Penumbra Detection With Oxygen Extraction Fraction Using Magnetic Susceptibility in Patients With Acute Ischemic Stroke.

BACKGROUND: The oxygen extraction fraction (OEF) has been applied to identify ischemic penumbral tissue, but is difficult to use in an urgent care setting. This study aimed to investigate whether an OEF map generated via magnetic resonance quantitative susceptibility mapping (QSM) could help identify the ischemic penumbra in patients with acute ischemic stroke. MATERIALS AND METHODS: This prospective imaging study included 21 patients with large anterior circulation vessel occlusion who were admitted <24 h after stroke onset and 21 age-matched healthy controls. We identified the ischemic penumbra as the region with a Tmax of >6 s during dynamic susceptibility contrast-magnetic resonance imaging (DSC-MRI) and calculated the perfusion-core mismatch ratio between the ischemic penumbra and infarct core volumes. The OEF values were measured based on magnetic susceptibility differences between the venous structures and brain tissues using rapid QSM acquisition. Volumes with increased OEF values were compared to the ischemic penumbra volumes using an anatomical template. RESULTS: Eleven patients had a perfusion-core mismatch ratio of ≥1.8, and reperfusion therapy was recommended. In these patients, the volumes with increased OEF values of >51.5%, which was defined using the anterior circulation territory OEF values from the 21 healthy controls, were positively correlated with the ischemic penumbra volumes (r = 0.636, 95% CI: 0.059 to 0.895, P = 0.035) and inversely correlated with the 30-day change in the National Institutes of Health Stroke Scale scores (r = -0.624, 95% CI: -0.891 to -0.039, P = 0.041). CONCLUSION: Tissue volumes with increased OEF values could predict ischemic penumbra volumes based on DSC-MRI, highlighting the potential of the QSM-derived OEF map as a penumbra biomarker to guide treatment selection in patients with acute ischemic stroke.

Machine learning trained with quantitative susceptibility mapping to detect mild cognitive impairment in Parkinson's disease.

BACKGROUND: Cognitive decline is commonly observed in Parkinson's disease (PD). Identifying PD with mild cognitive impairment (PD-MCI) is crucial for early initiation of therapeutic interventions and preventing cognitive decline. OBJECTIVE: We aimed to develop a machine learning model trained with magnetic susceptibility values based on the multi-atlas label-fusion method to classify PD without dementia into PD-MCI and normal cognition (PD-CN). METHODS: This multicenter observational cohort study retrospectively reviewed 61 PD-MCI and 59 PD-CN cases for the internal validation cohort and 22 PD-MCI and 21 PD-CN cases for the external validation cohort. The multi-atlas method parcellated the quantitative susceptibility mapping (QSM) images into 20 regions of interest and extracted QSM-based magnetic susceptibility values. Random forest, extreme gradient boosting, and light gradient boosting were selected as machine learning algorithms. RESULTS: All classifiers demonstrated substantial performances in the classification task, particularly the random forest model. The accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve for this model were 79.1%, 77.3%, 81.0%, and 0.78, respectively. The QSM values in the caudate nucleus, which were important features, were inversely correlated with the Montreal Cognitive Assessment scores (right caudate nucleus: r = -0.573, 95% CI: -0.801 to -0.298, p = 0.003; left caudate nucleus: r = -0.659, 95% CI: -0.894 to -0.392, p < 0.001). CONCLUSIONS: Machine learning models trained with QSM values successfully classified PD without dementia into PD-MCI and PD-CN groups, suggesting the potential of QSM values as an auxiliary biomarker for early evaluation of cognitive decline in patients with PD.

[Primary central nervous system vasculitis: a differential diagnosis of longitudinally extensive spinal cord lesion].

A 63-year-old man was admitted to our hospital with a 2-month history of anxiety. He presented with cognitive impairment and muscle weakness. On MRI, T2-weighted images showed longitudinally extensive spinal cord lesion (LESCL) from C2 to T6 and gadolinium-enhanced T1-weighted images showed fan-shaped multiple linear enhancements converging to the lateral ventricles. He was diagnosed as primary central nervous system vasculitis (PCNSV) by brain biopsy. After using high dose corticosteroids, cognitive impairment and muscle weakness were dramatically improved. In patients with cognitive impairment, PCNSV should be included in the differential diagnosis of LESCL.