Automated extraction of left atrial volumes from two-dimensional computer tomography images using a deep learning technique

Hung Hsun Chen, Chih Min Liu, Shih Lin Chang, Paul Yu Chun Chang, Wei Shiang Chen, Yo Ming Pan, Ssu Ting Fang, Shan Quan Zhan, Chieh Mao Chuang, Yenn Jiang Lin, Ling Kuo, Mei Han Wu, Chun Ku Chen, Ying Yueh Chang, Yang Che Shiu, Shih Ann Chen*, Henry Horng Shing Lu

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

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.

Original languageEnglish
JournalInternational Journal of Cardiology
DOIs
StateAccepted/In press - 1 Jan 2020

Keywords

  • Artificial intelligence
  • Atrial fibrillation
  • Deep learning
  • Left atrium
  • Segmentation

Fingerprint Dive into the research topics of 'Automated extraction of left atrial volumes from two-dimensional computer tomography images using a deep learning technique'. Together they form a unique fingerprint.

Cite this