Congratulations to our team working on computer-aided detection of brain metastases! "Deep-learning system identifies difficult-to-detect brain metastases" is currently the lead story and was selected as the Editor's Choice article for Physics World, the monthly physics research magazine produced by the Institute of Physics. Read the article.
The article explores our deep-learning-based computer-aided detection (CAD) system to identify difficult-to-detect brain metastases on MR images. It explores research presented at the recent ASTRO Annual Meeting, in which Devon Godfrey, PhD, "explained that the researchers designed the convolutional neural network–based CAD system specifically to improve the detection and segmentation of hard-to-detect retrospectively identified metastases and very small prospectively identified metastases." Dr. Godfrey and colleagues – former resident Andrew Fairchild, MD; current resident Brad Ackerson, MD; and faculty Joseph Salama, MD; John Kirkpatrick, MD, PhD; and Scott Floyd, MD, PhD – described the testing and validation of the system in an article published in the Red Journal in October. Learn more.