MedElevator Войти в исследования
← Поиск публикаций

DOI 10.1007/s00062-021-01099-x

Медицинская библиотека · Clinical neuroradiology · 2021

Support Vector Machine-based Spontaneous Intracranial Hypotension Detection on Brain MRI.

Arnold Philipp G, Kaya Emre, Reisert Marco, Lützen Niklas, Dovi-Akué Philippe, Fung Christian, Beck Jürgen, Urbach Horst

СтатьяПеревод пока не подготовлен

Аннотация

BACKGROUND AND PURPOSE: To develop a fully automatic algorithm for the magnetic resonance imaging (MRI) identification of patients with spontaneous intracranial hypotension (SIH).

MATERIAL AND

METHODS

A 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.

RESULTS

The 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.

CONCLUSION

A 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.

Для цитирования: Arnold Philipp G, Kaya Emre, Reisert Marco, Lützen Niklas, Dovi-Akué Philippe, Fung Christian, Beck Jürgen, Urbach Horst. Support Vector Machine-based Spontaneous Intracranial Hypotension Detection on Brain MRI.. Clinical neuroradiology. 2021. DOI: 10.1007/s00062-021-01099-x.

Предметные рубрики MeSH

Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.