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

2025/10/28 by Mustafa Ahmed Mahmutoglu, Aditya Rastogi, Yeong Chul Yun +8 · 1 voice · 1 citation
Neuroscience · Computer Science · #Brain Tumor Detection and Classification #Medical Image Segmentation Techniques #Advanced Neural Network Applications

paper · doi:10.1148/ryai.240847

Abstract

CTA-BET, a deep learning–based brain extraction model, achieved accurate and robust performance on CT angiography and non–contrast-enhanced CT datasets and significantly outperformed existing noncommercial tools, with potential applicability to diverse clinical and research settings.

Citations

• Deep Learning for Detecting Cerebral Aneurysms with CT Angiography

Cited by

• End-to-End Autonomous Quantification of Brain Aneurysm and Parent Artery Morphology at CT Angiography

Discussions

• #ThrowbackThursday – Extending brain extraction tools beyond non-enhanced CT (Dec 2025) https://doi.org/10.1148/ryai.240847 #ML #DeepLearning #ArtificialIntelligence [bsky, 8 points, 0 comments]

Related

• SAM vs BET: A Comparative Study for Brain Extraction and Segmentation of Magnetic Resonance Images using Deep Learning
• Deepbet: Fast brain extraction of T1-weighted MRI using Convolutional Neural Networks
• VesselShot: Few-shot learning for cerebral blood vessel segmentation
• Commercial AI Model Diagnostic Accuracy for Intracranial Large- and Medium-Vessel Occlusion at Emergency CT Angiography
• Deep Learning Angiography (DLA): Three-dimensional C-arm Cone Beam CT Angiography Using Deep Learning