Researchers have revealed a new AI-based performance that can accurately identify cancerous tumors and speed up the process of diagnosing the disease. Designed by experts at The Royal Marsden Institution, The Institute of Cancer Research London and Imperial College London, the AI tool can determine whether abnormal tumors seen on a CT scan are cancerous.
"In the future, we hope that early detection will make cancer treatment more successful, by focusing on high-risk patients and quickly following them up with early intervention," said Benjamin Hunter, an oncologist at the Royal Marsden Foundation.
And according to the British newspaper "Daily Mail", Hunter's team used CT scans of about 500 patients with large lung cancer cells, to develop an artificial intelligence algorithm using radiology. This technology can extract important information from x-ray images that are not easily detected by the human eye.
The model the scientists developed was tested to see if it could accurately identify precancerous nodes. The study used a measure called the 'Area Under the Curve', or AUC, to see how effective the model was at predicting cancer.
A value of 1 on the scale indicates a perfect model, while a number of 0.5 represents a random guess. The results showed that the AI model could determine the risk of cancer for each node with an AUC value of 0.87.
Commenting on these findings, the study's lead investigator, Dr. Richard Lee, said: "Through this work, we hope to push the boundaries to accelerate disease detection using innovative technologies such as artificial intelligence." Cancer causes about 10 million deaths annually, nearly one in six deaths worldwide, according to the World Health Organization.
0 Comments