Neuroimaging clinics of North America
-
Each orbit is a complex structure housing the globe, multiple cranial nerves, muscles, vascular structures, which support the visual sense. Many of these structures have been delineated in careful detail by anatomists but remain beyond the resolution of conventional imaging techniques. With the advances of higher resolution MR, surface coil usage, and thinner section computed tomographic images, the ability to resolve these small structures continues to improve, allowing radiologists to provide more detailed anatomic descriptions for preoperative and pretreatment planning.
-
The root of the neck is the junctional anatomic structure between the thoracic inlet, the axilla, and the lower neck. The detailed radiological anatomy of this critical area is discussed in this review.
-
Traumatic brain injury disrupts the complex anatomy of the afferent and efferent visual pathways. Injury to the afferent pathway can result in vision loss, visual field deficits, and photophobia. Injury to the efferent pathway primarily causes eye movement abnormalities resulting in ocular misalignment and double vision. Injury to both the afferent and efferent systems can result in significant visual disability.
-
The following article details the muscular anatomy of the head and neck, including insertion, origin, action and innervation, organized by anatomic subunit and/or major action. This article also describes the spaces of the head and neck, including boundaties and contents. Finally, cervical lymph nodes are addressed according to anatomic location and lymphatic drainage.
-
Neuroimaging Clin. N. Am. · Nov 2020
ReviewOverview of Machine Learning Part 1: Fundamentals and Classic Approaches.
The extensive body of research and advances in machine learning (ML) and the availability of a large volume of patient data make ML a powerful tool for producing models with the potential for widespread deployment in clinical settings. This article provides an overview of the classic supervised and unsupervised ML methods as well as fundamental concepts required for understanding how to develop generalizable and high-performing ML applications. It also describes the important steps for developing a ML model and how decisions made in these steps affect model performance and ability to generalize.