Displacement Tracking Techniques in Ultrasound Elastography: From Cross Correlation to Deep Learning

Area of Science:

• Medical Imaging
• Biomedical Engineering
• Acoustics

Background:

• Ultrasound elastography noninvasively maps tissue viscoelastic properties for disease characterization.
• Strain elastography (SE) and shear-wave elastography (SWE) are key techniques, both relying on accurate displacement estimation.
• Existing reviews often overlook displacement tracking algorithm advancements, focusing instead on clinical applications.

Purpose of the Study:

• To comprehensively review recently proposed displacement estimation algorithms for SE and SWE.
• To highlight algorithms beyond traditional methods, including deep learning approaches.
• To discuss validation, clinical translation, and future research directions in elastographic displacement tracking.

Main Methods:

• Review of various displacement estimation techniques: cross-correlation, block-matching, model-based, energy-based, and deep learning-based.
• Inclusion of algorithms for large/lateral displacement tracking, adaptive beamforming, data enhancement, and noise suppression.
• Discussion of simulation models, clinical validation, performance metrics, and available resources.

Main Results:

• Identification and categorization of diverse displacement tracking algorithms for ultrasound elastography.
• Emphasis on the critical role of accurate displacement estimation for SE and SWE performance.
• Overview of methods facilitating improved tracking accuracy and robustness.

Conclusions:

• Accurate displacement estimation is fundamental to the success of ultrasound elastography techniques like SE and SWE.
• Recent algorithmic developments offer significant potential for enhancing elastography's diagnostic capabilities.
• Further research is needed for clinical translation, validation, and addressing current limitations in elastographic tracking.