Skip to main content
SpringerLink
Log in

Automatic reorientation by deep learning to generate short-axis SPECT myocardial perfusion images

Journal of Nuclear Cardiology (2023)Cite this article

Abstract

Background

Single photon emission computed tomography (SPECT) myocardial perfusion images (MPI) can be displayed both in traditional short-axis (SA) cardiac planes and polar maps for interpretation and quantification. It is essential to reorient the reconstructed transaxial SPECT MPI into standard SA slices. This study is aimed to develop a deep-learning-based approach for automatic reorientation of MPI.

Methods

A total of 254 patients were enrolled, including 226 stress SPECT MPIs and 247 rest SPECT MPIs. Fivefold cross-validation with 180 stress and 201 rest MPIs was used for training and internal validation; the remaining images were used for testing. The rigid transformation parameters (translation and rotation) from manual reorientation were annotated by an experienced nuclear cardiologist and used as the reference standard. A convolutional neural network (CNN) was designed to predict the transformation parameters. Then, the derived transform was applied to the grid generator and sampler in spatial transformer network (STN) to generate the reoriented image. A loss function containing mean absolute errors for translation and mean square errors for rotation was employed. A three-stage optimization strategy was adopted for model optimization: (1) optimize the translation parameters while fixing the rotation parameters; (2) optimize rotation parameters while fixing the translation parameters; (3) optimize both translation and rotation parameters together.

Results

In the test set, the Spearman determination coefficients of the translation distances and rotation angles between the model prediction and the reference standard were 0.993 in X axis, 0.992 in Y axis, 0.994 in Z axis, 0.987 along X axis, 0.990 along Y axis and 0.996 along Z axis, respectively. For the 46 stress MPIs in the test set, the Spearman determination coefficients were 0.858 in percentage of profusion defect (PPD) and 0.858 in summed stress score (SSS); for the 46 rest MPIs in the test set, the Spearman determination coefficients were 0.9 in PPD and 0.9 in summed rest score (SRS).

Conclusions

Our deep learning-based LV reorientation method is able to accurately generate the SA images. Technical validations and subsequent evaluations of measured clinical parameters show that it has great promise for clinical use.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

39,95 €

Price includes VAT (Finland)

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7

Abbreviations

SPECT:

Single photon emission computerized tomography

MPI:

Myocardial perfusion imaging

CNN:

Convolutional neural networks

STN:

Spatial transformer network

LV:

Left ventricular

SA:

Short-axis

ECTb:

Emory Cardiac Toolbox

References

  1. Hage FG, AlJaroudi WA. Review of cardiovascular imaging in the Journal of Nuclear Cardiology in, 2017 Part 2 of 2: Myocardial perfusion imaging. J Nucl Cardiol 2018;25:1390‐9.

    Article  PubMed  Google Scholar 

  2. Kuhle WG, Porenta G, Huang SC, Phelps ME, Schelbert HR. Issues in the quantitation of reoriented cardiac PET images. J Nucl Med 1992;33:1235‐42.

    CAS  PubMed  Google Scholar 

  3. deKemp RA, Nahmias C. Automated determination of the left ventricular long axis in cardiac positron tomography. Physiol Meas 1996;17:95‐108.

    Article  CAS  PubMed  Google Scholar 

  4. Cauvin JC, Boire JY, Maublant JC, Bonny JM, Zanca M, Veyre A. Automatic detection of the left ventricular myocardium long axis and center in thallium-201 single photon emission computed tomography. Eur J Nucl Med 1992;19:1032‐7.

    CAS  PubMed  Google Scholar 

  5. van Hastenberg RP, Kemerink GJ, Hasman A. On the generation of short-axis and radial long-axis slices in thallium-201 myocardial perfusion single-photon emission tomography. Eur J Nucl Med 1996;23:924‐31.

    Article  PubMed  Google Scholar 

  6. Zhou WH, Garcia EV. Nuclear image-guided approaches for cardiac resynchronization therapy (CRT). Curr Cardiol Rep 2016;18:89.

    Article  Google Scholar 

  7. Garcia EV, Van Train K, Maddahi J, Prigent F, Friedman J, Areeda J. Quantification of rotational thallium-201 myocardial tomography. J Nucl Med 1985;26:17‐26.

    CAS  PubMed  Google Scholar 

  8. Lancaster JL, Starling MR, Kopp DT, Lasher JC, Blumhardt R. Effect of errors in reangulation on planar and tomographic thallium-201 washout profile curves. J Nucl Med 1986;26:1445‐55.

    Google Scholar 

  9. Depuey EG, Garcia EV. Optimal specificity of thallium-201 SPECT through recognition of imaging artifacts. J Nucl Med 1989;30:441‐9.

    CAS  PubMed  Google Scholar 

  10. He ZX, Maublant JC, Cauvin JC. Reorientation of the left ventricular long-axis on myocardial transaxial tomograms by a linear fitting method. J Nucl Med Offic Publ Soc Nucl Med 1991;32:1794.

    CAS  Google Scholar 

  11. Mullick R, Ezquerra NF. Automatic determination of LV orientation from SPECT data. IEEE Trans Med Imaging 1995;14:88‐99.

    Article  CAS  PubMed  Google Scholar 

  12. Germano G. Automatic reorientation of three-dimensional, transaxial myocardial perfusion SPECT. J Nucl Med 1995;36:7.

    Google Scholar 

  13. Slomka PJ, Hurwitz GA, Stephenson J, Cradduck T. Automated alignment and sizing of myocardial stress and rest scans to three-dimensional normal templates using an image registration algorithm. J Nucl Med 1995;36:1115‐22.

    CAS  PubMed  Google Scholar 

  14. Jin SK, Na Y, Bae KT. Segmentation of ECG-gated multidetector row-CT cardiac images for functional analysis. Paper presented at: Medical Imaging, 2002.

  15. Klein R, Lortie M, Adler A, Beanlands RS, Dekemp R. Fully Automated Software for Polar-Map Registration and Sampling from PET Images. Paper presented at: IEEE Nuclear Science Symposium Conference Record, 2006.

  16. Zhang D, Pretorius PH, Lin K, Miao W, Zhu W. A novel deep-learning–based approach for automatic reorientation of 3D cardiac SPECT images. Eur J Nucl Med Mol Imaging. 2021.

  17. Su YY, Liu Q, Xie WT, Hu PZ. YOLO-LOGO: A transformer-based YOLO segmentation model for breast mass detection and segmentation in digital mammograms. Comput Methods Programs Biomed 2022;221:15.

    Article  Google Scholar 

  18. Sadak F, Saadat M, Hajiyavand AM. Real-time deep learning-based image recognition for applications in automated positioning and injection of biological cells. Comput Biol Med 2020;125:156.

    Article  Google Scholar 

  19. Vigneault DM, Xie W, Ho CY, Bluemke DA, Noble JA. Omega-net: Fully automatic, multi-view cardiac MR detection, orientation, and segmentation with deep neural networks. 2017.

  20. Klein S, Staring M, Murphy K, Viergever MA, Pluim JPW. Elastix: A toolbox for intensity-based medical image registration. IEEE Trans Med Imaging 2010;29:196‐205.

    Article  PubMed  Google Scholar 

  21. Shamonin DP, Bron EE, Lelieveldt BPF, Smits M, Klein S, Staring M, et al. Fast parallel image registration on CPU and GPU for diagnostic classification of Alzheimer’s disease. Front Neuroinform 2014;7:14.

    Google Scholar 

  22. Jaderberg M, Simonyan K, Zisserman A, Kavukcuoglu K. Spatial Transformer Networks. Paper presented at: MIT Press, 2015

  23. Zhao C, Xu Y, He Z, Tang JS, Zhang YJ, Han JG, et al. Lung segmentation and automatic detection of COVID-19 using radiomic features from chest CT images. Pattern Recognit 2021;119:46.

    Article  Google Scholar 

  24. Zhao C, Keyak JH, Tang J, Kaneko TS, Zhou W. ST-V-Net: incorporating shape prior into convolutional neural networks for proximal femur segmentation. Complex Intelligent Systems. 2021.

  25. Wang TH, Lei Y, Tang HP, He Z, Castillo R, Wang C, et al. A learning-based automatic segmentation and quantification method on left ventricle in gated myocardial perfusion SPECT imaging: A feasibility study. J Nucl Cardiol 2020;27:976‐87.

    Article  PubMed  Google Scholar 

  26. Wen H, Wei Q, Huang J-L, Tsai S-C, Wang C-Y, Chiang K-F, et al. Analysis on SPECT myocardial perfusion imaging with a tool derived from dynamic programming to deep learning. Optik 2021;240:47.

    Article  Google Scholar 

  27. Zhu F, Zhao J, Zhao C, Tang S, Nan J, Li Y, et al. A new method incorporating deep learning with shape priors for left ventricular segmentation in myocardial perfusion SPECT images. ArXiv. 2022;abs/2206.03603.

  28. He Z, Fernandes FdA, do Nascimento EA, Garcia EV, Mesquita CT, Zhou W. Incremental value of left ventricular shape parameters measured by gated SPECT MPI in predicting the super-response to CRT. J Nucl Cardiol. 2021.

  29. He Z, Zhang X, Zhao C, Qian Z, Wang Y, Hou X, et al. A method using deep learning to discover new predictors of CRT response from mechanical dyssynchrony on gated SPECT MPI. 2021.

  30. Zhao C, Vij A, Malhotra S, Tang J, Tang H, Pienta D, et al. Automatic extraction and stenosis evaluation of coronary arteries in invasive coronary angiograms. Comput Biol Med 2021;136:58.

    Article  Google Scholar 

  31. Tang H, Bober RR, Zhao C, Zhang C, Zhou W. 3D fusion between fluoroscopy angiograms and SPECT myocardial perfusion images to guide percutaneous coronary intervention. J Nucl Cardiol. 2021.

  32. Xu Z, Tang H, Malhotra S, Dong M, Zhao C, Ye Z, et al. Three-dimensional fusion of myocardial perfusion SPECT and invasive coronary angiography guides coronary revascularization. J Nucl Cardiol. 2022.

  33. Zhou W, Hou X, Piccinelli M, Tang X, Tang L, Cao K, et al. 3D fusion of LV venous anatomy on fluoroscopy venograms with epicardial surface on SPECT myocardial perfusion images for guiding CRT LV lead placement. JACC-Cardiovascular Imaging 2014;7:1239‐48.

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

This research was supported in part by a Michigan Technological Research Excellence Fund Research Seed grant (PI: Weihua Zhou), a seed grant from Michigan Technological University Health Research Institute (PI: Weihua Zhou), Henan Science and Technology Development Plan 2022 (Project Number: 222102210219), and the National Natural Science Foundation of China under Grant 62106233.

Author information

Authors and Affiliations

  1. School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou, 450000, Henan, China

    Fubao Zhu PhD & Guojie Wang MS

  2. Department of Applied Computing, Michigan Technological University, Houghton, MI, 49931, USA

    Chen Zhao PhD, Zhuo He PhD & Weihua Zhou PhD

  3. Division of Cardiology, Cook County Health and Hospitals System, Chicago, IL, 60612, USA

    Saurabh Malhotra MD

  4. Division of Cardiology, Rush Medical College, Chicago, IL, 60612, USA

    Saurabh Malhotra MD

  5. Department of Nuclear Medicine, Xiangya Hospital, Central South University, Changsha, 410008, China

    Min Zhao MD, PhD

  6. Department of Cardiology, The First Affiliated Hospital of Nanjing Medical University, Guangzhou Road 300, Nanjing, 210029, Jiangsu, China

    Jianzhou Shi MD, PhD & Zhixin Jiang MD, PhD

  7. Center for Biocomputing and Digital Health, Institute of Computing and Cybersystems, and Health Research Institute, Michigan Technological University, 1400 Townsend Drive, Houghton, MI, 49931, USA

    Weihua Zhou PhD

Authors
  1. Fubao Zhu PhD
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Guojie Wang MS
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chen Zhao PhD
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Saurabh Malhotra MD
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Min Zhao MD, PhD
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Zhuo He PhD
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Jianzhou Shi MD, PhD
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Zhixin Jiang MD, PhD
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Weihua Zhou PhD
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Zhixin Jiang MD, PhD or Weihua Zhou PhD.

Ethics declarations

Disclosures

All authors declare that there are no conflicts of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

The authors of this article have provided a PowerPoint file, available for download at SpringerLink, which summarises the contents of the paper and is free for re-use at meetings and presentations. Search for the article DOI on SpringerLink.com.

The authors have also provided an audio summary of the article, which is available to download as ESM, or to listen to via the JNC/ASNC Podcast.

Supplementary Information

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhu, F., Wang, G., Zhao, C. et al. Automatic reorientation by deep learning to generate short-axis SPECT myocardial perfusion images. J. Nucl. Cardiol. (2023). https://doi.org/10.1007/s12350-023-03226-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s12350-023-03226-2

Keywords

  • SPECT MPI
  • reorientation
  • deep learning
  • convolutional neural networks

Search

Navigation