India accounts for 25% of 260,000 yearly worldwide cervical cancer deaths, killing over 67,000 women every year.
With early detection, the cancer can be preventable; so the solution could be a more effective screening program.
Microsoft believes that the introduction of AI technology will facilitate faster analysis of Pap smear samples. Last year, the company partnered with SRL Diagnostics to create an AI network for Pathology.
SRL Diagnostics performs cytoanalysis on over 100,000 Pap smear samples every year- 2% of which are abnormal and require further analysis. With the assistance of AI technology, cytopathologists will be able to perform their job much more efficiently.
“We were looking for ways to ensure our cytopathologists were able to find those 2% abnormal samples faster”- Dr. Arnab Roy, Technical Lead for New Initiatives & Knowledge Management at SRL Diagnostics.
The AI algorithm also helps with discrepancies between cytopathologists, and can “create a consensus on the areas assessed,” according to Manish Gupta, Principal Applied Researcher at Microsoft Azure Global Engineering.
Different cytopathologists examine different elements in a smear slide in a unique manner even if the overall diagnosis is the same. This is the subjectivity element in the whole process, which many a time is linked to the experience of the expert.”- Dr. Roy.
The algorithm was created based on thousands of annotations of cervical smears made by cytopathologists from multiple labs.
“The images for which annotations were found to be discordant — that is if they were viewed differently by three team members — were sent to senior cytopathologists for final analysis.” – Microsoft.
When put into practice this week, the Azure-powered Cervical Cancer Image Detection API could successfully screen liquid-based cytological slides, differentiate between the pathological ones and send them for further analysis. Not only that, but it could also classify smear slides based on the seven subtypes of cervical cytopathology.
The technology worked so successfully that it’s now under a period of validation in labs for 3-6 months. During this period, more than half a million anonymised digital slides will be evaluated, and previewed in hospitals and other diagnostic centres.
Cytopathologists now have to review fewer areas, 20 as of now, on a whole slide liquid-based cytology image and validate the positive cases thus bringing in greater efficiency and speeding up the initial screening process.” Microsoft.
“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.
This AI technology can help in early diagnosis of many pathologies including oral, pancreatic and liver cancer; and will undoubtedly lead to huge advancements in the field of medicine, eventually preserving the lives of hundreds of thousands every year.