One Network to Solve All ROIs: Deep Learning CT for Any ROI using Differentiated Backprojection

PURPOSE Computed tomography for the reconstruction of region of interest (ROI) has advantages in reducing the x-ray dose and the use of a small detector. However, standard analytic reconstruction methods such as filtered back projection (FBP) suffer from severe cupping artifacts, and existing model-based iterative reconstruction methods require extensive computations. Recently, we proposed a deep neural network to learn the cupping artifacts, but the network was not generalized well for different ROIs due to the singularities in the corrupted images. Therefore, there is an increasing demand for a neural network that works well for any ROI size. METHOD Two types of neural networks are designed. The first type learns ROI size-specific cupping artifacts from FBP images, whereas the second type network is for the inversion of the truncated Hilbert transform from the truncated differentiated backprojection (DBP) data. Their generalizabilities for different ROI sizes, pixel sizes, detector pitch and starting angles for a short scan are then investigated. RESULTS Experimental results show that the new type of neural networks significantly outperform existing iterative methods for all ROI sizes despite significantly lower runtime complexity. In addition, performance improvement is consistent across different acquisition scenarios. CONCLUSIONS Since the proposed method consistently surpasses existing methods, it can be used as a general CT reconstruction engine for many practical applications without compromising possible detector truncation.

[1]  M. Defrise,et al.  Solving the interior problem of computed tomography using a priori knowledge , 2008, Inverse problems.

[2]  Jong Chul Ye,et al.  Deep Convolutional Framelets: A General Deep Learning Framework for Inverse Problems , 2017, SIAM J. Imaging Sci..

[3]  Liang Li,et al.  Interior Tomography With Continuous Singular Value Decomposition , 2012, IEEE Transactions on Medical Imaging.

[4]  Michael Unser,et al.  Interior Tomography Using 1D Generalized Total Variation. Part II: Multiscale Implementation , 2015, SIAM J. Imaging Sci..

[5]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[6]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[7]  Hengyong Yu,et al.  Compressive Sensing–Based Interior Tomography: Preliminary Clinical Application , 2011, Journal of computer assisted tomography.

[8]  K. Stierstorfer,et al.  Image reconstruction and image quality evaluation for a 64-slice CT scanner with z-flying focal spot. , 2005, Medical physics.

[9]  Jong Chul Ye,et al.  A deep convolutional neural network using directional wavelets for low‐dose X‐ray CT reconstruction , 2016, Medical physics.

[10]  Michael Unser,et al.  Interior Tomography Using 1D Generalized Total Variation. Part I: Mathematical Foundation , 2015, SIAM J. Imaging Sci..

[11]  F. Noo,et al.  Cone-beam reconstruction using 1D filtering along the projection of M-lines , 2005 .

[12]  Hiroyuki Kudo,et al.  Truncated Hilbert transform and image reconstruction from limited tomographic data , 2006 .

[13]  Jong Chul Ye,et al.  Deep Learning Interior Tomography for Region-of-Interest Reconstruction , 2017, ArXiv.

[14]  Jong Chul Ye,et al.  Deep Residual Learning for Compressed Sensing CT Reconstruction via Persistent Homology Analysis , 2016, ArXiv.

[15]  Xiaochuan Pan,et al.  Image reconstruction on PI-lines by use of filtered backprojection in helical cone-beam CT. , 2004, Physics in medicine and biology.

[16]  Jaejun Yoo,et al.  Deep Convolutional Framelet Denosing for Low-Dose CT via Wavelet Residual Network , 2017, IEEE Transactions on Medical Imaging.

[17]  Alexander Katsevich,et al.  Finite Hilbert transform with incomplete data: null-space and singular values , 2012 .

[18]  Jong Chul Ye,et al.  Framing U-Net via Deep Convolutional Framelets: Application to Sparse-View CT , 2017, IEEE Transactions on Medical Imaging.

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

[20]  Jean-Baptiste Thibault,et al.  Algorithm to extend reconstruction field-of-view , 2004, 2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821).

[21]  Michael Unser,et al.  Deep Convolutional Neural Network for Inverse Problems in Imaging , 2016, IEEE Transactions on Image Processing.

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

[23]  Jong Chul Ye,et al.  Understanding Geometry of Encoder-Decoder CNNs , 2019, ICML.

[24]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[25]  M. Defrise,et al.  Single-slice rebinning method for helical cone-beam CT. , 1999, Physics in medicine and biology.

[26]  Xiaochuan Pan,et al.  Exact image reconstruction on PI-lines from minimum data in helical cone-beam CT. , 2004, Physics in medicine and biology.

[27]  Alexander Katsevich,et al.  Stability of the interior problem with polynomial attenuation in the region of interest , 2012 .

[28]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.