Mass Segmentation in Automated 3-D Breast Ultrasound Using Dual-Path U-net

TL;DR

This paper introduces a novel deep learning-based mass segmentation method for 3-D breast ultrasound images, significantly improving accuracy over traditional methods and aiding in breast cancer detection.

Contribution

The study proposes a dual-path U-net inspired deep learning approach for mass segmentation in 3-D breast ultrasound, addressing challenges of variability and dataset imbalance.

Findings

Achieved a mean Dice score of 0.82, outperforming existing methods.

Demonstrated improved segmentation accuracy on a dataset of 50 masses.

Outperformed two-stage edge-based and region growing segmentation methods.

Abstract

Automated 3-D breast ultrasound (ABUS) is a newfound system for breast screening that has been proposed as a supplementary modality to mammography for breast cancer detection. While ABUS has better performance in dense breasts, reading ABUS images is exhausting and time-consuming. So, a computer-aided detection system is necessary for interpretation of these images. Mass segmentation plays a vital role in the computer-aided detection systems and it affects the overall performance. Mass segmentation is a challenging task because of the large variety in size, shape, and texture of masses. Moreover, an imbalanced dataset makes segmentation harder. A novel mass segmentation approach based on deep learning is introduced in this paper. The deep network that is used in this study for image segmentation is inspired by U-net, which has been used broadly for dense segmentation in recent years. The system's performance was determined using a dataset of 50 masses including 38 malign and 12 benign lesions. The proposed segmentation method attained a mean Dice of 0.82 which outperformed a two-stage supervised edge-based method with a mean Dice of 0.74 and an adaptive region growing method with a mean Dice of 0.65.