SRL Diagnostics uses Microsoft’s new AI tool to diagnose cervical cancer faster

Researcher at SRL Diagnostics

As per the estimates of the World Health Organization (WHO), cervical cancer is the fourth most persistent cancer among women worldwide and in India, more women die with this disease than any other country in the world. This curable disease kills about 67,000 women in India every year, more than 25% of the 260,000 deaths in the world.

Cervical cancer is frequent in the rural regions of the country where literacy and awareness of the fatal disease are low.

SRL Diagnostics, the largest chain of diagnostic services in pathology and radiology in the country receives more than 100,000 Pap smear samples every year and since the proportion of cytopathologists is very low with respect to the number of patients in India, there are only a few trained cytopathologists who are supposed to examine such slides.

While 98% of samples are normal and just 2% of the samples come abnormal and require much intervention to them, to help cytopathologists able to find those 2% abnormal samples faster said Dr. Arnab Roy, Technical Lead – New Initiatives & Knowledge Management, SRL Diagnostics.

In September last year, SRL Diagnostics partnered with Microsoft to create an Artificial Intelligence Network for Pathology to make it easy for cytopathologists and histopathologists to test the samples.

This week, the two company announced that their collaboration has finally shown some results, SRL Diagnostics has started using the Cervical Cancer Image Detection API running on Microsoft Azure that is now able to quickly screen liquid-based cytology slide images for detection of cervical cancer in the early stages and returns insights to pathologists in labs.

A digitally scanned version of a Whole Slide Imaging (WSI) slide, which is used to train the AI model
A digitally scanned version of a Whole Slide Imaging (WSI) slide, which is used to train the AI model (Image: Microsoft)

As mentioned in the blog post, the new AI model can now differentiate between normal and abnormal smear slides with accuracy and is currently under validation in labs for a period of three to six months.

“The API has the potential of increasing the productivity of a cytopathology section by about four times. In a future scenario of automated slide preparation with assistance from AI, cytopathologists can do a job in two hours what would earlier take about eight hours!” Dr. Roy said.

Both companies are hopeful to implement this new tool in other fields of pathology such as diagnosis of kidney pathologies and in oral, pancreatic and liver cancers. The team also hopes to scale up its reach with tie-ups with private players and governments and expand the reach of the model even in remote geographies where the availability of histopathologists is a challenge.

India, the second-most populous nation in the world has become a testbed for multiple American tech companies like Microsoft which are developing new projects including AI-based projects that are helping solve problems in India.

Last week, Microsoft announced it’s AI-based driving test project to help the transport authority for driving license test in the country.

Leave a Reply

%d bloggers like this: