干旱区生态环境知识资源中心(Arid): Localized Motion Artifact Reduction on Brain MRI Using Deep Learning with Effective Data Augmentation Techniques

Arid

DOI	10.1109/IJCNN52387.2021.9534191
	Localized Motion Artifact Reduction on Brain MRI Using Deep Learning with Effective Data Augmentation Techniques
	Zhao, Yijun; Ossowski, Jacek; Wang, Xuming; Li, Shangjin; Devinsky, Orrin; Martin, Samantha P.; Pardoe, Heath R.
通讯作者	Zhao, YJ (corresponding author)，Fordham Univ, 113 60th St, New York, NY 10023 USA.
会议名称	International Joint Conference on Neural Networks (IJCNN)
会议日期	JUL 18-22, 2021
会议地点	ELECTR NETWORK
英文摘要	In-scanner motion degrades the quality of magnetic resonance imaging (MRI) thereby reducing its utility in the detection of clinically relevant abnormalities. We collaborate with doctors from NYU Langone's Comprehensive Epilepsy Center and apply a deep learning-based MRI artifact reduction model (DMAR) to correct head motion artifacts in brain MRI scans. Specifically, DMAR employs a two-stage approach: in the first, degraded regions are detected using the Single Shot Multibox Detector (SSD), and in the second, the artifacts within the found regions are reduced using a convolutional autoencoder (CAE). We further introduce a set of novel data augmentation techniques to address the high dimensionality of MRI images and the scarcity of available data. As a result, our model was trained on a large synthetic dataset of 225,000 images generated using 375 whole brain T1-weighted MRI scans from the OASIS-1 dataset. DMAR visibly reduces image artifacts when validated using real-world artifact-affected scans from the multi-center ABIDE study and proprietary data collected at NYU. Quantitatively, depending on the level of degradation, our model achieves a 27.8%-48.1% reduction in RMSE and a 2.88-5.79 dB gain in PSNR on a 5000-sample set of synthetic images. For real-world data without ground-truth, our model reduced the variance of image voxel intensity within artifact-affected brain regions (p = 0.014 ).
英文关键词	MRI motion artifact reduction deep learning object detection k-space
来源出版物	2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)
ISSN	2161-4393
出版年	2021
ISBN	978-0-7381-3366-9
出版者	IEEE
类型	Proceedings Paper
语种	英语
开放获取类型	Green Submitted
收录类别	CPCI-S
WOS记录号	WOS:000722581707016
WOS关键词	CNN
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Engineering, Electrical & Electronic
WOS研究方向	Computer Science ; Engineering
资源类型	会议论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/379064
作者单位	[Zhao, Yijun; Wang, Xuming; Li, Shangjin] Fordham Univ, 113 60th St, New York, NY 10023 USA; [Ossowski, Jacek] QS Investors LLC, New York, NY 10022 USA; [Devinsky, Orrin; Martin, Samantha P.; Pardoe, Heath R.] NYU, Grossman Sch Med, 145 East 32nd St, New York, NY USA
推荐引用方式 GB/T 7714	Zhao, Yijun,Ossowski, Jacek,Wang, Xuming,et al. Localized Motion Artifact Reduction on Brain MRI Using Deep Learning with Effective Data Augmentation Techniques[C]:IEEE,2021.