Google Cloud, Hologic use AI tools to fight cervical cancer

Google Cloud and medical technology vendor Hologic, a women's health specialist, are working together on a new AI algorithmic approach to diagnosing cervical cancer.

Cervical cancer is the fourth most common cancer in women. The World Health Organization (WHO) has targeted the disease for eradication.

Hologic, based in Marlborough, Mass., in 2020 introduced its Genius Digital Diagnostic system, a digital cytology platform that combines advanced volumetric medical imaging technology and AI algorithms to help researchers identify abnormal cells in cervical and other cancers in women.

Toward the WHO's ambitious goal, Google Cloud and Hologic in February 2021 unveiled a multiyear strategic collaboration based on integrating Google Cloud's machine learning  (ML) technologies with Hologic's Genius system to significantly improve cervical cancer screening.

"The new genius digital diagnostic system fundamentally changes to the screening process, giving technologists a new tool in the fight against cervical cancer," Michael Quick, vice president of research and development and innovation at Hologic, said during a breakout session at the Google Cloud Next '21 virtual conference.

For Google's part, the partnership is helping Google extending healthcare to places where there are shortages of doctors and reach more patients, said Alissa Lynch, global lead for medtech strategy and solutions at Google.

"Our vision for medical imaging is to transform disease detection and diagnosis and improve people's lives by making the world of imaging data accessible, interoperable and useful," Lynch said.

Google Cloud has already undertaken several collaborations in which it has been able to show that AI models may be able to diagnose some medical conditions with greater accuracy than human experts, Lynch said.

Our vision for medical imaging is to transform disease detection and diagnosis and improve people's lives by making the world of imaging data accessible, interoperable and useful.

One of the collaborations was with Northwestern University to determine whether AI can reduce the waiting time for breast cancer diagnosis. Another was with Verily, Google parent company Alphabet's life sciences and healthcare division, in which the vendors developed an algorithm for diagnosing diabetic eye disease.

With their work on cervical cancer screening, Google and Hologic are focusing on amplifying the importance of cervical cancer screening and using diagnostic systems with the latest AI and ML tools to makes the cervical screening technology available to regardless of socioeconomic background.

The vendors are using the backbone of Google's cloud infrastructure to support data organization, processing and access around the world.

Over the past year, the two companies have worked together to refine Hologic's cell-level algorithms using Google's AI and ML tools and to find new ways of diagnosing patients.

"The teams worked together to develop an elegant solution of a two-step model where the output of the first network feeding into the second [achieved] a high level of accuracy," Quick said.

That work resulted in a model that was tested on two separate clinical data sets. As a result of the tests, Quick said the data showed it is highly likely that digital algorithms will be able to match the accuracy of human review in situations in which there isn't enough healthcare infrastructure to provide an adequate standard of care.

He added that the research data also shows the need for more powerful AI and ML tools.

Hologic said its partnership with Google Cloud will help it develop new technologies in the Genius Digital Diagnostics portfolio and give healthcare professionals more tools to combat cervical cancer.