Deep learning-based noise reduction algorithm using patch group technique in cadmium zinc telluride fusion imaging system: A Monte Carlo simulation study

Abstract Anatomical and functional fusion imaging systems using cadmium zinc telluride (CZT) are widely used in the field of medical imaging and nuclear-medicine. However, noise is inevitable in the CZT images, and reducing noise is thus crucial for accurate diagnosis of diseases. Among various available techniques for noise reduction in images, deep learning-based noise reduction algorithm using patch group is considered the most efficient method. Therefore, this study is focused on designing deep learning-based noise reduction algorithm using patch group and evaluating it using simulated CZT fusion images with X-ray and gamma ray. We used the Geant4 Application for Tomographic Emission (version 6), which is a Monte Carlo simulation tool, and the normalized noise power spectrum, coefficient of variation (COV), and contrast to noise ratio (CNR) were evaluated. Furthermore, the proposed deep learning-based noise reduction algorithm exhibited better values compared with the conventional noise reduction algorithms. In particular, the COV and CNR values of our algorithm were approximately 8.46 and 1.85 times better than that of the original CZT image. Thus, we successfully demonstrated the feasibility of the proposed deep learning-based noise reduction algorithm using the patch group technique in a CZT fusion imaging system.

[2]  K. Laukamp,et al.  Reduction of artifacts caused by orthopedic hardware in the spine in spectral detector CT examinations using virtual monoenergetic image reconstructions and metal-artifact-reduction algorithms , 2018, Skeletal Radiology.

[3]  A. D. Vaiopoulos.  Developing Matlab scripts for image analysis and quality assessment , 2011, Remote Sensing.

[4]  Marc Moonen,et al.  Low-rank Approximation Based Multichannel Wiener Filter Algorithms for Noise Reduction with Application in Cochlear Implants , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[5]  He Ma,et al.  An Automatic Detection System of Lung Nodule Based on Multigroup Patch-Based Deep Learning Network , 2018, IEEE Journal of Biomedical and Health Informatics.

[6]  Xiaokang Yang,et al.  An Optimized Pixel-Wise Weighting Approach for Patch-Based Image Denoising , 2015, IEEE Signal Processing Letters.

[7]  Hamid Reza Shahdoosti,et al.  MRI and PET image fusion using structure tensor and dual ripplet-II transform , 2017, Multimedia Tools and Applications.

[8]  Donald W. Wilson,et al.  SemiSPECT: a small-animal single-photon emission computed tomography (SPECT) imager based on eight cadmium zinc telluride (CZT) detector arrays. , 2006, Medical physics.

[9]  Weiguo Gong,et al.  Combining edge difference with nonlocal self-similarity constraints for single image super-resolution , 2017, Neurocomputing.

[10]  E. Even-Sapir,et al.  Fused functional-anatomic images of metastatic cancer of cervix obtained by a combined gamma camera and an X-ray tube hybrid system with an illustrative case and review of the 18F-fluorodeoxyglucose literature. , 2003, Gynecologic oncology.

[11]  B. Lu,et al.  Image quality and diagnostic accuracy of coronary CT angiography derived from low-dose dynamic CT myocardial perfusion: a feasibility study with comparison to invasive coronary angiography , 2018, European Radiology.

[13]  M. Pradeep.  Implementation of image fusion algorithm using MATLAB (LAPLACIAN PYRAMID) , 2013, 2013 International Mutli-Conference on Automation, Computing, Communication, Control and Compressed Sensing (iMac4s).

[14]  Thomas Beyer,et al.  X-ray-based attenuation correction for positron emission tomography/computed tomography scanners. , 2003, Seminars in nuclear medicine.

[15]  Ying Chen,et al.  Intercomparison of methods for image quality characterization. II. Noise power spectrum. , 2006, Medical physics.

[16]  C. Budtz-Jørgensen,et al.  Response of CZT drift-strip detector to X- and gamma rays , 2001 .

[17]  Yuko Nakamura,et al.  Improvement of image quality at CT and MRI using deep learning , 2018, Japanese Journal of Radiology.

[18]  C. Mistretta,et al.  Noise reduction in spectral CT: reducing dose and breaking the trade-off between image noise and energy bin selection. , 2011, Medical physics.

[19]  Joon Koo Han,et al.  Hybrid iterative reconstruction technique for liver CT scans for image noise reduction and image quality improvement: evaluation of the optimal iterative reconstruction strengths , 2014, La radiologia medica.

[20]  Nilamani Bhoi,et al.  Total Variation Based Wavelet Domain Filter for Image Denoising , 2008, 2008 First International Conference on Emerging Trends in Engineering and Technology.

[21]  Wen-Xiong Kang,et al.  The Comparative Research on Image Segmentation Algorithms , 2009, 2009 First International Workshop on Education Technology and Computer Science.

[22]  J Ophir,et al.  An analysis of elastographic contrast-to-noise ratio. , 1998, Ultrasound in medicine & biology.

[23]  Kishore Rajendiran,et al.  Multi sensor image fusion for surveillance applications using hybrid image fusion algorithm , 2017, Multimedia Tools and Applications.

[24]  J M Boone,et al.  Comparison of x-ray cross sections for diagnostic and therapeutic medical physics. , 1996, Medical physics.

[25]  Derek C. Rose,et al.  Deep Machine Learning - A New Frontier in Artificial Intelligence Research [Research Frontier] , 2010, IEEE Computational Intelligence Magazine.

[26]  Hongming Zhang,et al.  Speckle noise reduction algorithm with total variation regularization in optical coherence tomography. , 2015, Optics express.

[27]  Charles E. Brown.  Coefficient of Variation , 1998 .

[28]  R. Sadeghi,et al.  Development of GATE Monte Carlo simulation for a dual-head gamma camera , 2012, Radiological Physics and Technology.

[29]  David Zhang,et al.  Patch Group Based Nonlocal Self-Similarity Prior Learning for Image Denoising , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[30]  Yinan Kong,et al.  Efficient Hardware Implementation For Fingerprint Image Enhancement Using Anisotropic Gaussian Filter , 2017, IEEE Transactions on Image Processing.

[31]  Yike Liu,et al.  Noise reduction by vector median filtering , 2013 .

[32]  Irène Buvat,et al.  Optimization of a parallel hole collimator/CdZnTe gamma-camera architecture for scintimammography. , 2011, Medical physics.

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

[34]  Jin-Suck Suh,et al.  Metal artefact reduction in gemstone spectral imaging dual-energy CT with and without metal artefact reduction software , 2012, European Radiology.