Microsoft and SRL Diagnostics have developed an Artificial Intelligence-based tool to help doctors diagnose cervical cancer faster.
The tool is essentially a Cervical Cancer Image Detection API which does the first-level check and offloads normal slides to help cytopathologists spend more time on slides that have signs of abnormality.
The AI is trained using the observations made by cytopathologists who studied digitally scanned versions of Whole Slide Imaging (WSI) slides. Each unit of WSI features 1,800 tile images. Microsoft and SRL Diagnostics appointed five cytopathologists across multiple labs and different locations to train the AI model.
“The issue of subjectivity was addressed by creating discordant and concordant notes on each sample image. 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,” said Microsoft in a blog post.
“As part of the new workflow, the large digital WSI scans from Device Image Scanners are uploaded to Azure where the Cervical Cancer Image Detection API runs. The AI-powered Cervical Cancer Image Detection API can quickly screen liquid-based cytology slide images for detection of cervical cancer in the early stages and return insights to pathologists in labs,” it added.
Microsoft says the AI model is now capable of differentiating between normal and abnormal smear slides with higher accuracy. The AI tool can also distinguish between smear slides on the basis of the seven-subtypes of cervical cytopathological scale, ranging from pre-cancerous to cancerous stages.
Microsoft hopes the partnership with SRL Diagnostics will help build more similar AI-enabled APIs for different fields of pathology. For instance, diagnosis of pancreatic and liver cancers. The SRL Diagnostics-Microsoft consortium is now looking to team up with more private firms and governments to provide the solution in remote areas where the availability of histopathologists is a hurdle.
“Our constructs of AI networks and multi-party collaboration with leading healthcare providers aim to unlock AI innovation to help in early risk stratification and move to better healthcare. I am really excited with the partnership that we have with SRL Diagnostics where we have been working together, using the power of AI, to increase the productivity of cytopathologists, leading to better results and accurate outcomes,” says Anil Bhansali, Corporate Vice President, Cloud & AI Platform, Microsoft.
