SRL Diagnostics (the largest diagnostics laboratory company in India), which has been working with Microsoft to develop digital pathology services, has begun assessing its Cervical Cancer Image Detection application programming interface (API). The Cervical Cancer Image Detection API operates on Microsoft’s Azure, and the research has been conducted in Mumbai.
According to TechCrunch the system is capable of rapidly screening liquid-based cytology slide images in order to detect cervical cancer at the early stages. Digital data is then transmitted back to pathologists in the originating laboratory.
Detecting cervical cancer early is key to increasing survival rates. The World Health Organization (WHO) finds that cervical cancer is the fourth most common type of cancer among women, globally. In India this form of cancer accounts for 16 percent of the worldwide rates for the disease.
Putting together the Cervical Cancer Image Detection API began with developing an artificial intelligence algorithm capable of assessing smear tile images as well as any experienced cytopathologist. This required, cytopathologists to carefully examine digitally scanned versions of Whole Slide Imaging slides and to mark key observations. These observations were used as the basis for training the AI model.
This was a slow and complex process since each slide image can comprise as many as 1,800 tile images. However, now the AI model can differentiate between normal and abnormal smear slides with a high -level of accuracy, and it is undergoing final evaluation.
Microsoft is also working with Apollo Hospitals, in India, to create an AI-powered API customized to predict risk of different heart diseases.
