Deep learning-based attenuation map generation for myocardial perfusion SPECT

Purpose Attenuation correction using CT transmission scanning increases the accuracy of single-photon emission computed tomography (SPECT) and enables quantitative analysis. Current existing SPECT-only systems normally do not support transmission scanning and therefore scans on these systems are susceptible to attenuation artifacts. Moreover, the use of CT scans also increases radiation dose to patients and significant artifacts can occur due to the misregistration between the SPECT and CT scans as a result of patient motion. The purpose of this study is to develop an approach to estimate attenuation maps directly from SPECT emission data using deep learning methods. Methods Both photopeak window and scatter window SPECT images were used as inputs to better utilize the underlying attenuation information embedded in the emission data. The CT-based attenuation maps were used as labels with which cardiac SPECT/CT images of 65 patients were included for training and testing. We implemented and evaluated deep fully convolutional neural networks using both standard training and training using an adversarial strategy. Results The synthetic attenuation maps were qualitatively and quantitatively consistent with the CT-based attenuation map. The globally normalized mean absolute error (NMAE) between the synthetic and CT-based attenuation maps were 3.60% ± 0.85% among the 25 testing subjects. The SPECT reconstructed images corrected using the CT-based attenuation map and synthetic attenuation map are highly consistent. The NMAE between the reconstructed SPECT images that were corrected using the synthetic and CT-based attenuation maps was 0.26% ± 0.15%, whereas the localized absolute percentage error was 1.33% ± 3.80% in the left ventricle (LV) myocardium and 1.07% ± 2.58% in the LV blood pool. Conclusion We developed a deep convolutional neural network to estimate attenuation maps for SPECT directly from the emission data. The proposed method is capable of generating highly reliable attenuation maps to facilitate attenuation correction for SPECT-only scanners for myocardial perfusion imaging.

[1]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[2]  N. Patchett.  Does Improved Technology in SPECT Myocardial Perfusion Imaging Reduce Downstream Costs? An Observational Study , 2017 .

[3]  Chi Liu,et al.  Recent advances in cardiac SPECT instrumentation and imaging methods , 2019, Physics in medicine and biology.

[4]  Jae Sung Lee,et al.  Generation of PET Attenuation Map for Whole-Body Time-of-Flight 18F-FDG PET/MRI Using a Deep Neural Network Trained with Simultaneously Reconstructed Activity and Attenuation Maps , 2019, The Journal of Nuclear Medicine.

[5]  J. Ottervanger,et al.  Value of attenuation correction in stress-only myocardial perfusion imaging using CZT-SPECT , 2016, Journal of Nuclear Cardiology.

[6]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  M A King,et al.  Estimation of attenuation maps from scatter and photopeak window single photon-emission computed tomographic images of technetium 99m-labeled sestamibi , 1997, Journal of nuclear cardiology : official publication of the American Society of Nuclear Cardiology.

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

[9]  Brian F. Hutton,et al.  Attenuation correction for lung SPECT: evidence of need and validation of an attenuation map derived from the emission data , 2009, European Journal of Nuclear Medicine and Molecular Imaging.

[10]  Habib Zaidi,et al.  Determination of the attenuation map in emission tomography. , 2003, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[11]  A. Bitarafan-Rajabi,et al.  Radiation dose in cardiac SPECT/CT: An estimation of SSDE and effective dose. , 2016, European journal of radiology.

[12]  H. Malcolm Hudson,et al.  Accelerated image reconstruction using ordered subsets of projection data , 1994, IEEE Trans. Medical Imaging.

[13]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[14]  Xiao Han,et al.  MR‐based synthetic CT generation using a deep convolutional neural network method , 2017, Medical physics.

[15]  Simon Arridge,et al.  Use of measured scatter data for the attenuation correction of single photon emission tomography without transmission scanning. , 2013, Medical physics.

[16]  Michael A. King,et al.  Segmentation of the body and lungs from Compton scatter and photopeak window data in SPECT: a Monte-Carlo investigation , 1996, IEEE Trans. Medical Imaging.

[17]  Gengsheng L. Zeng,et al.  Attenuation map estimation with SPECT emission data only , 2009 .

[18]  Dana I. Casetti-Dinescu,et al.  Generalizable Multi-Site Training and Testing Of Deep Neural Networks Using Image Normalization , 2019, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[19]  Luyao Shi,et al.  Generating Attenuation Map for SPECT-only systems using Generative Adversarial Networks , 2019 .

[20]  Dinggang Shen,et al.  Medical Image Synthesis with Deep Convolutional Adversarial Networks , 2018, IEEE Transactions on Biomedical Engineering.

[21]  James E. Bowsher,et al.  An EM algorithm for estimating SPECT emission and transmission parameters from emission data only , 2001, IEEE Transactions on Medical Imaging.

[22]  Luyao Shi,et al.  A Novel Loss Function Incorporating Imaging Acquisition Physics for PET Attenuation Map Generation using Deep Learning , 2019, MICCAI.

[23]  P. Gantet,et al.  Attenuation correction using SPECT emission data only , 2001 .

[24]  Patrick Dupont,et al.  Simultaneous maximum a posteriori reconstruction of attenuation and activity distributions from emission sinograms , 1999, IEEE Transactions on Medical Imaging.

[25]  Abhinav K. Jha,et al.  Fisher information analysis of list-mode SPECT emission data for joint estimation of activity and attenuation distribution , 2018, Inverse problems.

[26]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[27]  M. Shimizu,et al.  Cardiac function changes with switching from the supine to prone position: Analysis by quantitative semiconductor gated single-photon emission computed tomography , 2015, Journal of Nuclear Cardiology.