IEEE Trans Ultrason Ferroelectr Freq Control. 2021 Dec;68(12):3549-3559. doi: 10.1109/TUFFC.2021.3098308. Epub 2021 Nov 23.
Automated breast ultrasound image segmentation is essential in a computer-aided diagnosis (CAD) system for breast tumors. In this article, we present a feature pyramid nonlocal network (FPNN) with transform modal ensemble learning (TMEL) for accurate breast tumor segmentation in ultrasound images. Specifically, the FPNN fuses multilevel features under special consideration of long-range dependencies by combining the nonlocal module and feature pyramid network. Additionally, the TMEL is introduced to guide two iFPNNs to extract different tumor details. Two publicly available datasets, i.e., the Dataset-Cairo University and Dataset-Merge, were used for evaluation. The proposed FPNN-TMEL achieves a Dice score of 84.70% ± 0.53%, Jaccard Index (Jac) of 78.10% ± 0.48% and Hausdorff distance (HD) of 2.815 ± 0.016 mm on the Dataset-Cairo University, and Dice of 87.00% ± 0.41%, Jac of 79.16% ± 0.56%, and HD of 2.781±0.035 mm on the Dataset-Merge. Qualitative and quantitative experiments show that our method outperforms other state-of-the-art methods for breast tumor segmentation in ultrasound images. Our code is available at https://github.com/pixixiaonaogou/FPNN-TMEL.
自动乳腺超声图像分割是计算机辅助诊断（CAD）系统中乳腺肿瘤的关键。在本文中，我们提出了一种特征金字塔非局部网络（FPNN）与变换模态集成学习（TMEL），用于在超声图像中进行精确的乳腺肿瘤分割。具体来说，FPNN 通过结合非局部模块和特征金字塔网络，特别考虑了长程依赖关系，融合了多层次的特征。此外，引入 TMEL 来指导两个 iFPNN 提取不同的肿瘤细节。我们使用了两个公开的数据集，即 Cairo 大学数据集和 Merge 数据集进行评估。在 Cairo 大学数据集上，我们提出的 FPNN-TMEL 取得了 Dice 分数 84.70%±0.53%、Jaccard 指数（Jac）78.10%±0.48%和 Hausdorff 距离（HD）2.815±0.016mm 的结果；在 Merge 数据集上，Dice 分数为 87.00%±0.41%、Jac 分数为 79.16%±0.56%和 HD 分数为 2.781±0.035mm。定性和定量实验表明，我们的方法在超声图像中的乳腺肿瘤分割方面优于其他最先进的方法。我们的代码可在 https://github.com/pixixiaonaogou/FPNN-TMEL 上获取。
