Speckle Reduction via Deep Content-Aware Image Prior for Precise Breast Tumor Segmentation in an Ultrasound Image

Abstract

The performance of computer-aided diagnosis (CAD) systems that are based on ultrasound imaging has been enhanced owing to the advancement in deep learning. However, because of the inherent speckle noise in ultrasound images, the ambiguous boundaries of lesions deteriorate and are difficult to distinguish, resulting in the performance degradation of CAD. Although several methods have been proposed to reduce speckle noise over decades, this task remains a challenge that must be improved to enhance the performance of CAD. In this paper, we propose a deep content-aware image prior with a content-aware attention module for superior despeckling of ultrasound images without clean images. For the image prior, we developed a content-aware attention module to deal with the content information in an input image. In this module, super-pixel pooling is used to give attention to salient regions in an ultrasound image. Therefore, it can provide more content information regarding the input image when compared to other attention modules. The deep content-aware image prior consists of deep learning networks based on this attention module. The deep content-aware image prior is validated by applying it as a preprocessing step for breast tumor segmentation in ultrasound images, which is one of the tasks in CAD. Our method improved the segmentation performance by 15.89% in terms of the area under the precision-recall curve. The results demonstrate that our method enhances the quality of ultrasound images by effectively reducing speckle noise while preserving important information in the image, promising for the design of superior CAD systems. IEEE