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.
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.
Authors: Nathan R Huber; Andrew D Missert; Hao Gong; Scott S Hsieh; Shuai Leng; Lifeng Yu; Cynthia H McCollough Journal: Proc SPIE Int Soc Opt Eng Date: 2021-02-15
Authors: Nathan R Huber; Andrea Ferrero; Kishore Rajendran; Francis Baffour; Katrina N Glazebrook; Felix E Diehn; Akitoshi Inoue; Joel G Fletcher; Lifeng Yu; Shuai Leng; Cynthia H McCollough Journal: Phys Med Biol Date: 2022-09-02 Impact factor: 4.174
Authors: Darin P Clark; Fides R Schwartz; Daniele Marin; Juan C Ramirez-Giraldo; Cristian T Badea Journal: Med Phys Date: 2020-07-06 Impact factor: 4.071
Authors: Tonghe Wang; Yang Lei; Yabo Fu; Jacob F Wynne; Walter J Curran; Tian Liu; Xiaofeng Yang Journal: J Appl Clin Med Phys Date: 2020-12-11 Impact factor: 2.102
Authors: Taylor R Moen; Baiyu Chen; David R Holmes; Xinhui Duan; Zhicong Yu; Lifeng Yu; Shuai Leng; Joel G Fletcher; Cynthia H McCollough Journal: Med Phys Date: 2020-12-16 Impact factor: 4.071