Journal
IEEE ACCESS
Volume 11, Issue -, Pages 116903-116918Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2023.3326342
Keywords
Skull stripping; brain extraction; MRI; U-Net; GAN; ADNI; CC-12; LPBA40; NFBS; OASIS
Ask authors/readers for more resources
This study proposes a novel posture correction skull stripping (PCSS) method to improve the accuracy and consistency of skull stripping by adjusting the subject's head angle and position and utilizing machine learning techniques. Experimental results show that the PCSS method outperforms current state-of-the-art techniques in skull stripping performance.
A subject's head position in magnetic resonance imaging (MRI) scanners can vary significantly with the imaging environment and disease status. This variation is known to influence the accuracy of skull stripping (SS), a method to extract the brain region from the whole head image, which is an essential initial step to attain high performance in various neuroimaging applications. However, existing SS methods have failed to accommodate this wide range of variation. To achieve accurate, consistent, and fast SS, we introduce a novel two-stage methodology that we call posture correction skull stripping (PCSS): the first involves adjusting the subject's head angle and position, and the second involves the actual SS to generate the brain mask. PCSS also incorporates various machine learning techniques, such as a weighted loss function, adversarial training from generative adversarial networks, and ensemble methods. Thorough evaluations conducted on five publicly accessible datasets show that the PCSS method outperforms current state-of-the-art techniques in SS performance, achieving an average increase of 1.38 points on the Dice score and demonstrating the contributions of each PCSS component technique.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available