Unsupervised Despeckling

TL;DR

This paper introduces an unsupervised deep adversarial neural network for ultrasound image despeckling, aiming to reduce speckle noise while preserving image details, outperforming existing methods.

Contribution

The paper proposes a novel unsupervised deep adversarial approach with a residual neural network and combined loss functions for effective despeckling without oversmoothing.

Findings

Outperforms state-of-the-art despeckling methods

Effectively reduces speckle noise while preserving details

Demonstrates superior image quality in experiments

Abstract

Contrast and quality of ultrasound images are adversely affected by the excessive presence of speckle. However, being an inherent imaging property, speckle helps in tissue characterization and tracking. Thus, despeckling of the ultrasound images requires the reduction of speckle extent without any oversmoothing. In this letter, we aim to address the despeckling problem using an unsupervised deep adversarial approach. A despeckling residual neural network (DRNN) is trained with an adversarial loss imposed by a discriminator. The discriminator tries to differentiate between the despeckled images generated by the DRNN and the set of high-quality images. Further to prevent the developed DRNN from oversmoothing, a structural loss term is used along with the adversarial loss. Experimental evaluations show that the proposed DRNN is able to outperform the state-of-the-art despeckling approaches.