Department of Biomedical Engineering, College of Materials Science and Engineering, Sichuan University, Chengdu, China.
Department of Ultrasound, West China Hospital of Sichuan University, Chengdu, China.
J Xray Sci Technol. 2019;27(5):839-856. doi: 10.3233/XST-190548.
Breast cancer has the highest cancer prevalence rate among the women worldwide. Early detection of breast cancer is crucial for successful treatment and reducing cancer mortality rate. However, tumor detection of breast ultrasound (US) image is still a challenging work in computer-aided diagnosis (CAD).
This study aims to develop a novel automated algorithm for breast tumor detection based on deep learning.
We proposed a new deep learning network named One-step model which have one input and two outputs, the first one was the segmentation result and the other one was used for false-positive reduction. The proposed One-step model includes three key components: Base-net, Seg-net, and Cls-net based on Anchor Box. The model chose DenseNet to construct Base-net, the decoder part of RefineNet as Seg-net, and connected several middle layers of Base-net and Seg-net to Cls-net. From the first output acquired by Base-net and Seg-net, the model detected a series of suspicious lesion regions. Then the second output from the Cls-net was used to recognize and reduce the false-positive regions.
Experimental results showed that the new model achieved competitive detection result with 90.78% F1 score, which was 8.55% higher than Single Shot MultiBox Detector (SSD) method. In addition, running new model is also computational efficient and has comparative cost effect as SSD.
We established a novel One-step model which improves location accuracy by generating more precise bounding box via Seg-net and removing false targets by another object detection network (Cls-net). On the other hand, a real-time detection of tumor is achieved by sharing the common Base-net. The experimental results showed that the new model performed well on various irregular and blurred ultrasound images. As a result, this study demonstrated feasibility of applying deep learning scheme to detect breast lesions depicting on US image.
乳腺癌是全球女性中患病率最高的癌症。早期发现乳腺癌对于成功治疗和降低癌症死亡率至关重要。然而，乳腺超声（US）图像的肿瘤检测仍然是计算机辅助诊断（CAD）中的一项具有挑战性的工作。
本研究旨在开发一种基于深度学习的新型自动乳腺肿瘤检测算法。
我们提出了一种新的深度学习网络，称为一步模型，它有一个输入和两个输出，第一个是分割结果，另一个用于减少假阳性。所提出的一步模型包括三个关键组件：基于 Anchor Box 的 Base-net、Seg-net 和 Cls-net。该模型选择 DenseNet 构建 Base-net，RefineNet 的解码器部分作为 Seg-net，并将 Base-net 和 Seg-net 的几个中间层连接到 Cls-net。从 Base-net 和 Seg-net 获得的第一个输出中，模型检测到一系列可疑的病变区域。然后，从 Cls-net 获得的第二个输出用于识别和减少假阳性区域。
实验结果表明，新模型的检测结果具有竞争力，F1 得分为 90.78%，比单镜头多盒探测器（SSD）方法高 8.55%。此外，新模型的运行效率也很高，具有与 SSD 相当的成本效益。
我们建立了一种新的一步模型，该模型通过 Seg-net 生成更精确的边界框来提高定位精度，并通过另一个目标检测网络（Cls-net）去除假目标。另一方面，通过共享公共 Base-net 实现肿瘤的实时检测。实验结果表明，该新模型在各种不规则和模糊的超声图像上表现良好。因此，本研究证明了将深度学习方案应用于检测 US 图像上描绘的乳腺病变的可行性。
