Tumor Saliency Estimation for Breast Ultrasound Images via Breast Anatomy Modeling

TL;DR

This paper introduces a novel breast anatomy-based optimization model for tumor saliency estimation in breast ultrasound images, significantly improving accuracy over existing generic methods by leveraging anatomical information.

Contribution

It proposes a new approach that models breast anatomy and integrates it into saliency estimation, achieving state-of-the-art results in tumor localization.

Findings

Improved accuracy in tumor saliency maps, especially for varying tumor sizes.

Effective handling of images without tumors.

Outperforms eight existing saliency estimation methods.

Abstract

Tumor saliency estimation aims to localize tumors by modeling the visual stimuli in medical images. However, it is a challenging task for breast ultrasound due to the complicated anatomic structure of the breast and poor image quality; and existing saliency estimation approaches only model generic visual stimuli, e.g., local and global contrast, location, and feature correlation, and achieve poor performance for tumor saliency estimation. In this paper, we propose a novel optimization model to estimate tumor saliency by utilizing breast anatomy. First, we model breast anatomy and decompose breast ultrasound image into layers using Neutro-Connectedness; then utilize the layers to generate the foreground and background maps; and finally propose a novel objective function to estimate the tumor saliency by integrating the foreground map, background map, adaptive center bias, and region-based correlation cues. The extensive experiments demonstrate that the proposed approach obtains more accurate foreground and background maps with the assistance of the breast anatomy; especially, for the images having large or small tumors; meanwhile, the new objective function can handle the images without tumors. The newly proposed method achieves state-of-the-art performance when compared to eight tumor saliency estimation approaches using two breast ultrasound datasets.