AI crunches images in less than a second to devise cancer treatment plan

Devising a cancer treatment plan can be a slow process at times, with delays potentially leading to patient harm when doctors don’t act quickly enough.

But a new artificial intelligence tool, developed by UT Southwestern, could drastically speed things up by quickly crunching imaging data and developing a game plan in less than a second, according to a recent study in Medical Physics.

“Our AI can cut out much of the back and forth that happens between the doctor and the dosage planner. This improves the efficiency dramatically,” Steve Jiang, PhD, director of UT Southwestern’s Medical Artificial Intelligence and Automation Lab, said in a Jan. 27 announcement.

Jiang and colleagues noted that cancer patients can sometimes wait several days to a week to begin receiving radiation therapy. However, past studies have found that even a week’s delay in such care can increase the chance of cancer recurring or spreading by upward of 14%.

To address this issue, the research team fed imaging data from 70 prostate cancer patients into four-different deep learning models. The model was then able to devise 3D renderings of how best to distribute radiation in each individual, accurately predicting treatment plans later developed by the team. Where humans could take a week, AI spit out a radiation roadmap within five-hundredths of a second.

Jiang and colleagues also devised an additional AI model that accurately recalculates treatment dosages prior to each session, quickly assessing how patients’ anatomies change during each appointment. Typically, patients may wait 10 minutes or more for doctors to make these calculations, which does not include extra time for medical imaging before each session.

The UT AI team plans to further test these tools in regular clinical care. They’re also working to device new deep learning models aimed at enhancing medical imaging, automating procedures and improving disease diagnosis, according to the announcement.

Marty Stempniak

Marty Stempniak has covered healthcare since 2012, with his byline appearing in the American Hospital Association's member magazine, Modern Healthcare and McKnight's. Prior to that, he wrote about village government and local business for his hometown newspaper in Oak Park, Illinois. He won a Peter Lisagor and Gold EXCEL awards in 2017 for his coverage of the opioid epidemic. 

Trimed Popup
Trimed Popup