CT-image Super Resolution Using 3D Convolutional Neural Network
This work addresses the lack of effective super-resolution algorithms for 3D CT images, which is important for applications in geological exploration and medical diagnosis, but it is incremental as it builds on existing deep learning approaches.
The authors tackled the problem of low-resolution CT images by proposing a 3D convolutional neural network (3DSRCNN) for super-resolution, achieving better performance in PSNR, SSIM, and efficiency compared to conventional methods.
Computed Tomography (CT) imaging technique is widely used in geological exploration, medical diagnosis and other fields. In practice, however, the resolution of CT image is usually limited by scanning devices and great expense. Super resolution (SR) methods based on deep learning have achieved surprising performance in two-dimensional (2D) images. Unfortunately, there are few effective SR algorithms for three-dimensional (3D) images. In this paper, we proposed a novel network named as three-dimensional super resolution convolutional neural network (3DSRCNN) to realize voxel super resolution for CT images. To solve the practical problems in training process such as slow convergence of network training, insufficient memory, etc., we utilized adjustable learning rate, residual-learning, gradient clipping, momentum stochastic gradient descent (SGD) strategies to optimize training procedure. In addition, we have explored the empirical guidelines to set appropriate number of layers of network and how to use residual learning strategy. Additionally, previous learning-based algorithms need to separately train for different scale factors for reconstruction, yet our single model can complete the multi-scale SR. At last, our method has better performance in terms of PSNR, SSIM and efficiency compared with conventional methods.