Faculty Bibliography

Quantitative, volumetric analysis of Magnetic Resonance Imaging (MRI) is a fundamental way researchers study the brain in a host of neurological conditions including normal maturation and aging. Despite the availability of open-source brain segmentation software, widespread clinical adoption of volumetric analysis has been hindered due to processing times and reliance on manual corrections. Here, we extend the use of deep learning models from proof-of-concept, as previously reported, to present a comprehensive segmentation of cortical and deep gray matter brain structures matching the standard regions of aseg+ aparc included in the commonly used open-source tool, Freesurfer. The work presented here provides a real-life, rapid deep learning-based brain segmentation tool to enable clinical translation as well as research application of quantitative brain segmentation. The advantages of the presented tool include short (~ 1 minute) processing time and improved segmentation quality. This is the first study to perform quick and accurate segmentation of 102 brain regions based on the surface-based protocol (DMK protocol), widely used by experts in the field. This is also the first work to include an expert reader study to assess the quality of the segmentation obtained using a deep-learning-based model. We show the superior performance of our deep-learning-based models over the traditional segmentation tool, Freesurfer. We refer to the proposed deep learning-based tool as DARTS (DenseUnet-based Automatic Rapid Tool for brain Segmentation)

Every year in North America, approximately 3 million patients are evaluated for spinal injury. Of blunt trauma patients presenting to the emergency department, 3% to 4% will have a cervical spine injury, and up to 18% will suffer a thoracolumbar spine injury. Failure to identify an unstable spine injury can lead to devastating outcomes.

Spinal dural fistulas (SDAVFs) occasionally arise from the same segmental artery as the radiculomedullary branch to the anterior spinal artery. In such cases, selective fistula embolization that does not endanger the anterior spinal artery is not possible, and surgical fistula disconnection is recommended. We present an exceptional case in which rational embolization strategy of SDAVF was feasible because of separate origins from a common segmental artery pedicle of the ventral radiculomedullary artery and the dorsal radicular artery branch supplying the fistula.