This study aims to create and assess a deep learning framework for extracting left atrial appendage features in atrial fibrillation patients and combining them with clinical data to predict ischemic stroke risk. Clinical data and chest CT images from patients diagnosed with non-valvular atrial fibrillation will be collected. Patients will be categorized into stroke and non-stroke groups to build a data repository. The dataset will be divided into training and validation sets, with missing data handled and pulmonary vein CTV and virtual non-contrast images annotated. A deep learning model will be used for image segmentation and feature extraction to develop a prediction system.
This study aims to develop and evaluate a deep learning framework that can automatically extract imaging features of the left atrial appendage in patients with atrial fibrillation and combine them with clinical features to predict the risk of ischemic stroke in these patients. The study intends to retrospectively collect clinical data (including patients\' general information, medical history, laboratory tests, etc.) and chest CT images, as well as pulmonary vein CTV images (if available), from patients diagnosed with non-valvular atrial fibrillation between January 2018 and June 2024. The patients will be divided into stroke and non-stroke groups based on whether they have experienced an ischemic stroke, and a data analysis repository will be established. The dataset will be split into training and validation sets. Missing data will be handled, and data labeling will be performed on the pulmonary vein CTV sequence images and virtual non-contrast (VNC) sequence images. The left atrial morphology will be delineated, and a deep learning-based image segmentation network model will be developed to extract and select radiomic features for the prediction system.
Study Type
OBSERVATIONAL
Enrollment
1,500
Observational study without intervention
The First Affiliated Hospital, Zhejiang University School of Medicine
Hangzhou, Zhejiang, China
Performance of a Deep Learning Framework for Predicting Ischemic Stroke Risk in AF Patients.
This study aims to develop and evaluate a deep learning framework that automatically extracts Left Atrial Appendage (LAA) imaging features from 3D\_slicer software and combines them with clinical characteristics to predict ischemic stroke risk in patients with atrial fibrillation (AF). The performance of the developed system will be evaluated using receiver operating characteristic (ROC) curves, area under the curve (AUC), accuracy, sensitivity, and specificity.
Time frame: Through study completion, an average of 2 year.
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.