PROJECT TITLE :
Waveform inversion with source encoding for breast sound speed reconstruction in ultrasound computed tomography
Ultrasound computed tomography (USCT) holds nice promise for improving the detection and management of breast cancer. As a result of they are based on the acoustic wave equation, waveform inversion-primarily based reconstruction strategies can produce images that possess improved spatial resolution properties over those created by ray-based strategies. However, waveform inversion strategies are computationally demanding and haven't been applied widely in USCT breast imaging. In this work, source encoding ideas are used to develop an accelerated USCT reconstruction methodology that circumvents the large computational burden of standard waveform inversion strategies. This technique, referred to as the waveform inversion with source encoding (WISE) technique, encodes the measurement knowledge employing a random encoding vector and determines an estimate of the sound speed distribution by solving a stochastic optimization problem by use of a stochastic gradient descent algorithm. Each pc simulation and experimental phantom studies are conducted to demonstrate the utilization of the WISE methodology. The results suggest that the WISE method maintains the high spatial resolution of waveform inversion ways while significantly reducing the computational burden.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here