Deep learning-based automatic left atrial appendage filling defects assessment on cardiac computed tomography for clinical and subclinical atrial fibrillation patients

Ling Chen, Sung Hao Huang*, Tzu Hsiang Wang, Tzuo Yun Lan, Vincent S. Tseng, Hsuan Ming Tsao, Hsueh Han Wang, Gau Jun Tang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Rationale and objectives: Selecting region of interest (ROI) for left atrial appendage (LAA) filling defects assessment can be time consuming and prone to subjectivity. This study aimed to develop and validate a novel artificial intelligence (AI), deep learning (DL) based framework for automatic filling defects assessment on CT images for clinical and subclinical atrial fibrillation (AF) patients. Materials and methods: A total of 443,053 CT images were used for DL model development and testing. Images were analyzed by the AI framework and expert cardiologists/radiologists. The LAA segmentation performance was evaluated using Dice coefficient. The agreement between manual and automatic LAA ROI selections was evaluated using intraclass correlation coefficient (ICC) analysis. Receiver operating characteristic (ROC) curve analysis was used to assess filling defects based on the computed LAA to ascending aorta Hounsfield unit (HU) ratios. Results: A total of 210 patients (Group 1: subclinical AF, n = 105; Group 2: clinical AF with stroke, n = 35; Group 3: AF for catheter ablation, n = 70) were enrolled. The LAA volume segmentation achieved 0.931–0.945 Dice scores. The LAA ROI selection demonstrated excellent agreement (ICC ≥0.895, p < 0.001) with manual selection on the test sets. The automatic framework achieved an excellent AUC score of 0.979 in filling defects assessment. The ROC-derived optimal HU ratio threshold for filling defects detection was 0.561. Conclusion: The novel AI-based framework could accurately segment the LAA region and select ROIs while effectively avoiding trabeculae for filling defects assessment, achieving close-to-expert performance. This technique may help preemptively detect the potential thromboembolic risk for AF patients.

Original languageEnglish
Article numbere12945
JournalHeliyon
Volume9
Issue number1
DOIs
StatePublished - Jan 2023

Keywords

  • Artificial intelligence
  • Atrial fibrillation
  • Computed tomography
  • Deep learning
  • Left atrial appendage

Fingerprint

Dive into the research topics of 'Deep learning-based automatic left atrial appendage filling defects assessment on cardiac computed tomography for clinical and subclinical atrial fibrillation patients'. Together they form a unique fingerprint.

Cite this