Volume 25, Issue 2 (7-2022)
jha 2022, 25(2): 139-155 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Langarizadeh M, Jahanshahi M, khatibi T. Myocardial fibrosis delineation in Late Gadolinium Enhancement images of Hypertrophic Cardiomyopathy patients using Deep Learning methods. jha 2022; 25 (2) :139-155
URL: http://jha.iums.ac.ir/article-1-4091-en.html
URL: http://jha.iums.ac.ir/article-1-4091-en.html
1- Associate Professor, School of Health Management and Information Sciences, Iran University of Medical Sciences, Tehran
2- M.Sc. Student, School of Health Management and Information Sciences, Iran University of Medical Sciences, Tehran ,jahanshahi.m@iums.ac.ir
3- Associate Professor, School of Industrial and Systems Engineering, Tarbiat Modares University, Tehran, Iran
2- M.Sc. Student, School of Health Management and Information Sciences, Iran University of Medical Sciences, Tehran ,
3- Associate Professor, School of Industrial and Systems Engineering, Tarbiat Modares University, Tehran, Iran
Abstract: (2167 Views)
Introduction: Accurate delineation of myocardial fibrosis in Late Gadolinium Enhancement Cardiac Magnetic Resonance (LGE-CMR) has a crucial role in the assessment and risk stratification of HCM patients. As this is time-consuming and requires expertise, automation can be essential in accelerating this process. This study aims to use Unet-based deep learning methods to automate the mentioned process.
Methods: This study used three consecutive Unet-based networks for Region of Interest (ROI) detection, myocardial segmentation, and fibrosis delineation. The study was conducted on LGE images of 41 images diagnosed with HCM, which were contoured by two experts.
Results: This model reported a Dice similarity coefficient and accuracy of 89.74 and 98.22 in myocardial segmentation and 88.42 and 94.66 in fibrosis delineation, respectively, and could outperform the previous methods
Conclusion: The results confirm that using deep learning methods for delineating myocardial fibrosis not only can automate the process, but also helps improve the results and decrease the required time.
Methods: This study used three consecutive Unet-based networks for Region of Interest (ROI) detection, myocardial segmentation, and fibrosis delineation. The study was conducted on LGE images of 41 images diagnosed with HCM, which were contoured by two experts.
Results: This model reported a Dice similarity coefficient and accuracy of 89.74 and 98.22 in myocardial segmentation and 88.42 and 94.66 in fibrosis delineation, respectively, and could outperform the previous methods
Conclusion: The results confirm that using deep learning methods for delineating myocardial fibrosis not only can automate the process, but also helps improve the results and decrease the required time.
Type of Study: Research |
Subject:
Health Information Management
Received: 2022/03/11 | Accepted: 2022/06/20 | Published: 2022/12/21
Received: 2022/03/11 | Accepted: 2022/06/20 | Published: 2022/12/21
References
1. Liew AC, Vassiliou VS, Cooper R, Raphael CE. Hypertrophic cardiomyopathy-past, present and future. J Clin Med. 2017;6(12):1-20. [DOI:10.3390/jcm6120118]
2. Quarta G, Grasso A, Pasquale F, Flett AS, Sado DM, Bonini E, et al. Evolution and clinical importance of fibrosis in HCM. JACC Cardiovasc Imaging. 2011;4(11):1221-3. [DOI:10.1016/j.jcmg.2011.04.023]
3. Pagourelias ED, Alexandridis GM, Vassilikos VP. Fibrosis in hypertrophic cardiomyopathy: Role of novel echo techniques and multi-modality imaging assessment. Heart Fail Rev. 2021;26(6):1297-310. [DOI:10.1007/s10741-020-10058-6]
4. Mewton N, Liu CY, Croisille P, Bluemke D, Lima JAC. Assessment of myocardial fibrosis with cardiovascular magnetic resonance. J Am Coll Cardiol. 2011;57(8):891-903. [DOI:10.1016/j.jacc.2010.11.013]
5. Mrsic Z, Mousavi N, Hulten E, Bittencourt MS. The prognostic value of late gadolinium enhancement in nonischemic heart disease. Magn Reson Imaging Clin N Am. 2019;27(3):545-61. [DOI:10.1016/j.mric.2019.04.010]
6. Weng Z, Yao J, Chan RH, He J, Yang X, Zhou Y, et al. Prognostic value of LGE-CMR in HCM: A meta-analysis. JACC Cardiovasc Imaging. 2016;9(12):1392-402. [DOI:10.1016/j.jcmg.2016.02.031]
7. Freitas P, Ferreira AM, Arteaga-Fernández E, De Oliveira Antunes M, Mesquita J, Abecasis J, et al. The amount of late gadolinium enhancement outperforms current guideline-recommended criteria in the identification of patients with hypertrophic cardiomyopathy at risk of sudden cardiac death. J Cardiovasc Magn Reson. 2019;21(1):1-10. [DOI:10.1186/s12968-019-0561-4]
8. Greulich S, Seitz A, Herter D, Gunther F, Probst S, Bekeredjian R, et al. Long-term risk of sudden cardiac death in hypertrophic cardiomyopathy: A cardiac magnetic resonance outcome study. Eur Heart J Cardiovasc Imaging. 2021;22(7):732-41. [DOI:10.1093/ehjci/jeaa423]
9. Karami M, Fatehi M, Torabi M, Langarizadeh M, Rahimi A, Safdari R. Enhance hospital performance from intellectual capital to business intelligence. Radiol Manage. 2013; 35(6):30-5
10. Farahzadi HR, Langarizadeh M, Mirhosseini M, Fatemi Aghda A. An improved cluster formation process in wireless sensor network to decrease energy consumption. Wireless Network .2021;22(2):1077-87. [DOI:10.1007/s11276-020-02485-y]
11. Langarizadeh M, Orooji A, Sheikhtaheri A. Effectiveness of anonymization methods in preserving patients' privacy: A systematic literature review. Studies in Health Technology and Informatics. 2018; 248: 80-87.
12. Safdari R, Arpanahi HK, Langarizadeh M, Ghazisaeidi M, Dargahi H, zendehdel K. Design a fuzzy rule-based expert system to aid earlier diagnosis of gastric cancer. Acta Inform Med. 2018;26(1):19-23. [DOI:10.5455/aim.2018.26.19-23]
13. Samad-Soltani T, Ghanei M, Langarizadeh M. Development of a fuzzy decision support system to determine the severity of obestructive pulmonary in chemical injured victims. Acta Inform Med. 2015;23(3):138-41. [DOI:10.5455/aim.2015.23.138-141]
14. Tahmasebian Sh, Ghazisaeidi M, Langarizadeh M, Mokhtaran M, Mahdavi-Mazdeh M, Javadian P. Applying data mining techniques to detemine important parameters in chronic kidney disease and the relations of these parameters to each other. J Renal Inj Prev. 2017;6(2):83-7. [DOI:10.15171/jrip.2017.16]
15. Neizel M, Katoh M, Schade E, Rassaf T, Krombach GA, Kelm M, et al. Rapid and accurate determination of relative infarct size in humans using contrast-enhanced magnetic resonance imaging. Clin Res Cardiol. 2009;98(5):319-24. [DOI:10.1007/s00392-009-0007-3]
16. Kolipaka A, Chatzimavroudis GP, White RD, O'Donnell TP, Setser RM. Segmentation of non-viable myocardium in delayed enhancement magnetic resonance images. Int J Cardiovasc Imaging. 2005;21(2-3):303-11. [DOI:10.1007/s10554-004-5806-z]
17. Alba X, Figueras I Ventura RM, Lekadir K, Frangi AF. Healthy and scar myocardial tissue classification in DE-MRI. In: Camara O, Mansi T, Pop M, Rhode K, Sermesant M, Young A, editors. Proceedings of the Third International Workshop, STACOM 2012, Held in Conjunction with MICCAI 2012; 2012 Oct 5; Nice, France. Berlin, Germany: Springer; 2013. p. 62-70.
18. Lu Y, Connelly KA, Yang Y, Joshi SB, Wright G, Radau PE. Semi-automated analysis of infarct heterogeneity on DE-MRI using graph cuts. J Cardiovasc Magn Reson. 2012;14(1):1-3. [DOI:10.1186/1532-429X-14-S1-T6]
19. Ukwatta E, Arevalo H, Li K, Yuan J, Qiu W, Malamas P, et al. Myocardial infarct segmentation from magnetic resonance images for personalized modeling of cardiac electrophysiology. IEEE Trans Med Imaging. 2016;35(6):1408-19. [DOI:10.1109/TMI.2015.2512711]
20. Ukwatta E, Yuan J, Qiu W, Wu KC, Trayanova N, Vadakkumpadan F. Myocardial infarct segmentation and reconstruction from 2D late-gadolinium enhanced magnetic resonance images. Med Image Comput Comput Assist Interv. 2014;17(02):554-61. [DOI:10.1007/978-3-319-10470-6_69]
21. Usta F, Gueaieb W, White JA, Ukwatta E. 3D scar segmentation from LGE-MRI using a continuous max-flow method. Proceedings of the Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging; 2018 Feb 10-15; Houston, Texas, United States. Spie Medical Imaging; 2018. [DOI:10.1117/12.2294406]
22. Rajchl M, Yuan J, White JA, Ukwatta E, Stirrat J, Nambakhsh CMS, et al. Interactive hierarchical-flow segmentation of scar tissue from late-enhancement cardiac MR images. IEEE Trans Med Imaging. 2014;33(1):159-72. [DOI:10.1109/TMI.2013.2282932]
23. Zhu X, Vondrick C, Fowlkes CC, Ramanan D. Do we need more training data? Int J Comput Vis. 2016;119(1):76-92. [DOI:10.1007/s11263-015-0812-2]
24. Spiewak M, Malek LA, Misko J, Chojnowska L, Milosz B, Klopotowski M, et al. Comparison of different quantification methods of late gadolinium enhancement in patients with hypertrophic cardiomyopathy. Eur J Radiol. 2010;74(3):1-5. [DOI:10.1016/j.ejrad.2009.05.035]
25. Zhang L, Huttin O, Marie P-Y, Felblinger J, Beaumont M, DE Chillou C, et al. Myocardial infarct sizing by late gadolinium-enhanced MRI: Comparison of manual, full-width at half-maximum, and n-standard deviation methods. J Magn Reson Imaging. 2016;44(5):1206-17. [DOI:10.1002/jmri.25285]
26. Kurzendorfer T, Breininger K, Steidl S, Brost A, Forman C, Maier A. Myocardial scar segmentation in LGE-MRI using fractal analysis and random forest classification. Proceedings of the 24th International Conference on Pattern Recognition (ICPR); 2018 Aug 20-24; Beijing, China. IEEE; 2018. p. 3168-73. [DOI:10.1109/ICPR.2018.8545636]
27. Larroza A, Materka A, Lopez-Lereu MP, Monmeneu JV, Bodi V, Moratal D. Differentiation between acute and chronic myocardial infarction by means of texture analysis of late gadolinium enhancement and cine cardiac magnetic resonance imaging. Eur J Radiol. 2017;92:78-83. [DOI:10.1016/j.ejrad.2017.04.024]
28. Karim R, Bhagirath P, Claus P, James Housden R, Chen Z, Karimaghaloo Z, et al. Evaluation of state-of-the-art segmentation algorithms for left ventricle infarct from late Gadolinium enhancement MR images. Med Image Anal. 2016;30:95-107. [DOI:10.1016/j.media.2016.01.004]
29. Zabihollahy F, White JA, Ukwatta E. Convolutional neural network-based approach for segmentation of left ventricle myocardial scar from 3D late gadolinium enhancement MR images. Med Phys. 2019;46(4):1740-51. [DOI:10.1002/mp.13436]
30. Zabihollahy F, White JA, Ukwatta E. Myocardial scar segmentation from magnetic resonance images using convolutional neural network. Proceedings of the Medical Imaging 2018: Computer-Aided Diagnosis; 2018 Feb 10-15; Houston, Texas, United States. Spie Medical Imaging; 2018. [DOI:10.1117/12.2293518]
31. Moccia S, Banali R, Martini C, Muscogiuri G, Pontone G, Pepi M, et al. Development and testing of a deep learning-based strategy for scar segmentation on CMR-LGE images. MAGMA. 2019;32(2):187-95. [DOI:10.1007/s10334-018-0718-4]
32. Moccia S, Banali R, Martini C, Moscogiuri G, Pontone G, Pepi M, et al. Automated scar segmentation from CMR-LGE images using a deep learning approach. Proceedings of the Computing in Cardiology Conference (CinC); 2018 Sep 23-26; Maastricht, Netherlands. IEEE; 2019. p. 1-4.
33. Zabihollahy F, Rajchl M, White JA, Ukwatta E. Fully automated segmentation of left ventricular scar from 3D late gadolinium enhancement magnetic resonance imaging using a cascaded multi-planar U-Net (CMPU-Net). Med Phys. 2020;47(4):1645-55. [DOI:10.1002/mp.14022]
34. Fahmy AS, Rausch J, Neisius U, Chan RH, Maron MS, Appelbaum E, et al. Automated cardiac MR scar quantification in hypertrophic cardiomyopathy using deep convolutional neural networks. JACC Cardiovasc Imaging. 2018;11(12):1917-8. [DOI:10.1016/j.jcmg.2018.04.030]
35. Popescu DM, Abramson HG, Yu R, Lai C, Shade JK, Wu KC, et al. Anatomically informed deep learning on contrast-enhanced cardiac magnetic resonance imaging for scar segmentation and clinical feature extraction. Cardiovasc Digit Health J. 2022;3(1):2-13. [DOI:10.1016/j.cvdhj.2021.11.007]
36. Brahim K, Qayyum A, Lalande A, Boucher A, Sakly A, Meriaudeau F. A 3D network based shape prior for automatic myocardial disease segmentation in delayed-enhancement MRI. IRBM. 2021;42(6):424-34. [DOI:10.1016/j.irbm.2021.02.005]
37. Brahim K, Qayyum A, Lalande A, Boucher A, Sakly A, Meriaudeau F. A deep learning approach for the segmentation of myocardial diseases. Proceedings of the 25th International Conference on Pattern Recognition (ICPR); 2021 Jan 10-15; Milan, Italy. IEEE; 2021. p. 4544-51. [DOI:10.1109/ICPR48806.2021.9412793]
38. Brahim K, Qayyum A, Lalande A, Boucher A, Sakly A, Meriaudeau F. A 3D deep learning approach based on Shape Prior for automatic segmentation of myocardial diseases. Proceedings of the Tenth International Conference on Image Processing Theory, Tools and Applications (IPTA); 2020 Nov 9-12; Paris, France. IEEE;2020. p. 1-6. [DOI:10.1109/IPTA50016.2020.9286640]
39. Heidenreich JF, Gassenmaier T, Ankenbrand MJ, Bley TA, Wech T. Self-configuring nnU-net pipeline enables fully automatic infarct segmentation in late enhancement MRI after myocardial infarction. Eur J Radiol. 2021;141:1-5. [DOI:10.1016/j.ejrad.2021.109817]
40. Wang SH, McCann G, Tyukin I. Myocardial infarction detection and quantification based on a convolution neural network with online error correction capabilities. Proceedings of the International Joint Conference on Neural Networks (IJCNN); 2020 Jul 19-24; Glasgow, UK. IEEE; 2020. p. 1-8. [DOI:10.1109/IJCNN48605.2020.9207090]
41. De la Rosa E, Sidibe D, Decourselle T, Leclercq T, Cochet A, Lalande A. Myocardial infarction quantification from late Gadolinium enhancement MRI using top-hat transforms and neural networks. Algorithms. 2021;14(8):1-18. [DOI:10.3390/a14080249]
42. Fahmy AS, Rowin EJ, Chan RH, Manning WJ, Maron MS, Nezafat R. Improved quantification of myocardium scar in late Gadolinium enhancement images: Deep learning based image fusion approach. J Magn Reson Imaging. 2021;54(1):303-12. [DOI:10.1002/jmri.27555]
43. Lau F, Hendriks T, Lieman-Sifry J, Norman B, Sall S, Golden D. Scargan: Chained generative adversarial networks to simulate pathological tissue on cardiovascular MR scans. In: Stoyanov D, Taylor Z, Carneiro G, Syeda-Mahmood T, Martel A, Maier-Hein L, et al, editors. Proceedings of the 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018; 2018 Sep 20; Granada, Spain. Switzerland: Springer, Cham; 2018. p. 343-50. [DOI:10.1007/978-3-030-00889-5_39]
44. Fahmy AS, Neisius U, Chan RH, Rowin EJ, Manning WJ, Maron MS, et al. Three-dimensional deep convolutional neural networks for automated myocardial scar quantification in hypertrophic cardiomyopathy: A multicenter multivendor study. Radiology. 2020;294(1):52-60. [DOI:10.1148/radiol.2019190737]
45. Mantilla J, Paredes JL, Bellanger JJ, Betancur J, Schnell F, Leclercq C, et al. Detection of fibrosis in late gadolinium enhancement cardiac MRI using kernel dictionary learning-based clustering. Proceedings of the Computing in Cardiology Conference (CinC); 2015 Sep 6-9; Nice, France. IEEE; 2015. p. 357-60. [DOI:10.1109/CIC.2015.7408660]
46. Merino-Caviedes S, Cordero-Grande L, Perez Rodriguez MT, Sevilla-Ruiz MT, Revilla-Orodea A, Martin-Fernandez M, et al. A variational method for scar segmentation with myocardial contour correction in DE-CMR images. Proceedings of the IEEE 13th International Symposium on Biomedical Imaging (ISBI); 2016 Apr 13-16; Prague, Czech Republic. IEEE ;2016. p. 956-9. [DOI:10.1109/ISBI.2016.7493423]
47. Wang S, Singh VK, Cheah E, Wang X, Li Q, Chou SH, et al. Stacked dilated convolutions and asymmetric architecture for U-Net-based medical image segmentation. Comput Biol Med. 2022;148. [DOI:10.1016/j.compbiomed.2022.105891]
48. Heiberg E, Sjogren J, Ugander M, Carlsson M, Engblom H, Arheden H. Design and validation of segment-freely available software for cardiovascular image analysis. BMC Med Imaging. 2010;10(1):1-13. [DOI:10.1186/1471-2342-10-1]
49. Morisi R, Donini B, Lanconelli N, Rosengarden J, Morgan J, Harden S, et al. Semi-automated scar detection in delayed enhanced cardiac magnetic resonance images. Int J Mod Phys C. 2015;26(01):1-17. [DOI:10.1142/S0129183115500114]
50. Larroza A, Lopez-Lereu MP, Monmeneu JV, Gavara J, Chorro FJ, Bodi V, et al. Texture analysis of cardiac cine magnetic resonance imaging to detect nonviable segments in patients with chronic myocardial infarction. Med Phys. 2018;45(4):1471-80. [DOI:10.1002/mp.12783]
51. Carminati MC, Boniotti C, Pepi M, Caiani EG. Quantification of myocardial viability in late Gadolinium enhancement cardiac MRI. Proceedings of the Computing in Cardiology Conference (CinC); 2015 Sep 6-9; Nice, France. IEEE; 2016. p. 97-100. [DOI:10.1109/CIC.2015.7408595]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
Site Keywords
Health, Administration, Scientific Article, Iran University of Medical Sciences,
