Department of Electronic Engineering, Fudan University, No. 220, Handan Road, Yangpu District, Shanghai, 200433, China.
Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention (MICCAI) of Shanghai, Shanghai, 200032, China.
J Digit Imaging. 2020 Oct;33(5):1266-1279. doi: 10.1007/s10278-020-00366-6.
The accurate localization of nodules in ultrasound images can convey crucial information to support a reliable diagnosis. However, this is usually challenging due to low contrast and image artifacts, especially in thyroid ultrasound images where nodules are relatively small in most cases. To address these problems, in this paper, we propose a joint-training convolutional neural network (CNN) for thyroid nodule localization in ultrasound images. Considering the advantage of the faster region-based CNN (Faster R-CNN) in detecting natural targets, we adopt it as the basic framework. To boost the representative power and noise suppression capability of the network, the attention mechanism module is embedded for adaptive feature refinement along the channel and spatial dimensions. Furthermore, in the training process, we annotate the training set in a novel way, called joint-training annotation, by exploiting the fake foreground (FFG) area around the nodule as a spatial prior constraint to improve the sensitivity to small nodules. Ablation experiments are conducted to verify the effectiveness of our proposed method. The experimental results show that our method outperforms others by a mean average precision (mAP) of 0.93 and achieves an intersection over union (IoU) of 0.9, indicating that the localization results agree well with the ground truth. Furthermore, extended experiments on breast nodule datasets are also conducted to verify the generalizability of the proposed approach. Above all, the proposed algorithm is of considerable significance for accurate thyroid nodule localization in ultrasound images and can be generalized to other types of nodules, thereby providing trustworthy assistance for clinical diagnosis.
超声图像中结节的准确定位可以提供关键信息，以支持可靠的诊断。然而，由于对比度低和图像伪影，特别是在甲状腺超声图像中，大多数情况下结节相对较小，这通常具有挑战性。为了解决这些问题，在本文中，我们提出了一种联合训练卷积神经网络（CNN），用于甲状腺超声图像中的结节定位。考虑到基于区域的更快 CNN（Faster R-CNN）在检测自然目标方面的优势，我们将其作为基本框架。为了提高网络的代表性和噪声抑制能力，嵌入注意力机制模块，以沿通道和空间维度自适应地进行特征细化。此外，在训练过程中，我们通过利用结节周围的虚假前景（FFG）区域作为空间先验约束，以提高对小结节的敏感性，以一种新的称为联合训练标注的方式对训练集进行标注。进行了消融实验以验证所提出方法的有效性。实验结果表明，我们的方法的平均精度（mAP）为 0.93，交并比（IoU）为 0.9，优于其他方法，这表明定位结果与地面实况吻合较好。此外，还对乳腺结节数据集进行了扩展实验，以验证所提出方法的泛化能力。总之，所提出的算法对于超声图像中准确的甲状腺结节定位具有重要意义，并且可以推广到其他类型的结节，从而为临床诊断提供可靠的辅助。
