Detecting Brain Lesions in Multiple Sclerosis Patients with Deep Learning

One of the most promising applications of deep learning is image analysis (as part of computer vision), e.g. for image segmentation or classification. Whereas segmentation yields a probability distribution (also known as mask) for each class per pixel (i.e. each pixel belongs to 1 of K classes), classification does so for the whole image (i.e. each image belongs to 1 of K classes). Software solutions can be encountered nearly everywhere nowadays, for example in medical image analysis. In clinical research, where novel medications are tested, sometimes it is of interest if a drug can change the condition of a tissue, e.g. Medical images are created by imaging techniques such as medical ultrasound, X-ray, computed tomography (CT), magnetic resonance imaging (MRI), or even regular microscopes.