Li Yujie, Gu Hong, Wang Hongyu, Qin Pan, Wang Jia
Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, China.
Department of Surgery, The Second Hospital of Dalian Medical University, Dalian, China.
Front Oncol. 2022 Mar 25;12:848271. doi: 10.3389/fonc.2022.848271. eCollection 2022.
Ultrasound (US) imaging is a main modality for breast disease screening. Automatically detecting the lesions in US images is essential for developing the artificial-intelligence-based diagnostic support technologies. However, the intrinsic characteristics of ultrasound imaging, like speckle noise and acoustic shadow, always degenerate the detection accuracy. In this study, we developed a deep learning model called BUSnet to detect the breast tumor lesions in US images with high accuracy. We first developed a two-stage method including the unsupervised region proposal and bounding-box regression algorithms. Then, we proposed a post-processing method to enhance the detecting accuracy further. The proposed method was used to a benchmark dataset, which includes 487 benign samples and 210 malignant samples. The results proved the effectiveness and accuracy of the proposed method.
超声（US）成像为乳腺疾病筛查的主要方式。自动检测超声图像中的病灶对于开发基于人工智能的诊断支持技术至关重要。然而，超声成像的固有特性，如斑点噪声和声学阴影，总是会降低检测精度。在本研究中，我们开发了一种名为BUSnet的深度学习模型，以高精度检测超声图像中的乳腺肿瘤病灶。我们首先开发了一种两阶段方法，包括无监督区域提议和边界框回归算法。然后，我们提出了一种后处理方法以进一步提高检测精度。所提出的方法应用于一个基准数据集，该数据集包括487个良性样本和210个恶性样本。结果证明了所提出方法的有效性和准确性。
