Search for: All records

The feasibility of ultrafast (1.7 s) ventilation MRI with a 1 × 1 × 50 mm³voxel size is demonstrated using hyperpolarized propane gas contrast agent in excised rabbit lungs on a 0.35 T clinical MRI scanner without any scanner modification. 

Abstract Hyperpolarized¹²⁹Xe gas was FDA‐approved as an inhalable contrast agent for magnetic resonance imaging of a wide range of pulmonary diseases in December 2022. Despite the remarkable success in clinical research settings, the widespread clinical translation of HP¹²⁹Xe gas faces two critical challenges: the high cost of the relatively low‐throughput hyperpolarization equipment and the lack of¹²⁹Xe imaging capability on clinical MRI scanners, which have narrow‐bandwidth electronics designed only for proton (¹H) imaging. To solve this translational grand challenge of gaseous hyperpolarized MRI contrast agents, here we demonstrate the utility of batch‐mode production of proton‐hyperpolarized diethyl ether gas via heterogeneous pairwise addition of parahydrogen to ethyl vinyl ether. An approximately 0.1‐liter bolus of hyperpolarized diethyl ether gas was produced in 1 second and injected in excised rabbit lungs. Lung ventilation imaging was performed using sub‐second 2D MRI with up to 2×2 mm²in‐plane resolution using a clinical 0.35 T MRI scanner without any modifications. This feasibility demonstration paves the way for the use of inhalable diethyl ether as a gaseous contrast agent for pulmonary MRI applications using any clinical MRI scanner. 

Abstract Analysis of 3D medical imaging data has been a large topic of focus in the area of Machine Learning/Artificial Intelligence, though little work has been done in algorithmic (particularly unsupervised) analysis of neonatal brain MRI’s. A myriad of conditions can manifest at an early age, including neonatal encephalopathy (NE), which can result in lifelong physical consequences. As such, there is a dire need for better biomarkers of NE and other conditions. The objective of the study is to improve identification of anomalies and prognostication of neonatal MRI brain scans. We introduce a framework designed to support the analysis and assessment of neonatal MRI brain scans, the results of which can be used as an aid to neuroradiologists. We explored the efficacy of the framework through iterations of several deep convolutional Autoencoder (AE) unsupervised modeling architectures designed to learn normalcy of the neonatal brain structure. We tested this framework on the developing human connectome project (dHCP) dataset with 97 patients that were previously categorized by severity. Our framework demonstrated the model’s ability to identify and distinguish subtle morphological signatures present in brain structures. Normal and abnormal neonatal brain scans can be distinguished with reasonable accuracy, correctly categorizing them in up to 83% of cases. Most critically, new brain anomalies originally missed during the radiological reading were identified and corroborated by a neuroradiologist. This framework and our modeling approach demonstrate an ability to improve prognostication of neonatal brain conditions and are able to localize new anomalies.