Related Experiment Video
Updated: Jun 13, 2026
09:32
Measurement of Pulse Propagation Velocity, Distensibility and Strain in an Abdominal Aortic Aneurysm Mouse Model
Published on: February 23, 2020
2D Ultrasound Elasticity Imaging of Abdominal Aortic Aneurysms Using Deep Neural Networks
Utsav Ratna Tuladhar1, Richard Simon1, Doran Mix2
1Rochester Institute of Technology, Rochester, NY 14623 USA.
IEEE Transactions on Computational Imaging
|June 12, 2026
Summary
Deep learning enhances ultrasound imaging for abdominal aortic aneurysms (AAA). This new method accurately maps tissue stiffness, improving rupture risk assessment beyond diameter alone.
Area of Science:
- Biomedical Engineering
- Medical Imaging
- Computational Mechanics
Background:
- Abdominal aortic aneurysms (AAA) rupture risk is critical but poorly assessed by diameter alone.
- Vessel wall elasticity is a key factor in AAA rupture risk.
- Current imaging methods lack detailed mechanical property assessment.
Purpose of the Study:
- To develop a deep learning framework for elasticity imaging of AAAs using 2D ultrasound.
- To infer spatial modulus distribution from ultrasound-derived displacement fields.
- To provide a more accurate assessment of AAA rupture risk.
Main Methods:
- Utilized finite element simulations to generate displacement field and modulus distribution datasets.
- Trained a U-Net deep learning model using normalized mean squared error (NMSE).
- Validated the model on digital phantoms, physical phantoms, and clinical AAA ultrasound data.
Main Results:
- Achieved 1.6% NMSE in reconstructing modulus distributions from simulated data.
- Demonstrated accurate generalization to phantom data, with predicted modular ratios matching expected values.
- Deep learning method showed comparable performance to iterative methods but with significantly faster computation.
Conclusions:
- The proposed deep learning framework accurately reconstructs AAA tissue elasticity from ultrasound.
- This approach offers a promising tool for near real-time assessment of AAA growth and rupture risk.
- Enables improved clinical decision-making by providing detailed mechanical insights into AAAs.
