Google Cloud partnering with Varian on radiation oncology platform
April 14, 2021
by Lisa Chamoff
, Contributing Reporter
Google Cloud has tapped Varian Medical Systems to collaborate on the development of a new artificial intelligence (AI)-based diagnostic platform for cancer treatment.
The collaboration will use Neural Architecture Search (NAS) technology via the Google Cloud AI Platform to create AI models for organ segmentation, a crucial but labor-intensive step in radiation oncology.
Organ segmentation is the process of using diagnostic images to identify the organs and tissues that must be targeted or protected during a course of radiation therapy. The segmented images are used to create radiotherapy treatment plans that specify where and how much dose will be deposited during treatment. The process can take a clinician hours per patient, and in some parts of the world it can limit patients’ access to advanced treatments.
Varian will use Google Cloud AI Platform’s NAS technology to create an AI segmentation engine that is trained using Varian’s proprietary treatment planning image data. This will create customized auto-segmentation models for organs, which Varian plans to incorporate into its Eclipse treatment planning software.
“The collaboration with Google Cloud is a longer-term development project that is expected to impact how Varian makes AI tools in the future, and revises and trains them so that they are always evolving,” Kevin O'Reilly, senior vice president and president of Varian Oncology Systems, told HCB News.
“At Google Cloud, we believe AI technology has the power to impact a wide variety of industries, which is especially true in the field of medicine,” said Craig Wiley, director of product management for Google Cloud, in a statement. “We are excited to see how Varian accelerates AI innovation and segmentation quality to improve cancer care with radiation therapy using our state-of-the-art NAS technology. As Varian’s AI platform of choice, our teams are working closely to deliver best-in-class AI for cancer treatment to patients around the world.”