AI Matches Doctors in Mapping Lung Tumors, Enhancing Radiation Therapy Precision

Northwestern Medicine has introduced iSeg, an AI tool that matches doctors in mapping lung tumors and identifying areas often missed, promising more precise radiation therapy and better patient care.

In a new study published today in the journal npj Precision Oncology, scientists at Northwestern Medicine reveals that iSeg, an AI tool they developed, not only matches doctors in accurately outlining lung tumors on CT scans but can also identify areas that some doctors may miss.

Precision is critical in radiation therapy as oncologists must meticulously map the size and location of a tumor to deliver high-dose radiation that destroys cancer cells while sparing healthy tissue. This process, known as tumor segmentation, is typically labor-intensive, done manually and can vary between doctors, sometimes leading to critical tumor areas being missed.

Unlike past AI tools that dealt with static images, iSeg is the first 3D deep learning tool shown to segment tumors as they move with each breath — a critical factor in planning radiation treatment.

This advancement could significantly enhance the accuracy of radiation therapy, which is a vital part of treatment for nearly half of all cancer patients in the U.S.

“We’re one step closer to cancer treatments that are even more precise than any of us imagined just a decade ago,” senior author Mohamed Abazeed, chair and professor of radiation oncology at Northwestern University Feinberg School of Medicine, said in a news release.

“The goal of this technology is to give our doctors better tools,” added Abazeed, who leads a research team focused on developing data-driven tools to personalize and improve cancer treatment and is also a member of the Robert H. Lurie Comprehensive Cancer Center of Northwestern University.

Training iSeg

The team trained iSeg using CT scans and doctor-drawn tumor outlines from hundreds of lung cancer patients treated at nine clinics within the Northwestern Medicine and Cleveland Clinic health systems.

This expansive dataset contrasts with the smaller, single-hospital datasets used in many past studies.

Upon training, iSeg’s performance was tested on patient scans it had not encountered before. Its outputs were then compared with those drawn by physicians.

The study found that iSeg consistently matched expert outlines across various hospitals and scan types. Remarkably, it also highlighted additional areas that some doctors missed, which were linked to worse outcomes if left untreated.

“Accurate tumor targeting is the foundation of safe and effective radiation therapy, where even small errors in targeting can impact tumor control or cause unnecessary toxicity,” Abazeed added.

First author Sagnik Sarkar, a senior research technologist at Feinberg who earned a master of science in artificial intelligence from Northwestern, added, “By automating and standardizing tumor contouring, our AI tool can help reduce delays, ensure fairness across hospitals and potentially identify areas that doctors might miss — ultimately improving patient care and clinical outcomes.”

Clinical Deployment

The research team is currently testing iSeg in clinical environments, comparing its performance to that of physicians in real-time scenarios.

They are also incorporating features like user feedback and are working to extend the technology to other tumor types, including liver, brain and prostate cancers.

Plans are also in place to adapt iSeg to additional imaging methods, such as MRI and PET scans.

“We envision this as a foundational tool that could standardize and enhance how tumors are targeted in radiation oncology, especially in settings where access to subspecialty expertise is limited,” added co-author Troy Teo, an instructor of radiation oncology at Feinberg. “This technology can help support more consistent care across institutions, and we believe clinical deployment could be possible within a couple of years.”

Source: Northwestern University