Doctors may soon have a powerful new tool to help diagnose lung cancer earlier and more accurately thanks to new AI technology developed by scientists at the Massachusetts Institute of Technology in Cambridge.
The AI system, called Sybil, can identify tell-tale signs of lung cancer that doctors might miss when examining CT scans.
Sybil analyzes CT scan images and can detect tissue changes at a cellular level that could point to cancerous growths, even before they are visible on scans or X-rays. Based on what it sees, Sybil predicts whether a person will develop lung cancer in the next one to six years.
There have even been cases where Sybil has detected signs of cancers that radiologists did not catch until nodules were visible on a CT scan years later.
During testing, the system could correctly identify tiny early-stage lung cancer tumors up to 94% of the time, far outperforming the accuracy of human radiologists.
According to the American Cancer Society, lung cancer is the second most common cancer in both men and women and is responsible for the most cancer-related deaths. One reason for the high mortality rates is that early-stage lung cancer can be challenging to detect using traditional diagnostic methods.
With this new AI technology, doctors may be able to detect lung cancer at earlier stages, making treatment more effective and survival rates higher.
While Sybil is not yet ready for routine clinical use, the results are promising. Researchers hope that further testing and development will enable doctors to better diagnose lung cancer and save more lives.