Fanli Zhou1,2, Zhidong Yuan3, Xianglin Liu4, Keyan Yu3, Bowei Li3, Xingyan Li5, Xin Liu6, Guanxun Cheng7. 1. Department of Radiology, Peking University Shenzhen Hospital, Futian, Shenzhen, 518036, Guangdong, China. fanlizhou@outlook.com. 2. Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Nanshan, Shenzhen, 518055, Guangdong, China. fanlizhou@outlook.com. 3. Department of Radiology, Peking University Shenzhen Hospital, Futian, Shenzhen, 518036, Guangdong, China. 4. Center for Artificial Intelligence, Peng Cheng Laboratory, Nanshan, Shenzhen, 518066, Guangdong, China. 5. Ultrasound Department, Chenzhou No. 1 People's Hospital, Beihu, Chenzhou, 424300, Hunan, China. 6. Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Nanshan, Shenzhen, 518055, Guangdong, China. 7. Department of Radiology, Peking University Shenzhen Hospital, Futian, Shenzhen, 518036, Guangdong, China. chengguanxun@outlook.com.
Abstract
PURPOSE: To elucidate the role of atrial anatomical remodeling in atrial fibrillation (AF), we proposed an automatic method to extract and analyze morphological characteristics in left atrium (LA), left atrial appendage (LAA) and pulmonary veins (PVs) and constructed classifiers to evaluate the importance of identified features. METHODS: The LA, LAA and PVs were segmented from contrast computed tomography images using either a commercial software or a self-adaptive algorithm proposed by us. From these segments, geometric and fractal features were calculated automatically. To reduce the model complexity, a feature selection procedure is adopted, with the important features identified via univariable analysis and ensemble feature selection. The effectiveness of this approach is well illustrated by the high accuracy of our models. RESULTS: Morphological features, such as LAA ostium dimensions and LA volume and surface area, statistically distinguished ([Formula: see text]) AF patients or AF with LAA filling defects (AF(def+)) patients among all patients. On the test set, the best model to predict AF among all patients had an area under the receiver operating characteristic curve (AUC) of 0.91 (95% CI, 0.8-1) and the best model to predict AF(def+) among all patients had an AUC of 0.92 (95% CI, 0.81-1). CONCLUSION: This study automatically extracted and analyzed atrial morphology in AF and identified atrial anatomical remodeling that statistically distinguished AF or AF(def+). The importance of identified atrial morphological features in characterizing AF or AF(def+) was validated by corresponding classifiers. This work provides a good foundation for a complete computer-assisted diagnostic workflow of predicting the occurrence of AF or AF(def+).
PURPOSE: To elucidate the role of atrial anatomical remodeling in atrial fibrillation (AF), we proposed an automatic method to extract and analyze morphological characteristics in left atrium (LA), left atrial appendage (LAA) and pulmonary veins (PVs) and constructed classifiers to evaluate the importance of identified features. METHODS: The LA, LAA and PVs were segmented from contrast computed tomography images using either a commercial software or a self-adaptive algorithm proposed by us. From these segments, geometric and fractal features were calculated automatically. To reduce the model complexity, a feature selection procedure is adopted, with the important features identified via univariable analysis and ensemble feature selection. The effectiveness of this approach is well illustrated by the high accuracy of our models. RESULTS: Morphological features, such as LAA ostium dimensions and LA volume and surface area, statistically distinguished ([Formula: see text]) AF patients or AF with LAA filling defects (AF(def+)) patients among all patients. On the test set, the best model to predict AF among all patients had an area under the receiver operating characteristic curve (AUC) of 0.91 (95% CI, 0.8-1) and the best model to predict AF(def+) among all patients had an AUC of 0.92 (95% CI, 0.81-1). CONCLUSION: This study automatically extracted and analyzed atrial morphology in AF and identified atrial anatomical remodeling that statistically distinguished AF or AF(def+). The importance of identified atrial morphological features in characterizing AF or AF(def+) was validated by corresponding classifiers. This work provides a good foundation for a complete computer-assisted diagnostic workflow of predicting the occurrence of AF or AF(def+).
Authors: Shadi Yaghi; Andrew D Chang; Ronald Akiki; Scott Collins; Tracy Novack; Morgan Hemendinger; Ashley Schomer; Brain Mac Grory; Shawna Cutting; Tina Burton; Christopher Song; Athena Poppas; Ryan McTaggart; Mahesh Jayaraman; Alexander Merkler; Hooman Kamel; Mitchell S V Elkind; Karen Furie; Michael K Atalay Journal: J Cardiovasc Comput Tomogr Date: 2019-04-16
Authors: Katarzyna Dudzińska-Szczerba; Ilona Michałowska; Roman Piotrowski; Agnieszka Sikorska; Agnieszka Paszkowska; Urszula Stachnio; Ilona Kowalik; Piotr Kułakowski; Jakub Baran Journal: Int J Cardiol Date: 2021-01-29 Impact factor: 4.164
Authors: Lance D Burrell; Benjamin D Horne; Jeffrey L Anderson; J Brent Muhlestein; Brian K Whisenant Journal: Am J Cardiol Date: 2013-07-02 Impact factor: 2.778
Authors: Roy Beinart; E Kevin Heist; John B Newell; Godtfred Holmvang; Jeremy N Ruskin; Moussa Mansour Journal: J Cardiovasc Electrophysiol Date: 2011-01
Authors: Luigi Di Biase; Pasquale Santangeli; Matteo Anselmino; Prasant Mohanty; Ilaria Salvetti; Sebastiano Gili; Rodney Horton; Javier E Sanchez; Rong Bai; Sanghamitra Mohanty; Agnes Pump; Mauricio Cereceda Brantes; G Joseph Gallinghouse; J David Burkhardt; Federico Cesarani; Marco Scaglione; Andrea Natale; Fiorenzo Gaita Journal: J Am Coll Cardiol Date: 2012-08-07 Impact factor: 24.094
Authors: Gabriella Captur; Audrey L Karperien; Chunming Li; Filip Zemrak; Catalina Tobon-Gomez; Xuexin Gao; David A Bluemke; Perry M Elliott; Steffen E Petersen; James C Moon Journal: J Cardiovasc Magn Reson Date: 2015-09-07 Impact factor: 5.364