Image domain dual material decomposition for dual-energy CT using butterfly network.

PURPOSE Dual-energy CT (DECT) has been increasingly used in imaging applications because of its capability for material differentiation. However, material decomposition suffers from magnified noise from two CT images of independent scans, leading to severe degradation of image quality. Existing algorithms exhibit suboptimal decomposition performance because they fail to fully depict the mapping relationship between DECT images and basis materials under noisy conditions. Convolutional neural network exhibits great promise in the modeling of data coupling and has recently become an important technique in medical imaging application. Inspired by its impressive potential, we developed a new Butterfly network to perform the image domain dual material decomposition. METHODS The Butterfly network is derived from the model of image domain DECT decomposition by exploring the geometric relationship between the mapping functions of the data model and network components. The network is designed as the double-entry double-out crossover architecture based on the decomposition formulation. It enters a pair of dual-energy images as inputs and defines the ground true decomposed images as each label. The crossover architecture, which plays an important role in material decomposition, is designed to implement the information exchange between the two material generation pathways in the network. The proposed network is further applied on the digital phantom and clinical data to evaluate its performance. RESULTS The qualitative and quantitative evaluations of the material decomposition of digital phantoms and clinical data indicate that the proposed network outperforms its counterparts. For the digital phantom, the proposed network reduces the standard deviation (SD) of noise in tissue, bone, and mixture regions by an average of 95.75% and 86.58% compared with the direct matrix inversion and the conventional iterative method, respectively. The line profiles and image biases of the decomposition results of digital phantom indicate that the proposed network provides the decomposition results closest to the ground truth. The proposed network reduces the SD of the noise in decomposed images of clinical head data by over 90% and 80% compared with the direct matrix inversion and conventional iterative method, respectively. As the modulation transfer function decreases to 50%, the proposed network increases the spatial resolution by average factors of 1.34 and 1.17 compared with the direct matrix inversion and conventional iterative methods, respectively. The proposed network is further applied to the clinical abdomen data. Among the three methods, the proposed method received the highest score from six radiologists in the visual inspection of noise suppression in the clinical data. CONCLUSIONS We develop a model-based Butterfly network to perform image domain material decomposition for DECT. The decomposition results of digital phantom validate its capability of decomposing two basis materials from DECT images. The proposed approach also leads to higher decomposition quality in noise suppression on clinical datasets as compared with those using conventional schemes.

[1]  Yann LeCun,et al.  Learning Fast Approximations of Sparse Coding , 2010, ICML.

[2]  Xiaochuan Pan,et al.  Algorithm-enabled partial-angular-scan configurations for dual-energy CT. , 2018, Medical physics.

[3]  Lei Zhu,et al.  Noise suppression for dual-energy CT via penalized weighted least-square optimization with similarity-based regularization. , 2016, Medical physics.

[4]  W. D. Friedman,et al.  Review of dual-energy computed tomography techniques , 1990 .

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

[6]  Guang-Hong Chen,et al.  Dual energy CT using slow kVp switching acquisition and prior image constrained compressed sensing , 2010, Physics in medicine and biology.

[7]  Philip Schniter,et al.  Onsager-corrected deep learning for sparse linear inverse problems , 2016, 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

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

[9]  Ken D. Sauer,et al.  Model-Based Iterative Reconstruction for Dual-Energy X-Ray CT Using a Joint Quadratic Likelihood Model , 2014, IEEE Transactions on Medical Imaging.

[10]  P. Joseph,et al.  Noise considerations in dual energy CT scanning. , 1979, Medical physics.

[11]  Xiaochuan Pan,et al.  Image reconstruction and scan configurations enabled by optimization-based algorithms in multispectral CT , 2017, Physics in medicine and biology.

[12]  James T Dobbins,et al.  Quantitative , 2020, Psychology through Critical Auto-Ethnography.

[13]  W. Marsden.  I and J , 2012 .

[14]  Jeffrey A. Fessler,et al.  Multi-Material Decomposition Using Statistical Image Reconstruction for Spectral CT , 2014, IEEE Transactions on Medical Imaging.

[15]  R. Siddon.  Fast calculation of the exact radiological path for a three-dimensional CT array. , 1985, Medical physics.

[16]  Max A. Viergever,et al.  Generative Adversarial Networks for Noise Reduction in Low-Dose CT , 2017, IEEE Transactions on Medical Imaging.

[17]  B. R. Pullan,et al.  X-ray energies for effective atomic number determination , 2004, Neuroradiology.

[18]  Neil Genzlinger.  A. and Q , 2006 .

[19]  A. Macovski,et al.  Energy-selective reconstructions in X-ray computerised tomography , 1976, Physics in medicine and biology.

[20]  M. Reiser,et al.  Material differentiation by dual energy CT: initial experience , 2007, European Radiology.

[21]  Qing Ling,et al.  Learning A Deep $\ell_\infty$ Encoder for Hashing. , 2016, 1604.01475.

[22]  Jonas Adler,et al.  Learned Primal-Dual Reconstruction , 2017, IEEE Transactions on Medical Imaging.

[23]  Bin Dong,et al.  Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations , 2017, ICML.

[24]  M J Yaffe,et al.  Theoretical optimization of dual-energy x-ray imaging with application to mammography. , 1985, Medical physics.

[25]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[26]  Maneesha Singh,et al.  Explosives detection systems (EDS) for aviation security , 2003, Signal Process..

[27]  Alexander Binder,et al.  Evaluating the Visualization of What a Deep Neural Network Has Learned , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[28]  W. Kalender,et al.  Evaluation of a prototype dual-energy computed tomographic apparatus. I. Phantom studies. , 1986, Medical physics.

[29]  Daniele Marin,et al.  State of the art: dual-energy CT of the abdomen. , 2014, Radiology.

[30]  Xiaochuan Pan,et al.  Impact of polychromatic x-ray sources on helical, cone-beam computed tomography and dual-energy methods. , 2004, Physics in medicine and biology.

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

[32]  Marc Kachelrieß,et al.  Image-based dual energy CT using optimized precorrection functions: A practical new approach of material decomposition in image domain. , 2009, Medical physics.

[33]  T. Niu,et al.  Statistical image‐domain multimaterial decomposition for dual‐energy CT , 2017, Medical physics.

[34]  Bin Yan,et al.  Euler’s Elastica Strategy for Limited-Angle Computed Tomography Image Reconstruction , 2017, IEEE Transactions on Nuclear Science.

[35]  Hu Chen,et al.  Low-dose CT via convolutional neural network. , 2017, Biomedical optics express.

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

[37]  Thomas Flohr,et al.  Modified Dual-Energy Algorithm for Calcified Plaque Removal: Evaluation in Carotid Computed Tomography Angiography and Comparison With Digital Subtraction Angiography , 2017, Investigative radiology.

[38]  A. Macovski,et al.  Measurement-Dependent Filtering: A Novel Approach to Improved SNR , 1983, IEEE Transactions on Medical Imaging.

[39]  Ehsan Samei,et al.  Towards task-based assessment of CT performance: System and object MTF across different reconstruction algorithms. , 2012, Medical physics.

[40]  E. Samei,et al.  A method for measuring the presampled MTF of digital radiographic systems using an edge test device. , 1998, Medical physics.

[41]  Ge Wang,et al.  A Perspective on Deep Imaging , 2016, IEEE Access.

[42]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[43]  A. Macovski,et al.  Generalized image combinations in dual KVP digital radiography. , 1981, Medical physics.

[44]  James T. Dobbins,et al.  Recent progress in noise reduction and scatter correction in dual-energy imaging , 1995, Medical Imaging.

[45]  Bin Yan,et al.  Image Prediction for Limited-angle Tomography via Deep Learning with Convolutional Neural Network , 2016, ArXiv.

[46]  C. Crawford,et al.  Dual energy computed tomography for explosive detection , 2006 .

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

[48]  Aaas News,et al.  Book Reviews , 1893, Buffalo Medical and Surgical Journal.

[49]  C. McCollough,et al.  Dual- and Multi-Energy CT: Principles, Technical Approaches, and Clinical Applications. , 2015, Radiology.

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

[51]  Predrag Sukovic,et al.  Penalized weighted least-squares image reconstruction for dual energy X-ray transmission tomography , 2000, IEEE Transactions on Medical Imaging.

[52]  Lei Zhu,et al.  Iterative image-domain decomposition for dual-energy CT. , 2014, Medical physics.

[53]  Xiaochuan Pan,et al.  An algorithm for constrained one-step inversion of spectral CT data , 2015, Physics in medicine and biology.

[54]  Patrick J La Rivière,et al.  Joint reconstruction of multi-channel, spectral CT data via constrained total nuclear variation minimization , 2014, Physics in medicine and biology.

[55]  Quanzheng Li,et al.  Iterative Low-Dose CT Reconstruction With Priors Trained by Artificial Neural Network , 2017, IEEE Transactions on Medical Imaging.