Related Experiment Video
Updated: Dec 12, 2025
06:59
Improved Registration of 3D CT Angiography with X-ray Fluoroscopy for Image Fusion During Transcatheter Aortic Valve Implantation
Published on: June 3, 2018
10.9K
3D Automatic Segmentation of Aortic Computed Tomography Angiography Combining Multi-View 2D Convolutional Neural
Alice Fantazzini1,2, Mario Esposito3, Alice Finotello4
1Department of Experimental Medicine, University of Genoa, Via Leon Battista Alberti, 2, 16132, Genoa, Italy. alice.fantazzini@edu.unige.it.
Cardiovascular Engineering and Technology
|August 13, 2020
Summary
This study introduces a deep learning pipeline for automated aortic lumen segmentation in Computed Tomography Angiography (CTA) scans. The method accurately segments the aorta, improving preoperative planning for vascular surgery.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Vascular Surgery
Background:
- Quantitative analysis of contrast-enhanced Computed Tomography Angiography (CTA) is crucial for assessing aortic anatomy and planning vascular surgery.
- Manual and semi-automatic segmentation methods for CTA have limitations in accuracy and efficiency.
Purpose of the Study:
- To develop and validate a deep learning-based pipeline for automatic segmentation of the aortic lumen in CTA scans.
- To improve the accuracy and efficiency of aortic lumen segmentation for clinical applications.
Main Methods:
- A multi-stage deep learning approach was employed, starting with a coarse segmentation CNN followed by three single-view CNNs (axial, sagittal, coronal).
- Integration of predictions from orthogonal networks ensured 3D spatial coherence for the final aortic lumen segmentation.
Main Results:
- The pipeline achieved a high Dice coefficient (DSC) of 0.93 ± 0.02 for multi-view integration.
- Segmentation accuracy was comparable across single-view networks (DSC ~0.92).
- The prediction phase was rapid, taking approximately 25 ± 1 seconds per scan.
Conclusions:
- The proposed deep learning pipeline effectively localizes and segments the aortic lumen in CTA scans.
- This automated approach offers a promising solution for enhancing preoperative planning in vascular surgery.
