干旱区生态环境知识资源中心(Arid): Convolutional neural networks for skull-stripping in brain MR imaging using silver standard masks

Arid

DOI	10.1016/j.artmed.2019.06.008
	Convolutional neural networks for skull-stripping in brain MR imaging using silver standard masks
	Lucena, Oeslle 1,2; Souza, Roberto 3,4,5; Rittner, Leticia 2; Frayne, Richard 3,4,5; Lotufo, Roberto 2
通讯作者	Lucena, Oeslle
来源期刊	ARTIFICIAL INTELLIGENCE IN MEDICINE
ISSN	0933-3657
EISSN	1873-2860
出版年	2019
卷号	98 页码:48-58
英文摘要	Manual annotation is considered to be the gold standard in medical imaging analysis. However, medical imaging datasets that include expert manual segmentation are scarce as this step is time-consuming, and therefore expensive. Moreover, single-rater manual annotation is most often used in data-driven approaches making the network biased to only that single expert. In this work, we propose a CNN for brain extraction in magnetic resonance (MR) imaging, that is fully trained with what we refer to as silver standard masks. Therefore, eliminating the cost associated with manual annotation. Silver standard masks are generated by forming the consensus from a set of eight, public, non-deep-learning-based brain extraction methods using the Simultaneous Truth and Performance Level Estimation (STAPLE) algorithm. Our method consists of (1) developing a dataset with silver standard masks as input, and implementing (2) a tri-planar method using parallel 2D U-Net-based convolutional neural networks (CNNs) (referred to as CONSNet). This term refers to our integrated approach, i.e., training with silver standard masks and using a 2D U-Net-based architecture. We conducted our analysis using three public datasets: the Calgary-Campinas-359 (CC-359), the LONI Probabilistic Brain Atlas (LPBA40), and the Open Access Series of Imaging Studies (OASIS). Five performance metrics were used in our experiments: Dice coefficient, sensitivity, specificity, Hausdorff distance, and symmetric surface-to-surface mean distance. Our results showed that we outperformed (i.e., larger Dice coefficients) the current state-of-the-art skull-stripping methods without using gold standard annotation for the CNNs training stage. CONSNet is the first deep learning approach that is fully trained using silver standard data and is, thus, more generalizable. Using these masks, we eliminate the cost of manual annotation, decreased inter-/intra-rater variability, and avoided CNN segmentation overfitting towards one specific manual annotation guideline that can occur when gold standard masks are used. Moreover, once trained, our method takes few seconds to process a typical brain image volume using modem a high-end GPU. In contrast, many of the other competitive methods have processing times in the order of minutes.
英文关键词	Silver standard masks Convolutional neural network (CNN) Skull-stripping Data augmentation
类型	Article
语种	英语
国家	England ; Brazil ; Canada
收录类别	SCI-E
WOS记录号	WOS:000488323400006
WOS关键词	ALZHEIMER-DISEASE ; SEGMENTATION ; IMAGES ; ATLAS ; HIPPOCAMPUS ; PERFORMANCE ; EXTRACTION ; ALGORITHM ; DIAGNOSIS ; CNN
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Biomedical ; Medical Informatics
WOS研究方向	Computer Science ; Engineering ; Medical Informatics
来源机构	University of London
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/214413
作者单位	1.Kings Coll London, Sch Biomed Engn & Imaging Sci, London, England; 2.Univ Estadual Campinas, Sch Elect & Comp Engn, Dept Comp Engn & Ind Automat, Med Image Comp Lab, Campinas, SP, Brazil; 3.Univ Calgary, Hotchkiss Brain Inst, Dept Radiol, Calgary, AB, Canada; 4.Univ Calgary, Hotchkiss Brain Inst, Dept Clin Neurosci, Calgary, AB, Canada; 5.Alberta Hlth Serv, Seaman Family Magnet Resonance Res Ctr, Foothills Med Ctr, Calgary, AB, Canada
推荐引用方式 GB/T 7714	Lucena, Oeslle,Souza, Roberto,Rittner, Leticia,et al. Convolutional neural networks for skull-stripping in brain MR imaging using silver standard masks[J]. University of London,2019,98:48-58.
APA	Lucena, Oeslle,Souza, Roberto,Rittner, Leticia,Frayne, Richard,&Lotufo, Roberto.(2019).Convolutional neural networks for skull-stripping in brain MR imaging using silver standard masks.ARTIFICIAL INTELLIGENCE IN MEDICINE,98,48-58.
MLA	Lucena, Oeslle,et al."Convolutional neural networks for skull-stripping in brain MR imaging using silver standard masks".ARTIFICIAL INTELLIGENCE IN MEDICINE 98(2019):48-58.