Technology 3 min read

AI Can Help Cancer Patients Start Radiation Therapy Sooner

Mark_Kostich / Shutterstock.com

Mark_Kostich / Shutterstock.com

Artificial intelligence can instantly translate complex clinical data for cancer patients into an optimal plan of attack. That way, the patients can start radiation therapy sooner.

Radiation therapy is a cancer treatment that involves using high beams of radiation to destroy cancerous cells or shrink tumors.

According to past studies, delaying the therapy can increase the chance of some cancers spreading by 12 to 14 percent. In the worst cases, it could increase the possibility of the disease reoccurring.

Unfortunately, delays happen.

Health professionals usually spend as much as a week manually developing a treatment plan. So, patients have to spend just as long waiting and hoping that cancer doesn’t spread or reoccur.

Head of UT Southwestern’s Medical Artificial Intelligence and Automation (MAIA) Lab, Steve Jiang, Ph.D. explained:

“Some of these patients need radiation therapy immediately, but doctors often have to tell them to go home and wait. Achieving optimal treatment plans in near real-time is important. “

So, the UT Southwestern team did just that. In their paper in Medical Physics, they showed how AI could streamline the time it takes to develop a treatment plan to a fraction of a second.

Here’s how it works

Using Deep-Learning Model to Jump Start Radiation Therapy

According to Jiang, developing a sophisticated treatment plan can be tedious.

Aside from carefully reviewing the patient’s imaging data, the process also involves several phases of feedback with the medical team. Yes, it’s all so time-consuming, and that’s where AI comes in.

The researchers fed the data for 70 prostrate cancer patients into four deep learning models. Then, the models developed a 3-D rendering of the best way to distribute radiation therapy for individual patients.

Also, each model was able to accurately predict the treatment plans that the medical team developed for each case.

Our AI can cut out much of the back and forth that happens between the doctor and the dosage planner,” Jiang noted. “This improves efficiency dramatically.”

Using Artificial Intelligence to Calculate Dosages

Health professionals usually have to recalculate dosages before each radiation therapy. That’s because the patient’s anatomy may have changed since the last treatment.

So, the new dosage must take these possible changes into account.

The recalculation process could take up to 10 minutes. However, another study by Jiang shows that AI can also reduce the waiting time.

Jiang and his colleagues’ algorithm combines two conventional models that could help calculate doses.

The first model is simple and fast but lacked accuracy. Meanwhile, the other model is complex and requires longer time, but it’s accurate

The team intends to use the new AI capabilities in clinical care after implementing a patient interface. For now, they’re working on other deep-learning tools for several different purposes.

These include enhanced medical imaging and image processing, improved disease diagnosis and treatment outcome prediction, as well as automated medical procedures.

Part of our broader mission is to use AI to improve all aspects of cancer care,” Jiang concluded.

Read More: How AI is Personalizing Healthcare

First AI Web Content Optimization Platform Just for Writers

Found this article interesting?

Let Sumbo Bello know how much you appreciate this article by clicking the heart icon and by sharing this article on social media.


Profile Image

Sumbo Bello

Sumbo Bello is a creative writer who enjoys creating data-driven content for news sites. In his spare time, he plays basketball and listens to Coldplay.

Comments (0)
Most Recent most recent
You
share Scroll to top

Link Copied Successfully

Sign in

Sign in to access your personalized homepage, follow authors and topics you love, and clap for stories that matter to you.

Sign in with Google Sign in with Facebook

By using our site you agree to our privacy policy.