An efficient transfer learning-based Super-Resolution model for Medical Ultrasound Image

Abstract

There are many imaging modalities for clinical diagnosis, but we heavily use ultrasound imaging; some of the ultrasound images are low resolution because of the body’s internal weakness. This paper presents a novel unsupervised super-resolution framework for ultrasound image enhancement without considering any large sets of training samples which is the major concern in many single image super-resolution techniques. Here, the most powerful nonlinear mapping is introduced within convolutional neural networks to restore potentially useful and prominent spatial information generated from the model sets considered for image enhancements. Here, two techniques are used: dilated convolution and residual learning to increase the convergence and reconstruction accuracy in terms of quality measures. The potential metrics of dilated convolution in extract spatial information and residual learning are used to narrow the convergence time by learning only the difference between the test input and distorted input image. By evaluating the proposed framework on real ultrasound image sets, the performance metrics are validated. The proposed model outperformed the other competitive image enhancement models in the USSR field.