Summary: 80% of patients with multiple sclerosis remain disease-free for the long term following an autologous hematopoietic stem cell transplant. Every day, one person in Switzerland is diagnosed with multiple sclerosis. MS is an autoimmune disease in which the body's own immune system attacks the myelin sheath of the nerve cells in the brain and spinal cord. The disease leads to paralysis, pain and permanent fatigue, among other symptoms. Fortunately, there have been great advances in therapies in recent decades.

The automated detection of cortical lesions (CLs) in patients with multiple sclerosis (MS) is a challenging task that, despite its clinical relevance, has received very little attention. Accurate detection of the small and scarce lesions requires specialized sequences and high or ultra-high field MRI. For supervised training based on multimodal structural MRI at 7T, two experts generated ground truth segmentation masks of 60 patients with 2014 CLs. We implemented a simplified 3D U-Net with three resolution levels (3D U-Net-). By increasing the complexity of the task (adding brain tissue segmentation), while randomly dropping input channels during training, we improved the performance compared to the baseline. Considering a minimum lesion size of 0.75 {\mu}L, we achieved a lesion-wise cortical lesion detection rate of 67% and a false positive rate of 42%. However, 393 (24%) of the lesions reported as false positives were post-hoc confirmed as potential or definite lesions by an expert. This indicates the potential of the proposed method to support experts in the tedious process of CL manual segmentation.

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.