Wednesday, March 14, 2018
Aunt Minnie (3/14, Ridley) reports that research presented last month at the SPIE Medical Imaging 2018 conference in Houston demonstrated that an artificial intelligence algorithm may enable breast imagers to sharply reduce radiation dose from digital breast tomosynthesis (DBT) exams – perhaps by as much as 80 percent. A multi-institutional team led by Junchi Liu from the Illinois Institute of Technology in Chicago “developed a deep learning-based image processing technique that can convert lower-dose DBT images to virtual images that approximate higher-dose exams,” according to Aunt Minnie. In testing on images acquired on cadaver phantoms, the method yielded high-quality images at as little as 79 percent of the dose of standard DBT studies, according to the article.
Categories: 2018, March, News, Screening and MammographyNumber of views: 2491