Abstract
Background and PurposeTo develop a fully automatic algorithm for the magnetic resonance imaging (MRI) identification of patients with spontaneous intracranial hypotension (SIH).Material and MethodsA support vector machine (SVM) was trained with structured reports of 140 patients with clinically suspected SIH. Venous sinuses and basal cisterns were segmented on contrast-enhanced T1-weighted MPRAGE (Magnetization Prepared-Rapid Gradient Echo) sequences using a convolutional neural network (CNN). For the segmented sinuses and cisterns, 56 radiomic features were extracted, which served as input data for the SVM. The algorithm was validated with an independent cohort of 34 patients with proven cerebrospinal fluid (CSF) leaks and 27 patients who had MPRAGE scans for unrelated reasons.ResultsThe venous sinuses and the suprasellar cistern had the best discriminative power to separate SIH and non-SIH patients. On a combined score with 2 points, mean SVM score was 1.41 (±0.60) for the SIH and 0.30 (±0.53) for the non-SIH patients (p < 0.001). Area under the curve (AUC) was 0.91.ConclusionA fully automatic algorithm analyzing a single MRI sequence separates SIH and non-SIH patients with a high diagnostic accuracy. It may help to consider the need of invasive diagnostics and transfer to a SIH center.
Highlights
Spontaneous intracranial hypotension (SIH) is an orthostatic headache syndrome that in almost all cases is caused by spinal cerebrospinal fluid (CSF) leaks [1]
Dobrocky et al 2019 proposed a scoring system which has been later termed the Bern score where pachymeningeal contrast enhancement, engorgement of venous sinuses and effacement of the suprasellar cistern of 4.0 mm or less were shown to be the most important discriminating features and weighted with 2 points each while subdural fluid collection, effacement of the prepontine cistern of 5 mm or less, and a mamillopontine distance of 6.5 mm or less were weighted with 1 point each resulting into a maximum score of 9 [8]
We analyzed 34 patients with a CSF leak proven by conventional myelography, CT myelography or digital subtraction myelography (DSM) between 2018 and 2020 and no prior spontaneous intracranial hypotension (SIH)-related treatment and 27 patients who underwent a contrastenhanced T1-weighted MPRAGE sequence for unrelated reasons and had inconspicuous findings
Summary
Spontaneous intracranial hypotension (SIH) is an orthostatic headache syndrome that in almost all cases is caused by spinal cerebrospinal fluid (CSF) leaks [1]. Patients with total scores of 2 points or fewer were classified as having a low, with 3–4 points as having an intermediate, and with 5 or more points as having a high probability for a spinal CSF leak; some of the features (especially the engorgement of the venous sinuses) are somewhat arbitrary in definition which can lead to a different assessment for different raters. We hypothesized that these and other shape changes of the venous sinuses are better detected by a machine learning algorithm. The algorithm was validated with an independent cohort of 34 patients with proven cerebrospinal fluid (CSF) leaks and 27 patients who had MPRAGE scans for unrelated reasons
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
