Myocardial Iron Overload Assessment with Automatic Segmentation of Cardiac MR Images based on Deep Neural Networks

Document Type : Original Paper

Authors

1 Department of Medical Informatics, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran

2 Institute of Bioinformatics, University Medicine Greifswald, Greifswald, Germany.

3 Department of Radiology, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran

10.22038/ijmp.2024.77319.2362

Abstract

Introduction: Heart failure due to myocardial iron overload is one of the main causes of death in thalassemia major (TM) patients. Therefore, cardiac magnetic resonance (CMR) imaging method with a multi-echo sequence can be used to assess the iron overload of TM patients. This study aimed to evaluate the myocardial iron overload in TM patients with automatic left ventricular (LV) segmentation of CMR images.
Material and Methods: Thirty-six TM patients were selected to acquire CMR images and clinical data. Automatic LV segmentation was implemented with U-Net, an automatically adapted deep convolutional neural network based on U-Net. With the signal intensity of the LV segmented area, T2* value can be calculated at different echo times, a widely used and approved method to assess myocardial iron overload. Results: The accuracy of LV segmentation as measured by intersection-over-union (0.95) was substantially higher than non-deep learning based methods and at par with other deep learning based methods like. In addition, our results indicate that the proposed method outperformed in assessing LV iron overload over other deep learning based methods in terms of negative predictive value, positive predictive value, and Jaccard.
Conclusion: Relying on these outcomes, the proposed method as a deep learning based model yields better LV segmentation and notably impacts assessing myocardial iron overload.

Keywords

Main Subjects

References

  1. Franke GN, Kubasch AS, Cross M, Vucinic V, Platzbecker U. Iron overload and its impact on outcome of patients with hematological diseases. Mol Aspects Med. 2020;75:100868. DOI: 10.1016/j.mam.2020.100868.
  2. Fernandes JL. MRI for Iron overload in thalassemia. Hematol Oncol Clin North Am. 2018;32(2):277-95. DOI: 10.1016/j.hoc.2017.11.012.
  3. Sarikouch S, Koerperich H, Boethig D, Peters B, Lots J, Gutberlet M, et al. Reference values for atrial size and function in children and young adults by cardiac MR: a study of the German competence network congenital heart defects. J Magn Reson Imaging. 2011;33(5):1028-39. DOI: 10.1002/jmri.22521.
  4. Wood JC, Enriquez C, Ghugre N, Otto-duessel M, Aguilar M, Nelson MD, et al. Physiology and pathophysiology of iron cardiomyopathy in thalassemia. Ann N Y Acad Sci. 2005;1054:386-95. DOI: 10.1196/annals.1345.047.
  5. Vogel M, Anderson LJ, Holden S, Deanfield JE, Pennell DJ, Walker JM. Tissue doppler echocardiography in patients with thalassaemia detects early myocardial dysfunction related to myocardial iron overload. Eur Heart J. 2003;24(1):113-9. DOI: 10.1016/s0195-668x(02)00381-0.
  6. Zareiamand H, Darroudi A, Mohammadi I, Moravvej SV, Danaei S, Alizadehsani R. Cardiac Magnetic Resonance Imaging (CMRI) Applications in Patients with Chest Pain in the Emergency Department: A Narrative Review. Diagnostics (Basel). 2023;13(16):2667. DOI: 10.3390/diagnostics13162667.
  7. Fragasso A, Ciancio A, Mannarella C, Gaudiano C, Scarciolla O, Ottonello C, et al. Myocardial iron overload assessed by magnetic resonance imaging (MRI) T2* in multi-transfused patients with thalassemia and acquired anemias. Eur J Intern Med. 2011;22(1):62-5. DOI: 10.1016/j.ejim.2010.10.005.
  8. Meloni A, Restaino G, Borsellino Z, Caruso V, Spasiano A, Zuccarelli A, et al. Different patterns of myocardial iron distribution by whole-heart T2* magnetic resonance as risk markers for heart complications in thalassemia major. Int J Cardiol. 2014;177(3):1009-12. DOI: 10.1016/j.ijcard.2014.09.139.
  9. Luo Y, Ko JK, Guan Y, Li L, Qin J, Ha PA, et al. Myocardial iron loading assessment by automatic left ventricle segmentation with morphological operations and geodesic active contour on T2* images. Sci Rep. 2015;5:12438. DOI: 10.1038/srep12438.
  10. Wantanajittikul K, Theera-Umpon N, Saekho S, Auephanwiriankul S, Phrommintikul A, Leemasawat K. Automatic cardiac T2* relaxation time estimation from magnetic resonance images using region growing method with automatically initialized seed points. Comput Methods Programs Biomed. 2016;130:76-86. DOI: 10.1016/j.cmpb.2016.03.015.
  11. Petitjean C, Dacher JN. A review of segmentation methods in short axis cardiac MR images. Med Image Anal. 2011;15(2):169-84. DOI: 10.1016/j.media.2010.12.004.
  12. Chen C, Qin C, Qiu H, Tarroni G, Duan J, Bai W, et al. Deep Learning for Cardiac Image Segmentation: A Review. Front Cardiovasc Med. 2020;7:25. DOI: 10.3389/fcvm.2020.00025.
  13. Hu H, Pan N, Liu H, Liu L, Yin T, Tu Z, et al. Automatic segmentation of left and right ventricles in cardiac MRI using 3D-ASM and deep learning. Signal Process Image Commun. 2021;96:116303. DOI: 10.1016/j.image.2021.116303.
  14. Xie L, Song Y, Chen Q. Automatic left ventricle segmentation in short-axis MRI using deep convolutional neural networks and central-line guided level set approach. Comput Biol Med. 2020;122:103877. DOI: 10.1016/j.compbiomed.2020.103877.
  15. Vigneault DM, Xie W, Ho CY, Bluemke DA, Noble JA. Ω-Net (Omega-Net): Fully automatic, multi-view cardiac MR detection, orientation, and segmentation with deep neural networks. Med Image Anal. 2018;48:95-106. DOI: 10.1016/j.media.2018.05.008.
  16. Abdeltawab H, Khalifa F, Taher F, Alghamdi NS, Ghazal M, Beache G, et al. A deep learning-based approach for automatic segmentation and quantification of the left ventricle from cardiac cine MR images. Comput Med Imaging Graph. 2020;81:101717. DOI: 10.1016/j.compmedimag.2020.101717.
  17. Avendi MR, Kheradvar A, Jafarkhani H. A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI. Med Image Anal. 2016;30:108-19. DOI: 10.1016/j.media.2016.01.005.
  18. Martini N, Meloni A, Positano V, et al. Fully Automated Regional Analysis of Myocardial T2* Values for Iron Quantification Using Deep Learning. Electronics. 2022;11:2749. DOI: 10.3390/electronics11172749.
  19. Shiae Ali E, Bakhshali MA, Shoja Razavi SJ, Poorzand H, Layegh P. Cardiac MR images of thalassemia major patients with myocardial iron overload: a data note. BMC Res Notes. 2021;14:318. DOI: 10.1186/s13104-021-05733-2.
  20. Nazarpoor M. Non-uniformity of Clinical Head, Head and Neck, and Body Coils in Magnetic Resonance Imaging (MRI). Iran J Med Phys. 2014;11(4):322-7.
  21. Lotfi Marangaloo S, Ariamanesh AS, Aminzadeh B, Abedi H, Abbaszadeh A, Montazerabadi A. Comparison of Three-Dimensional Double-Echo Steady-State Sequence with Routine Two-Dimensional Sequence in the Depiction of Knee Cartilage. Iran J Med Phys. 2020;17(2):75-80.
  22. Anderson LJ, Holden S, Davis B, Prescott E, Charrier CC, Bunce NH, et al. Cardiovascular T2-star (T2*) magnetic resonance for the early diagnosis of myocardial iron overload. Eur Heart J. 2001;22(23):2171-9. DOI: 10.1053/euhj.2001.2822.
  23. Zhu YM. Volume image registration by cross-entropy optimization. IEEE Trans Med Imaging. 2002;21(2):174-80. DOI: 10.1109/42.993135.
  24. Li Q, Li L, Wang W, Li Q, Zhong J. A comprehensive exploration of semantic relation extraction via pre-trained CNNs. Knowl Based Syst. 2020;194:105488. DOI: 10.1016/j.knosys.2020.105488.
  25. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab N, Hornegger J, Wells W, Frangi A, editors. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Cham: Springer; 2015. p. 234– DOI: 10.1007/978-3-319-24574-4_28.

 

 

 

Iranian Journal of Medical Physics
Volume 22, Issue 1
January and February 2025
Pages 6-13

Files

History

  • Receive Date: 06 January 2024
  • Revise Date: 08 March 2024
  • Accept Date: 16 March 2024

Share

How to cite

Statistics