A Hybrid Framework for Tumor Saliency Estimation

TL;DR

This paper introduces a hybrid tumor saliency estimation framework that combines domain knowledge and low-level features to improve breast ultrasound tumor segmentation across diverse data sources.

Contribution

It presents a novel hybrid approach integrating high-level domain knowledge with low-level saliency assumptions, overcoming limitations of traditional TSE methods.

Findings

Outperforms state-of-the-art TSE methods

Effective across diverse BUS image sources

Enhances tumor segmentation accuracy

Abstract

Automatic tumor segmentation of breast ultrasound (BUS) image is quite challenging due to the complicated anatomic structure of breast and poor image quality. Most tumor segmentation approaches achieve good performance on BUS images collected in controlled settings; however, the performance degrades greatly with BUS images from different sources. Tumor saliency estimation (TSE) has attracted increasing attention to solving the problem by modeling radiologists' attention mechanism. In this paper, we propose a novel hybrid framework for TSE, which integrates both high-level domain-knowledge and robust low-level saliency assumptions and can overcome drawbacks caused by direct mapping in traditional TSE approaches. The new framework integrated the Neutro-Connectedness (NC) map, the adaptive-center, the correlation and the layer structure-based weighted map. The experimental results demonstrate that the proposed approach outperforms state-of-the-art TSE methods.