Hung-Hsun Chen1, Chih-Min Liu2, Shih-Lin Chang2, Paul Yu-Chun Chang3, Wei-Shiang Chen3, Yo-Ming Pan3, Ssu-Ting Fang3, Shan-Quan Zhan4, Chieh-Mao Chuang5, Yenn-Jiang Lin2, Ling Kuo2, Mei-Han Wu6, Chun-Ku Chen7, Ying-Yueh Chang8, Yang-Che Shiu9, Shih-Ann Chen10, Henry Horng-Shing Lu11. 1. Center of Teaching and Learning Development, National Chiao Tung University, Taiwan. 2. Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taipei, Taiwan; Faculty of Medicine, School of Medicine, National Yang-Ming University, Taipei, Taiwan; Institute of Clinical Medicine, National Yang-Ming University, Taipei, Taiwan. 3. Institute of Statistics, National Chiao Tung University, Taiwan. 4. Institute of Data Science and Engineering, National Chiao Tung University, Taiwan. 5. Division of Pediatric Cardiology, China Medical University Children's Hospital, China Medical University, Taichung, Taiwan. 6. Faculty of Medicine, School of Medicine, National Yang-Ming University, Taipei, Taiwan; Department of Radiology, Taipei Veterans General Hospital, Taipei, Taiwan; Department of Medical Imaging, Diagnostic Radiology, Cheng Hsin General Hospital, Taipei, Taiwan. Electronic address: maybelin.wu@gmail.com. 7. Faculty of Medicine, School of Medicine, National Yang-Ming University, Taipei, Taiwan; Institute of Clinical Medicine, National Yang-Ming University, Taipei, Taiwan; Department of Radiology, Taipei Veterans General Hospital, Taipei, Taiwan. 8. Department of Radiology, Taipei Veterans General Hospital, Taipei, Taiwan. 9. Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taipei, Taiwan. 10. Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taipei, Taiwan; Faculty of Medicine, School of Medicine, National Yang-Ming University, Taipei, Taiwan. Electronic address: epsachen@ms41.hinet.net. 11. Institute of Statistics, National Chiao Tung University, Taiwan. Electronic address: hslu@stat.nctu.edu.tw.
Abstract
BACKGROUND: Precise segmentation of the left atrium (LA) in computed tomography (CT) images constitutes a crucial preparatory step for catheter ablation in atrial fibrillation (AF). We aim to apply deep convolutional neural networks (DCNNs) to automate the LA detection/segmentation procedure and create three-dimensional (3D) geometries. METHODS: Five hundred eighteen patients who underwent procedures for circumferential isolation of four pulmonary veins were enrolled. Cardiac CT images (from 97 patients) were used to construct the LA detection and segmentation models. These images were reviewed by the cardiologists such that images containing the LA were identified/segmented as the ground truth for model training. Two DCNNs which incorporated transfer learning with the architectures of ResNet50/U-Net were trained for image-based LA classification/segmentation. The LA geometry created by the deep learning model was correlated to the outcomes of AF ablation. RESULTS: The LA detection model achieved an overall 99.0% prediction accuracy, as well as a sensitivity of 99.3% and a specificity of 98.7%. Moreover, the LA segmentation model achieved an intersection over union of 91.42%. The estimated mean LA volume of all the 518 patients studied herein with the deep learning model was 123.3 ± 40.4 ml. The greatest area under the curve with a LA volume of 139 ml yielded a positive predictive value of 85.5% without detectable AF episodes over a period of one year following ablation. CONCLUSIONS: The deep learning provides an efficient and accurate way for automatic contouring and LA volume calculation based on the construction of the 3D LA geometry.
BACKGROUND: Precise segmentation of the left atrium (LA) in computed tomography (CT) images constitutes a crucial preparatory step for catheter ablation in atrial fibrillation (AF). We aim to apply deep convolutional neural networks (DCNNs) to automate the LA detection/segmentation procedure and create three-dimensional (3D) geometries. METHODS: Five hundred eighteen patients who underwent procedures for circumferential isolation of four pulmonary veins were enrolled. Cardiac CT images (from 97 patients) were used to construct the LA detection and segmentation models. These images were reviewed by the cardiologists such that images containing the LA were identified/segmented as the ground truth for model training. Two DCNNs which incorporated transfer learning with the architectures of ResNet50/U-Net were trained for image-based LA classification/segmentation. The LA geometry created by the deep learning model was correlated to the outcomes of AF ablation. RESULTS: The LA detection model achieved an overall 99.0% prediction accuracy, as well as a sensitivity of 99.3% and a specificity of 98.7%. Moreover, the LA segmentation model achieved an intersection over union of 91.42%. The estimated mean LA volume of all the 518 patients studied herein with the deep learning model was 123.3 ± 40.4 ml. The greatest area under the curve with a LA volume of 139 ml yielded a positive predictive value of 85.5% without detectable AF episodes over a period of one year following ablation. CONCLUSIONS: The deep learning provides an efficient and accurate way for automatic contouring and LA volume calculation based on the construction of the 3D LA geometry.
Authors: Jonathan James Hyett Bray; Moghees Ahmad Hanif; Mohammad Alradhawi; Jacob Ibbetson; Surinder Singh Dosanjh; Sabrina Lucy Smith; Mahmood Ahmad; Dominic Pimenta Journal: Eur Heart J Open Date: 2022-03-17
Authors: Musa Abdulkareem; Mark S Brahier; Fengwei Zou; Alexandra Taylor; Athanasios Thomaides; Peter J Bergquist; Monvadi B Srichai; Aaron M Lee; Jose D Vargas; Steffen E Petersen Journal: Front Cardiovasc Med Date: 2022-01-28