Shen Tianyu, Hao Kunkun, Gou Chao, Wang Fei-Yue
Institute of Automation, Chinese Academy of Sciences, Beijing, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China.
School of Software Engineering, Xi'an Jiaotong University, Xi'an, China.
Comput Methods Programs Biomed. 2021 Apr;202:106019. doi: 10.1016/j.cmpb.2021.106019. Epub 2021 Feb 20.
In medical imaging, the scarcity of labeled lesion data has hindered the application of many deep learning algorithms. To overcome this problem, the simulation of diverse lesions in medical images is proposed. However, synthesizing labeled mass images in mammograms is still challenging due to the lack of consistent patterns in shape, margin, and contextual information. Therefore, we aim to generate various labeled medical images based on contextual information in mammograms.
In this paper, we propose a novel approach based on GANs to generate various mass images and then perform contextual infilling by inserting the synthetic lesions into healthy screening mammograms. Through incorporating features of both realistic mass images and corresponding masks into the adversarial learning scheme, the generator can not only learn the distribution of the real mass images but also capture the matching shape, margin and context information.
To demonstrate the effectiveness of our proposed method, we conduct experiments on publicly available mammogram database of DDSM and a private database provided by Nanfang Hospital in China. Qualitative and quantitative evaluations validate the effectiveness of our approach. Additionally, through the data augmentation by image generation of the proposed method, an improvement of 5.03% in detection rate can be achieved over the same model trained on original real lesion images.
The results show that the data augmentation based on our method increases the diversity of dataset. Our method can be viewed as one of the first steps toward generating labeled breast mass images for precise detection and can be extended in other medical imaging domains to solve similar problems.
在医学成像中，标记病变数据的稀缺阻碍了许多深度学习算法的应用。为克服这一问题，人们提出了在医学图像中模拟各种病变的方法。然而，由于乳腺钼靶图像中缺乏形状、边缘和上下文信息的一致模式，合成标记的肿块图像仍然具有挑战性。因此，我们旨在基于乳腺钼靶图像中的上下文信息生成各种标记的医学图像。
在本文中，我们提出了一种基于生成对抗网络（GANs）的新方法来生成各种肿块图像，然后通过将合成病变插入健康的筛查乳腺钼靶图像中来进行上下文填充。通过将逼真的肿块图像及其相应掩码的特征纳入对抗学习方案，生成器不仅可以学习真实肿块图像的分布，还可以捕捉匹配的形状、边缘和上下文信息。
为了证明我们提出的方法的有效性，我们在公开可用的数字数据库乳腺影像存档与通信系统（DDSM）数据库以及中国南方医院提供的一个私有数据库上进行了实验。定性和定量评估验证了我们方法的有效性。此外，通过我们提出的方法进行图像生成的数据增强，与在原始真实病变图像上训练的相同模型相比，检测率可提高5.03%。
结果表明，基于我们方法的数据增强增加了数据集的多样性。我们的方法可被视为朝着生成用于精确检测的标记乳腺肿块图像迈出的第一步之一，并且可以在其他医学成像领域进行扩展以解决类似问题。
