FINE TUNING	CYCLE GAN INSPIRED	NEURAL	NETWORK FOR SPEED OF	SOUND IMAGING	FROM	ULTRASOUND

Content Files

Li, Andrew-FA23-ECE499-Thesis.pdf

Permalink

https://hdl.handle.net/2142/124770

Title: FINE TUNING CYCLE GAN INSPIRED NEURAL NETWORK FOR SPEED OF SOUND IMAGING FROM ULTRASOUND
Author(s): Li, Andrew
Issue Date: 2023-12-01
Keyword(s): Ultrasound, Neural Networks, Hyper Parameter Tuning
Date of Ingest: 2024-10-02T13:57:13-05:00
Abstract: A speed of sound map of tissue using ultrasound can be used to diagnose various issues with the tissue while not being as costly as other forms of imaging. An emerging method of generating the speed of sound map from ultrasound signals is through deep learning. As with any deep learning method there are often hyper parameters that need to be tuned for better results. To accomplish this, I used a variation of grid search to find the optimal parameters for the network. The results were compared by calculated the root mean squared error (RMSE) of test data generated either via full wave simulation or straight wave simulation. Upon tuning the optimal learning rates, batch size, and loss function weighting decrease in the RMSE can be observed.
Type of Resource: text
Genre of Resource: dissertation/thesis
Language: eng

The best of ECE undergraduate research