Deep learning has dramatically improved object recognition, speech recognition, medical image analysis and many other fields. Optical coherence tomography (OCT) has become a standard of care imaging modality for ophthalmology. We asked whether deep learning could be used to segment cornea OCT images. Using a custom-built ultrahigh-resolution OCT system, we scanned 72 healthy eyes and 70 keratoconic eyes. In total, 20,160 images were labeled and used for the training in a supervised learning approach. A custom neural network architecture called CorneaNet was designed and trained. Our results show that CorneaNet is able to segment both healthy and keratoconus images with high accuracy (validation accuracy: 99.56%). Thickness maps of the three main corneal layers (epithelium, Bowman's layer and stroma) were generated both in healthy subjects and subjects suffering from keratoconus. CorneaNet is more than 50 times faster than our previous algorithm. Our results show that deep learning algorithms can be used for OCT image segmentation and could be applied in various clinical settings. In particular, CorneaNet could be used for early detection of keratoconus and more generally to study other diseases altering corneal morphology.

The results suggest that MR imaging of the intervertebral disk, using sodium imaging and T2 mapping, can help characterize different component changes and that both of these methods are to some degree related to the Pfirrmann score.

This study demonstrates the feasibility of a combined T2 mapping approach for the facet joints and intervertebral discs using a single axial slab.

The introduction of hepatobiliary contrast agents, most notably gadoxetic acid (GA), has expanded the role of MRI, allowing not only a morphologic but also a functional evaluation of the hepatobiliary system. The mechanism of uptake and excretion of gadoxetic acid via transporters, such as organic anion transporting polypeptides (OATP1,3), multidrug resistance-associated protein 2 (MRP2) and MRP3, has been elucidated in the literature. Furthermore, GA uptake can be estimated on either static images or on dynamic imaging, for example, the hepatic extraction fraction (HEF) and liver perfusion. GA-enhanced MRI has achieved an important role in evaluating morphology and function in chronic liver diseases (CLD), allowing to distinguish between the two subgroups of nonalcoholic fatty liver diseases (NAFLD), simple steatosis and nonalcoholic steatohepatitis (NASH), and help to stage fibrosis and cirrhosis, predict liver transplant graft survival, and preoperatively evaluate the risk of liver failure if major resection is planned. Finally, because of its noninvasive nature, GA-enhanced MRI can be used for long-term follow-up and post-treatment monitoring. This review article aims to describe the current role of GA-enhanced MRI in quantifying liver function in a variety of hepatobiliary disorders.