Magnetic Resonance Imaging Signs of Idiopathic Intracranial Hypertension

IMPORTANCE: The magnetic resonance imaging (MRI) criteria currently used to diagnose idiopathic intracranial hypertension (IIH) are based on expert opinion and have limited accuracy. Additional neuroimaging signs have been proposed and used with contradictory results; thus, prospective evidence is needed to improve diagnostic accuracy. OBJECTIVE: To provide evidence-based, accurate MRI signs for IIH diagnosis. DESIGN, SETTING, AND PARTICIPANTS: This prospective cohort study was conducted from January 2018 to May 2021 with 3 validation cohorts at 2 Danish headache centers and with 3 independent international cohorts. Consecutive patients with suspected IIH were enrolled. Eligibility required the clinical suspicion of IIH, age 18 years or older, and written informed consent. The validation cohorts comprised patients with confirmed IIH from Austria and the US, and patients without IIH from the US. Data analysis was performed from December 2021 to August 2023. EXPOSURE: Standardized diagnostic workup was performed to classify cases according to current criteria, and blinded evaluation of cerebral radiological diagnostics and papilledema was performed. MAIN OUTCOMES AND MEASURES: The primary outcomes were MRI signs associated with IIH as assessed by univariate analyses. An MRI score estimating papilledema was calculated using machine learning. Internal validation of associations with lumbar puncture opening pressure and outcome and external validation of accuracy were performed in 3 cohorts. RESULTS: Of 192 eligible patients (185 women [96.4%]; median [IQR] age, 28.0 [23.0-35.0] years), 110 were classified as having IIH, 4 as having probable IIH, and 1 as having suspected IIH without papilledema; 77 did not have IIH and served as controls, with corresponding age, sex, and weight. Papilledema at diagnosis was associated with perioptic subarachnoid space distension (56 patients [68.3%] vs 21 patients [41.2%]), posterior globe flattening (53 patients [66.3%] vs 10 patients