Left Atrial Appendage Analysis from Echocardiographic Images: Relevance in Left Atrial Appendage Occlusion

被引:0
作者
Sarapardeh, Haniyeh Samareh Hemmati [1 ]
Fayazi, Ali [1 ]
Zadeh, Hossein Ghayoumi [1 ]
Rezaee, Khosro [2 ]
机构
[1] Vali E Asr Univ Rafsanjan, Dept Elect Engn, 22 Bahman Sq, Rafsanjan 7718897111, Iran
[2] Meybod Univ, Dept Biomed Engn, Meybod 8961699557, Iran
关键词
left atrial appendage; neural network; Watchman; echocardiography; segmentation; SEGMENTATION; FIBRILLATION; FUSION;
D O I
10.1520/JTE20230425
中图分类号
TB3 [工程材料学];
学科分类号
0805 ; 080502 ;
摘要
Atrial fibrillation, a prevalent cardiac arrhythmia, disrupts the normal path of electrical signals within the heart. To address this issue, the left atrial appendage closure is often considered. This involves using a closure instrument named the Watchman to obstruct the left atrial appendage (LAA) ostium. The wide variety of LAA shapes, sizes, and forms in individuals makes selecting the correct Watchman size crucial. This study first isolates the LAA from echocardiographic images and then recommends the appropriate Watchman size. The 3-D echocardiographic images used in this study are from 32 male and female patients who underwent successful LAA closure at Kings College Hospital London over two years. For each patient, there are 208 cardiac echo slices in the imaging mode. This study presents an image processing -based model to separate LAA regions and extract relevant features. These features are then inputted into a classification platform in which a neural network determines the suitable Watchman size. The average and mode Hausdorff distances, calculated between the proposed method and the traditional manual calculation for the 501 analyzed LAA images, are approximately 0.2467 and 0.0587, respectively. Because of limited data, a 10 -fold cross -validation was used to assess the classifier, yielding an accuracy of 74.07 %. The proposed model effectively isolated the LAA from the corresponding slices of the 3-D echocardiographic images. However, the classifier's accuracy is not ideal because of insufficient data, which could be improved by expanding the database. This research's outcomes could aid physicians in selecting the proper Watchman size.
引用
收藏
页码:2175 / 2192
页数:18
相关论文
共 30 条
[21]   Left Atrial Appendage Closure Guided by 3D Printed Cardiac Reconstruction: Emerging Directions and Future Trends [J].
Pellegrino, Pier Luigi ;
Fassini, Gaetano ;
Di Biase, Matteo ;
Tondo, Claudio .
JOURNAL OF CARDIOVASCULAR ELECTROPHYSIOLOGY, 2016, 27 (06) :768-771
[22]   Fully automatic segmentation of the mitral leaflets in 3D transesophageal echocardiographic images using multi-atlas joint label fusion and deformable medial modeling [J].
Pouch, A. M. ;
Wang, H. ;
Takabe, M. ;
Jackson, B. M. ;
Gorman, J. H., III ;
Gorman, R. C. ;
Yushkevich, P. A. ;
Sehgal, C. M. .
MEDICAL IMAGE ANALYSIS, 2014, 18 (01) :118-129
[23]   Fully automated segmentation of the left atrium, pulmonary veins, and left atrial appendage from magnetic resonance angiography by joint-atlas-optimization [J].
Qiao, Menyun ;
Wang, Yuanyuan ;
Berendsen, Floris F. ;
van der Geest, Rob J. ;
Tao, Qian .
MEDICAL PHYSICS, 2019, 46 (05) :2074-2084
[24]   Morphologic Assessment of the Left Atrial Appendage in Patients with Atrial Fibrillation by Gray Values-Inverted Volume-Rendered Imaging of Three-Dimensional Transesophageal Echocardiography: A Comparative Study with Computed Tomography [J].
Song, Hongning ;
Zhou, Qing ;
Deng, Qing ;
Chen, Jinling ;
Zhang, Lan ;
Tan, Tuantuan ;
Guo, Ruiqiang .
JOURNAL OF THE AMERICAN SOCIETY OF ECHOCARDIOGRAPHY, 2016, 29 (11) :1100-1108
[25]   A fast instance segmentation with one-stage multi-task deep neural network for autonomous driving [J].
Tseng, Kuo-Kun ;
Lin, Jiangrui ;
Chen, Chien-Ming ;
Hassan, Mohammad Mehedi .
COMPUTERS & ELECTRICAL ENGINEERING, 2021, 93
[26]   A review on modern defect detection models using DCNNs - Deep convolutional neural networks [J].
Tulbure, Andrei-Alexandru ;
Tulbure, Adrian-Alexandru ;
Dulf, Eva-Henrietta .
JOURNAL OF ADVANCED RESEARCH, 2022, 35 :33-48
[27]   Left Atrial Appendage Segmentation Based on Ranking 2-D Segmentation Proposals [J].
Wang, Lei ;
Feng, Jianjiang ;
Jin, Cheng ;
Lu, Jiwen ;
Zhou, Jie .
STATISTICAL ATLASES AND COMPUTATIONAL MODELS OF THE HEART: IMAGING AND MODELLING CHALLENGES, 2016, 2017, 10124 :21-29
[28]   Fully Automatic Left Atrium Segmentation From Late Gadolinium Enhanced Magnetic Resonance Imaging Using a Dual Fully Convolutional Neural Network [J].
Xiong, Zhaohan ;
Fedorov, Vadim V. ;
Fu, Xiaohang ;
Cheng, Elizabeth ;
Macleod, Rob ;
Zhao, Jichao .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2019, 38 (02) :515-524
[29]   Intelligent fault diagnosis of machines with small & imbalanced data: A state-of-the-art review and possible extensions [J].
Zhang, Tianci ;
Chen, Jinglong ;
Li, Fudong ;
Zhang, Kaiyu ;
Lv, Haixin ;
He, Shuilong ;
Xu, Enyong .
ISA TRANSACTIONS, 2022, 119 :152-171
[30]   Multi-Part Modeling and Segmentation of Left Atrium in C-Arm CT for Image-Guided Ablation of Atrial Fibrillation [J].
Zheng, Yefeng ;
Yang, Dong ;
John, Matthias ;
Comaniciu, Dorin .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2014, 33 (02) :318-331