Key result
A multi-stage pipeline based on fully-convolutional neural networks was proposed for the automatic segmentation of cardiac structures from non-contrast enhanced CMR images in arrhythmic patients.
Why the study?
Manual delineation of cardiac structures from non-contrast enhanced CMR is labor-intensive and challenging due to low contrast, while arrhythmia impairs image quality with blurring and motion artifacts.
A proposed multi-stage CNN pipeline may automate the challenging segmentation of cardiac structures from non-contrast CMR in arrhythmic patients, potentially aiding LAA occlusion guidance.
Image fusion may streamline LAA occlusion; leaves open whether outcomes improve in randomized trials.
Left atrial appendage (LAA) is the source of thrombi formation in more than 90% of strokes in patients with nonvalvular atrial fibrillation. Catheter-based LAA occlusion is being increasingly applied as a treatment strategy to prevent stroke. Anatomical complexity of LAA makes percutaneous occlusion commonly performed under transesophageal echocardiography (TEE) and X-ray (XR) guidance especially challenging. Image fusion techniques integrating 3D anatomical models derived from pre-procedural imaging into the live XR fluoroscopy can be applied to guide each step of the LAA closure. Cardiac magnetic resonance (CMR) imaging gains in importance for radiation-free evaluation of cardiac morphology as alternative to gold-standard TEE or computed tomography angiography (CTA). Manual delineation of cardiac structures from non-contrast enhanced CMR is, however, labor-intensive, tedious, and challenging due to the rather low contrast. Additionally, arrhythmia often impairs the image quality in ECG synchronized acquisitions causing blurring and motion artifacts. Thus, for cardiac segmentation in arrhythmic patients, there is a strong need for an automated image segmentation method. Deep learning-based methods have shown great promise in medical image analysis achieving superior performance in various imaging modalities and different clinical applications. Fully-convolutional neural networks (CNNs), especially U-Net, have become the method of choice for cardiac segmentation. In this paper, we propose an approach for automatic segmentation of cardiac structures from non-contrast enhanced CMR images of arrhythmic patients based on CNNs implemented in a multi-stage pipeline. Two-stage implementation allows subdividing the task into localization of the relevant cardiac structures and segmentation of these structures from the cropped sub-regions obtained from previous step leading to efficient and effective way of automated cardiac segmentation.
No takes yet. Share an insight, caveat, or question.
Vernikouskaya et al. (2024) studied Arrhythmia / Nonvalvular atrial fibrillation. Multi-stage pipeline based on fully-convolutional neural networks (CNNs) was evaluated on Automatic segmentation of cardiac structures. A multi-stage pipeline based on fully-convolutional neural networks was proposed for the automatic segmentation of cardiac structures from non-contrast enhanced CMR images in arrhythmic patients.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: