Pushing the limits of low-cost ultra-low-field MRI by dual-acquisition deep learning 3D superresolution.

PURPOSE: Recent development of ultra-low-field (ULF) MRI presents opportunities for low-power, shielding-free, and portable clinical applications at a fraction of the cost. However, its performance remains limited by poor image quality. Here, a computational approach is formulated to advance ULF MR brain imaging through deep learning of large-scale publicly available 3T brain data. METHODS: A dual-acquisition 3D superresolution model is developed for ULF brain MRI at 0.055 T. It consists of deep cross-scale feature extraction, attentional fusion of two acquisitions, and reconstruction. Models for T1 -weighted and T2 -weighted imaging were trained with 3D ULF image data sets synthesized from the high-resolution 3T brain data from the Human Connectome Project. They were applied to 0.055T brain MRI with two repetitions and isotropic 3-mm acquisition resolution in healthy volunteers, young and old, as well as patients. RESULTS: The proposed approach significantly enhanced image spatial resolution and suppressed noise/artifacts. It yielded high 3D image quality at 0.055 T for the two most common neuroimaging protocols with isotropic 1.5-mm synthetic resolution and total scan time under 20 min. Fine anatomical details were restored with intrasubject reproducibility, intercontrast consistency, and confirmed by 3T MRI. CONCLUSION: The proposed dual-acquisition 3D superresolution approach advances ULF MRI for quality brain imaging through deep learning of high-field brain data. Such strategy can empower ULF MRI for low-cost brain imaging, especially in point-of-care scenarios or/and in low-income and mid-income countries.

A low-cost and shielding-free ultra-low-field brain MRI scanner.

Magnetic resonance imaging is a key diagnostic tool in modern healthcare, yet it can be cost-prohibitive given the high installation, maintenance and operation costs of the machinery. There are approximately seven scanners per million inhabitants and over 90% are concentrated in high-income countries. We describe an ultra-low-field brain MRI scanner that operates using a standard AC power outlet and is low cost to build. Using a permanent 0.055 Tesla Samarium-cobalt magnet and deep learning for cancellation of electromagnetic interference, it requires neither magnetic nor radiofrequency shielding cages. The scanner is compact, mobile, and acoustically quiet during scanning. We implement four standard clinical neuroimaging protocols (T1- and T2-weighted, fluid-attenuated inversion recovery like, and diffusion-weighted imaging) on this system, and demonstrate preliminary feasibility in diagnosing brain tumor and stroke. Such technology has the potential to meet clinical needs at point of care or in low and middle income countries.

Optic neuritis as the initial clinical presentation of limbic encephalitis: a case report.

BACKGROUND: Limbic encephalitis is characterized by rapid onset of working memory deficit, mood changes, and often seizures. The condition has a strong paraneoplastic association, but not all cases are invariably due to tumors. CASE PRESENTATION: We present a case of limbic encephalitis in a Chinese patient who initially presented to our hospital with optic neuritis and no other neurological symptoms. The diagnosis was made radiologically, and cognitive and neurological symptoms did not occur until 5 months later. Extensive investigations for autoimmune, infective, and neoplastic causes were all negative. A working diagnosis of paraneoplastic neurological syndrome was made, and the patient is being managed with high-dose steroid therapy according to the Optic Neuritis Treatment Trial protocol during relapses, as well as with tumor surveillance. CONCLUSIONS: This case highlights ocular symptoms as important clues for diagnosing neurological diseases, as well as autoimmune encephalitis as an important differential diagnosis in the management of "idiopathic" optic neuritis in the Chinese population.

Antiplatelet Resumption after Antiplatelet-Related Intracerebral Hemorrhage: A Retrospective Hospital-Based Study.

BACKGROUND: Antiplatelet resumption in patients who developed intracerebral hemorrhage (ICH) while on antiplatelet therapy (antiplatelet-related ICH) represents an important medical dilemma. We aimed to study the long-term cardiovascular outcomes of antiplatelet-related ICH survivors, and the risk of recurrent ICH with antiplatelet resumption. METHODS: This was an observational study of 109 antiplatelet-related ICH survivors. The clinical end points were recurrent ICH, ischemic vascular events, and vascular death (fatal ICH or ischemic vascular events). Predictors of recurrent ICH and vascular death were derived using a multivariable Cox regression model. RESULTS: The median duration of follow-up was 3.5 years (interquartile range, 1.6-5.8 years). Ischemic vascular events were more common than recurrent ICHs (6.8 per 100 patient-years vs. 2.6 per 100 patient-years; P = 0.028). Antiplatelet use was not associated with an elevated risk of recurrent ICH (hazard ratio [HR], 1.11, 95% confidence interval [CI], 0.27-4.62). A mean follow-up systolic blood pressure of >140 mmHg increased the risk of both recurrent ICH (HR, 4.28; 95% CI, 1.01-18.11) and vascular death (HR, 11.14; 95% CI, 2.72-45.62). Cerebral amyloid angiopathy (CAA) was an independent predictor for recurrent ICH (HR, 24.34; 95% CI, 2.80-211.47). CONCLUSIONS: Antiplatelet resumption after antiplatelet-related ICH did not appear to carry a clinically significant risk of recurrent ICH, whereas inadequate blood pressure control and CAA contributed to a more robust risk. Antiplatelet resumption should be considered, especially in survivors with adequate blood pressure control and without CAA.