Robust Brain Extraction Tool for Nonenhanced CT and CT Angiography: CTA-BET

Abstract

Purpose: To develop and evaluate a deep learning–based brain extraction model, CTA-BET, capable of providing accurate brain segmentation for CT angiography (CTA) and non–contrast-enhanced CT (NCCT) images. Materials and Methods: In this retrospective study, CTA-BET was trained using CTA data from multi-institutional cohorts (n = 100 patients) and validated on an external CTA dataset (n = 50 patients). NCCT validation was performed using the publicly available CQ500 dataset (n = 132 patients). The model’s performance was compared with five benchmark noncommercial brain extraction tools. Dice score, Hausdorff distance, and z score–normalized histograms were used to evaluate segmentation performance. Results: The CTA-BET model outperformed all benchmark models, achieving a mean Dice score of 0.99 (95% CI: 0.99, 0.99) on CTA data (P