Synthesizing images from multiple kernels using a deep convolutional neural network.

PURPOSE Filtering measured projections with a particular convolutional kernel is an essential step in analytic reconstruction of computed tomography (CT) images. A tradeoff between noise and spatial resolution exists for different choices of reconstruction kernel. In a clinical setting, this often requires producing multiple images reconstructed with different kernels for a single CT exam, which increases the burden of computation, networking, archival, and reading. We address this problem by training a deep convolutional neural network (CNN) to synthesize multiple input images into a single output image which exhibits low noise while also preserving features in images reconstructed with the sharpest kernels. METHODS A CNN architecture consisting of repeated blocks of residual units containing a total of 20 convolutional layers was used to combine features. The CNN inputs consisted of two images produced with different reconstruction kernels, one smooth and one sharp, which were stacked in the channel dimension. The network was trained using supervised learning with both full-dose and simulated quarter-dose abdominal CT images. After training, the performance was evaluated using a reserved set of full-dose scans that were not used for network optimization. Noise reduction performance was measured by comparing root mean square (RMS) measurements in uniform regions. Spatial resolution was compared using line profiles of anatomic features. RESULTS For the regions tested, the synthetic images feature noise levels slightly below those of the smooth input images, while maintaining the resolution of anatomic details found in the sharp input images. CONCLUSIONS A deep CNN can be used combine features from CT images reconstructed with different kernels to produce a single synthesized image series that exhibits both low noise and high spatial resolution. This approach has implications for improving image quality, reducing radiation dose, and simplifying the clinical workflow for CT imaging.

[1]  Xuanqin Mou,et al.  Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss , 2017, IEEE Transactions on Medical Imaging.

[2]  Feng Lin,et al.  Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network , 2017, IEEE Transactions on Medical Imaging.

[3]  Paul Babyn,et al.  Sharpness-Aware Low-Dose CT Denoising Using Conditional Generative Adversarial Network , 2017, Journal of Digital Imaging.

[4]  M. Shiung,et al.  Development and Validation of a Practical Lower-Dose-Simulation Tool for Optimizing Computed Tomography Scan Protocols , 2012, Journal of computer assisted tomography.

[5]  Baiyu Chen,et al.  Low‐dose CT for the detection and classification of metastatic liver lesions: Results of the 2016 Low Dose CT Grand Challenge , 2017, Medical physics.

[6]  Uwe Kruger,et al.  Competitive performance of a modularized deep neural network compared to commercial algorithms for low-dose CT image reconstruction , 2019, Nat. Mach. Intell..

[7]  Marc Kachelrieß,et al.  Alpha image reconstruction (AIR): a new iterative CT image reconstruction approach using voxel-wise alpha blending. , 2014, Medical physics.

[8]  Mannudeep K. Kalra,et al.  Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN) , 2017, ArXiv.

[9]  Lifeng Yu,et al.  Simulation of CT images reconstructed with different kernels using a convolutional neural network and its implications for efficient CT workflow , 2019, Medical Imaging.

[10]  Zhuowen Tu,et al.  Aggregated Residual Transformations for Deep Neural Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Dongmei Sun,et al.  Hybrid convolution kernel: optimized CT of the head, neck, and spine. , 2011, AJR. American journal of roentgenology.

[12]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).