Left atrial appendage segmentation and quantitative assisted diagnosis of atrial fibrillation based on fusion of temporal-spatial information. (1st May 2018)

• Record Type: Journal Article
• Authors: Jin, Cheng; Feng, Jianjiang; Wang, Lei; Yu, Heng; Liu, Jiang; Lu, Jiwen; Zhou, Jie
• Is Part Of: Computers in biology and medicine. Volume 96(2018)
• Page Start: 52
• Page End: 68
• Publication Date: 2018-05-01
• Subjects: Atrial fibrillation (AF) -- 4D-CT -- Left atrial appendage(LAA) -- Multi-phase segmentation -- Temporal-spatial information; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2018.03.002
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: In this paper, we present an approach for left atrial appendage (LAA) multi-phase fast segmentation and quantitative assisted diagnosis of atrial fibrillation (AF) based on 4D-CT data. We take full advantage of the temporal dimension information to segment the living, flailed LAA based on a parametric max-flow method and graph-cut approach to build 3-D model of each phase. To assist the diagnosis of AF, we calculate the volumes of 3-D models, and then generate a "volume-phase" curve to calculate the important dynamic metrics: ejection fraction, filling flux, and emptying flux of the LAA's blood by volume. This approach demonstrates more precise results than the conventional approaches that calculate metrics by area, and allows for the quick analysis of LAA-volume pattern changes of in a cardiac cycle. It may also provide insight into the individual differences in the lesions of the LAA. Furthermore, we apply support vector machines (SVMs) to achieve a quantitative auto-diagnosis of the AF by exploiting seven features from volume change ratios of the LAA, and perform multivariate logistic regression analysis for the risk of LAA thrombosis. The 100 cases utilized in this research were taken from the Philips 256-iCT. The experimental results demonstrate that our approach can construct the 3-D LAA geometries robustly compared to manual annotations, and reasonably infer that the LAA undergoes filling, emptying and re-filling, re-emptying in a cardiac cycle. This research provides a potential for exploring various physiological functions of the LAA and quantitatively estimating the risk of stroke in patients with AF. Highlights: We take full advantage of the temporal information to segment the living LAA. The approach can quickly segment multi-phases LAAs with lobes in batches. We introduce volume change ratio to calculate key functional metrics of the LAA. We apply SVM to achieve a quantitative auto-diagnosis of the AF. We perform multivariate logistic regression analysis for the risk of LAA thrombosis.