Recent advances in deep learning have brought many breakthroughs in medical image analysis by providing more robust and consistent tools for the detection, classification and quantification of patterns in medical images. Specifically, analysis of advanced modalities such as computed tomography (CT) and magnetic resonance imaging (MRI) has benefited most from the data-driven nature of deep learning. This is because the need of knowledge and experience-oriented feature engineering process can be circumvented by automatically deriving representative features from the complex high dimensional medical images with respect to the target tasks. In this paper, we will review recent applications of deep learning in the analysis of CT and MR images in a range of tasks and target organs. While most applications are focused on the enhancement of the productivity and accuracy of current diagnostic analysis, we will also introduce some promising applications which will significantly change the current workflow of medical imaging. We will conclude by discussing opportunities and challenges of applying deep learning to advanced imaging and suggest future directions in this domain.
Classification ; Diagnostic Imaging ; Efficiency ; Learning* ; Magnetic Resonance Imaging*

Cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy (CADASIL) is a single-gene disease caused by mutations in the neurogenic locus notch homolog protein 3 (NOTCH3) gene. The spectrum of clinical manifestations is broad, ranging from asymptomatic to typical ischemic stroke, and mainly depends on the location of the mutations. We describe the case of a 76-year-old female without apparent neurological deficits. However, brain magnetic resonance imaging revealed confluent lesions in the white matter. Direct sequencing of the NOTCH3 gene revealed a novel pathogenic mutation, c.811T>A, which results in a mild phenotype. Therefore, this report will expand the current knowledge in regards to the mutations that can cause CADASIL.

Cardiac papillary fibroelastomas are associated with a high risk of systemic embolization in spite of benign nature. We report a case of 85-year-old patient with left supraclinoid internal carotid artery occlusion who treated with aspiration thrombectomy. Despite of the absence of residual mass on echocardiography, we could analyze pathologic specimens using retrieved embolus and confirmed cardiac papillary fibroelastoma as a rare cause of stroke.