Abstract

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.

Highlights

  • Prostate cancer is a malignant tumor that will pose great threats to middle-aged and elderly males

  • We have introduced the proposed image generation technique into prostate MR image classification method based on Laplacian eigenmaps network (LENet) [25] and network-in-network (NIN) [26]

  • To evaluate the effectiveness of CapGAN in generating realistic MR images, several experiments have been performed on different datasets including the well-known BrainWeb phantom [35] and the real prostate Magnetic resonance imaging (MRI) dataset [36,37,38]

Read more

Summary

Introduction

Prostate cancer is a malignant tumor that will pose great threats to middle-aged and elderly males. According to the Global Cancer Report 2018 issued by the International Agency for Research on Cancer (IARC) of the World Health Organization, the incidence rate of prostate cancer ranks the second and its mortality rate is in the top five among male tumors in the world [1]. Diagnosis is critical for reducing the harm of prostate cancer. Magnetic resonance imaging (MRI) has become the optimal imaging technique for the detection and diagnosis of prostate cancer due to its higher accuracy over transrectal ultrasonography (TRUS) and prostate-specific antigen (PSA) [2]. Images, can clearly display the anatomical and functional information of prostate regions due to different information from various modalities [3]. Compared with the single modality, mp-MRI has Sensors 2020, 20, 5736; doi:10.3390/s20205736 www.mdpi.com/journal/sensors

Methods
Results
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.