work associated with this research in papers in the Workshop on Computational Pathology 2018, and in Proceedings of Society of Photo-optical Instrumentation Engineers (SPIE) 2018.