Ministry of Education Key Laboratory of Molecular Biophysics, Department of Biomedical Engineering, School of Life Science and Technology, Huazhong University of Science and Technology, No 1037, Luoyu Road, Wuhan 430074, China.
Department of Mathematics and Statistics, Hubei University of Science and Technology, No 88, Xianning Road, Xianning 437000, China.
Sensors (Basel). 2020 Oct 9;20(20):5736. doi: 10.3390/s20205736.
Prostate cancer remains a major health concern among elderly men. Deep learning is a state-of-the-art technique for MR image-based prostate cancer diagnosis, but one of major bottlenecks is the severe lack of annotated MR images. The traditional and Generative Adversarial Network (GAN)-based data augmentation methods cannot ensure the quality and the diversity of generated training samples. In this paper, we have proposed a novel GAN model for synthesis of MR images by utilizing its powerful ability in modeling the complex data distributions. The proposed model is designed based on the architecture of deep convolutional GAN. To learn the more equivariant representation of images that is robust to the changes in the pose and spatial relationship of objects in the images, the capsule network is applied to replace CNN used in the discriminator of regular GAN. Meanwhile, the least squares loss has been adopted for both the generator and discriminator in the proposed GAN to address the vanishing gradient problem of sigmoid cross entropy loss function in regular GAN. Extensive experiments are conducted on the simulated and real MR images. The results demonstrate that the proposed capsule network-based GAN model can generate more realistic and higher quality MR images than the compared GANs. The quantitative comparisons show that among all evaluated models, the proposed GAN generally achieves the smallest Kullback-Leibler divergence values for image generation task and provides the best classification performance when it is introduced into the deep learning method for image classification task.
前列腺癌仍然是老年男性的主要健康关注点。深度学习是基于磁共振成像（MR）的前列腺癌诊断的一种先进技术，但主要瓶颈之一是缺乏大量标注的 MR 图像。传统的和基于生成对抗网络（GAN）的数据增强方法不能保证生成训练样本的质量和多样性。在本文中，我们提出了一种新的基于 GAN 的方法来合成 MR 图像，利用其强大的建模复杂数据分布的能力。所提出的模型基于深度卷积 GAN 的架构设计。为了学习更等变的图像表示，该模型对图像中物体的姿态和空间关系的变化具有鲁棒性，将胶囊网络应用于替换常规 GAN 中鉴别器中使用的 CNN。同时，在所提出的 GAN 中，对生成器和鉴别器都采用了最小二乘损失，以解决常规 GAN 中 sigmoid 交叉熵损失函数的梯度消失问题。在模拟和真实的 MR 图像上进行了广泛的实验。结果表明，与其他 GAN 相比，基于胶囊网络的 GAN 模型可以生成更真实、更高质量的 MR 图像。定量比较表明，在所评估的所有模型中，所提出的 GAN 在图像生成任务中通常可以获得最小的 Kullback-Leibler 散度值，并且在将其引入用于图像分类任务的深度学习方法时可以提供最佳的分类性能。
