Key result
3D CT machine learning links right inferior pulmonary vein and LAA ostium to LAA thrombus.
Why the study?
The study was conducted to develop a comprehensive method for estimating thrombus formation factors in the left atrial appendage using 3D CT images and machine learning.
Can machine learning models using 3D CT images and clinical data predict left atrial appendage thrombus formation and identify key structural factors?
Can machine learning models using 3D CT images and clinical data predict left atrial appendage thrombus formation and identify key structural factors?
Machine learning analysis of 3D CT images identifies the LAA ostium area as the most significant structural factor influencing LAA thrombus formation.
Answers are grounded in this paper and cite their sources.
May aid future CT-based LAA thrombus risk models; leaves open prospective validation before clinical use.
This paper proposes a comprehensive method for estimating thrombus formation factors in the left atrial appendage (LAA). First, using 3D CT (Computer Tomography) image data as input, classification of thrombus presence/absence is learned using 3D ResNet. Besides, 3D Grad-CAM is applied to the prediction results to visualize regions of interest in thrombus formation. Second, features are extracted based on the visualization of regions of interest. Using the extracted features and numerical data obtained from the hospital as input, a regression analysis is performed to predict the presence/absence of thrombus using LightGBM. Visualization of regions of interest using 3D ResNet and 3D Grad-CAM shows that the right inferior pulmonary vein and the LAA were particularly correlated with thrombus formation. Estimation of important factors for thrombus formation using LightGBM shows that the LAA ostium area has the greatest influence on thrombus formation.Clinical Relevance-This paper shows the factors that contribute to thrombus formation in the LAA from the viewpoint of three-dimensional structure. In addition, the features considered important in thrombus formation were identified by comparing a variety of features.
No takes yet. Share an insight, caveat, or question.
Nako et al. (2023) studied Left atrial appendage thrombus. Machine learning model using 3D CT images was evaluated on Prediction of presence/absence of thrombus. Machine learning analysis of 3D CT images identified the right inferior pulmonary vein and LAA ostium area as the most important structural factors contributing to LAA thrombus formation.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: