Journal of neuroimaging : official journal of the American Society of Neuroimaging
-
Review Meta Analysis
Artificial intelligence/machine learning for neuroimaging to predict hemorrhagic transformation: Systematic review/meta-analysis.
Early and reliable prediction of hemorrhagic transformation (HT) in patients with acute ischemic stroke (AIS) is crucial for treatment decisions and early intervention. The purpose of this study was to conduct a systematic review and meta-analysis on the performance of artificial intelligence (AI) and machine learning (ML) models that utilize neuroimaging to predict HT. ⋯ AI/ML models can reliably predict the occurrence of HT in AIS patients. More prospective studies are needed for subgroup analyses and higher clinical certainty and usefulness.
-
The optic nerve sheath diameter (ONSD) is a commonly used estimate of intracranial pressure (ICP). The rationale behind this is that pressure changes in the cerebrospinal fluid affect the optic nerve subarachnoid space (ONSAS) thickness. Still, possible effects on other compartments of the optic nerve sheath (ONS) have not been studied. This is the first study ever to analyze all measurable compartments of the ONS for associations with elevated ICP. ⋯ The results from this study challenge the current understanding of the mechanism behind the association between ICP and ONSD. Contrary to the common opinion that ONSAS is the only affected compartment, this study shows a more complex picture. It suggests that all ONS compartments may add value in predicting changes in ICP.
-
High-resolution magnetic resonance imaging (HR-MRI) can provide valuable insights into the histopathological characteristics of moyamoya disease (MMD). However, the patterns of vessel wall contrast enhancement have not been well established. We aimed to identify the contrast enhancement patterns of the vessel walls associated with acute cerebral infarction using HR-MRI in MMD. ⋯ Concentric wall enhancement was a significant predictor of acute cerebral infarction in patients with MMD.
-
Meningiomas are the most common neoplasms of the central nervous system, accounting for approximately 40% of all brain tumors. Surgical resection represents the mainstay of management for symptomatic lesions. Preoperative planning is largely informed by neuroimaging, which allows for evaluation of anatomy, degree of parenchymal invasion, and extent of peritumoral edema. ⋯ We also summarize the role of advanced imaging techniques, including magnetic resonance perfusion and spectroscopy, for the preoperative evaluation of meningiomas. In addition, we describe the potential impact of emerging technologies, such as artificial intelligence and machine learning, on meningioma diagnosis and management. A strong foundation of knowledge in the latest meningioma imaging techniques will allow the neuroradiologist to help optimize preoperative planning and improve patient outcomes.
-
Magnetic resonance imaging (MRI) is heavily relied upon for the diagnosis and monitoring of multiple sclerosis (MS), a chronic, demyelinating disease of the central nervous system. Serum biomarkers may serve as an accessible tool for increasing sensitivity, improving accessibility, corroborating symptoms, and providing additional data to guide clinical management. This scoping review investigates the current understanding of how the serum biomarker glial fibrillary acidic protein (sGFAP) relates to brain MRI metrics. ⋯ These results highlight that while sGFAP may not be specific for MS, it may have utility for increasing sensitivity in postdiagnosis monitoring of MS progression.