In a recent study, deep learning algorithms proved superior to conventional machine learning frameworks for automatically detecting a certain type of brain lesion on magnetic resonance imaging  scans. In particular, a type of deep learning algorithm called a convolutional neural network performed best of all. The performance of the convolutional neural network was improved upon when researchers added a new way to incorporate spatial information.Read the whole story at Bioengineering Today: Deep Learning Algorithms Can Detect Subtle Brain Lesions.