- Red Hat, DarwinAI Partner for COVID-19 Artificial Intelligence
InnerEye will shorten the lengthy cancer treatment planning stage that patients undergo, which is critical for cancers of the head and neck, as these types of cancers can grow if left untreated.
Experts are expecting survival rates to increase, as a result.
“The results from InnerEye are a game-changer. To be diagnosed with a tumor of any kind is an incredibly traumatic experience for patients,” Raj Jena, MD, an oncologist at Addenbrooke’s and co-lead of InnerEye, said in the announcement.
“As clinicians we want to start radiotherapy promptly to improve survival rates and reduce anxiety. Using machine learning tools can save time for busy clinicians and help get our patients into treatment as quickly as possible,” Jena continued.
InnerEye was developed at the company’s Cambridge Research Lab. Addenbrooke’s has been working with Microsoft to develop and pilot the initiative over the past eight years. When the artificial tool is in place, the hospital will be able to use its own data to improve accuracy.
Nearly half of all individuals in the UK will be diagnosed with cancer at some point in their lives, Microsoft stated. And of these people, half will be treated with radiotherapy.
This type of treatment involves high-intensity radiation beams to combat the DNA of cancerous tumors while avoiding healthy organs simultaneously.
First, radiologists will take a 3D CT scan of the individual. Each CT scan comes in different forms and must be thoroughly examined and marked by a radiation oncologist, clinical oncologist, or specialist technician.
Experts must manually draw a contour line around the tumors and healthy organs in the target area. The whole process is lengthy, taking several hours. InnerEye is able to perform the task 13 times faster.
“There is no doubt that InnerEye is saving me time. It’s very good at understanding where the prostate gland is and healthy organs surrounding it, such as the bladder. It’s speeding up the process so I can concentrate on looking at a patient’s diagnostic images and tailoring treatment to them,” said Yvonne Rimmer, consultant clinical oncologist at Addenbrooke’s.
“But it’s important for patients to know that the AI is helping me in my professional role; it’s not replacing me in the process. I doublecheck everything the AI does and can change it if I need to. The key thing is that most of the time, I don’t need to change anything,” Rimmer continued.
Microsoft stated that it has made the tool freely available as open-source software so that all hospitals can use the InnerEye Deep Learning toolkit.
Overall, AI models trained with InnerEye help to speed up the cancer care process and empower clinical oncologists with an AI assistant, said Javier Alvarez-Valle, principal research manager at Microsoft Research Cambridge.
“The AI works in the background, so clinical oncologists just open up the scans on their computer and they can see what their AI model has highlighted. The clinical oncologist then decides what to do with that information,” Alvarez-Valle said. “AI models trained with InnerEye will be hosted in Microsoft’s Azure cloud, so all the data is securely held in the UK and only available to the medical staff who need to use it.”