Communications of the ACM
AI Model Can Detect Future Lung Cancer Risk
Said Mass General Cancer Center thoracic interventional radiologist Florian Fintelmann, “It’s important to know that if you detect lung cancer early, the long-term outcome is significantly better."
Credit: Cleveland Clinic
Researchers at the Massachusetts Institute of Technology (MIT), the Mass General Cancer Center and Taiwan's Chang Gung Memorial Hospital have developed an artificial intelligence tool that can perform lung cancer risk assessments without the help of a radiologist.
The tool, named Sybil, can analyze low-dose computed tomography (LDCT) scans to predict the risk that a patient will develop a future lung cancer within six years.
Sybil was trained using hundreds of CT scans with visible cancerous tumors and then tested on CT scans without discernible signs of cancer.
MIT's Jeremy Wohlwend said, "We found that while we [as humans] couldn't quite see where the cancer was, the model could still have some predictive power as to which lung would eventually develop cancer. Knowing [Sybil] was able to highlight which side was the most likely side was really interesting to us."
From MIT News
View Full Article
Abstracts Copyright © 2023 SmithBucklin, Washington, DC, USA
No entries found