Method for real-time automatic setting of ultrasonic image parameters based on deep learning

Abstract

We propose a method for the automatic setting of ultrasonic image parameter values based on deep learning of image classification in this paper. The method first classifies ultrasonic images through a convolutional neural network and then sets gray map and Gain parameters correspondingly to acquire high-quality images. In the classification step, we initially tried to classify the images using GoogLeNet. However, as GoogLeNet has a complicated structure and a low operating speed, this paper proposes a new structure for the convolutional neural network to classify the images. The results show that the customized classification method can result in faster recognition without compromising the performance, thus successfully achieving rapid and automatic setting of ultrasonic image parameters.