Key result
3D spatio-temporal CNNs cut elasticity estimation error by ~57% versus conventional time-of-flight methods.
Why the study?
Conventional shear wave elasticity imaging neglects information such as the shape of the propagating shear wave or push sequence characteristics for local elasticity estimation.
Does a 3D spatio-temporal CNN approach improve the accuracy of elasticity estimation in ultrasound shear wave imaging compared to conventional methods in phantom models?
Does a 3D spatio-temporal CNN approach improve the accuracy of elasticity estimation in ultrasound shear wave imaging compared to conventional methods in phantom models?
Effect estimate: MAE 5.01 kPa
Absolute Event Rate: 5.01% vs 11.61%
A 3D spatio-temporal CNN approach provides fast and more accurate local elasticity estimations from ultrasound shear wave data compared to conventional methods in phantom models.
May enable rapid local elasticity mapping from shear waves; leaves open clinical validation in cardiovascular tissues.
Ultrasound shear wave elasticity imaging is a valuable tool for quantifying the elastic properties of tissue. Typically, the shear wave velocity is derived and mapped to an elasticity value, which neglects information such as the shape of the propagating shear wave or push sequence characteristics. We present 3D spatio-temporal CNNs for fast local elasticity estimation from ultrasound data. This approach is based on retrieving elastic properties from shear wave propagation within small local regions. A large training data set is acquired with a robot from homogeneous gelatin phantoms ranging from 17.42 kPa to 126.05 kPa with various push locations. The results show that our approach can estimate elastic properties on a pixelwise basis with a mean absolute error of 5.01(437) kPa. Furthermore, we estimate local elasticity independent of the push location and can even perform accurate estimates inside the push region. For phantoms with embedded inclusions, we report a 53.93% lower MAE (7.50 kPa) and on the background of 85.24% (1.64 kPa) compared to a conventional shear wave method. Overall, our method offers fast local estimations of elastic properties with small spatio-temporal window sizes.
No takes yet. Share an insight, caveat, or question.
A 2022 study studied Tissue elasticity imaging. 3D spatio-temporal CNNs vs. Conventional Time-of-Flight (ToF) shear wave estimation was evaluated on Mean absolute error (MAE) of elasticity estimation in homogeneous phantoms (MAE 5.01 kPa). The 3D spatio-temporal CNN approach estimated local elastic properties on a pixelwise basis with a mean absolute error of 5.01 kPa, outperforming conventional time-of-flight methods.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: