Machine Learning Makes Its Mark On Medical Imaging And Therapy

At the APS March Meeting, a focus session examined the latest medical applications of artificial intelligence and machine learning. Alison Deatsch from the University of Wisconsin, Madison discussed the use of deep learning for diagnosing and monitoring brain disease. Neuroimaging, such as MRI, functional MRI, PET and SPECT, could fill the gap for reliable tools for diagnosis and progression monitoring. Deep learning methods such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are being used to maximize information output from neurological images. This shift could advance medical diagnosis and treatment.