Scientists from the Center for Memorial College and Memorial Sloan Kettering Cancer have developed an artificial intelligence tool that can detect breast cancer through a MRI survey and indicate the deployment of tumors. The results of the study were published "Radiology. Artificial Intelligence "magazine.
The system has been trained based on data from the world's largest database database and tested on images of two clinics cancer patients.
"The model accuracy is comparable to the results of experienced X-ray in the diagnosis of breast cancer. At the same time, the algorithm shows better results than the existing automatic systems, "said Lucas Parra, a professor of CCNY biomedical engineering.
Unlike most existing algorithms, the new model has been tested independently and is now available in the public domain in the United States.
Researchers emphasize that new technology can accelerate the work of doctors and reduce the workload of X-ray. Scientists have explained that it is difficult to interpret the MRT images, especially in women with a dense breast tissue, which is not always good to be analyzed through mammography. The algorithm not only discovers the tumors, but also indicates their accurate deployment, which reduces the risk of false positive diagnosis.
Translation of: Euromedia24.com
