Fully Automated Regional Analysis of Myocardial T2* Values for Iron Quantification Using Deep Learning
Abstract
:1. Introduction
2. Materials and Methods
2.1. Study Population
2.2. Image Acquisition and T2* Map Generation
2.3. Data Preparation and Labeling
2.4. Deep Learning Segmentation
2.5. Network Training
2.6. Evaluation of the Model Performance
2.6.1. Segmentation Accuracy Assessment
2.6.2. Accuracy of T2* Quantification
2.6.3. Assessment of Validity
2.6.4. Inter-Observer Agreement
3. Results
Performance of U-Net
4. Discussion
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Al-Tubaikh, J.A. (Ed.) Hemosiderosis and Hemochromatosis. In Internal Medicine; Springer: Berlin/Heidelberg, Germany, 2010; pp. 290–292. ISBN 978-3-642-03708-5. [Google Scholar]
- Pilo, F.; Cilloni, D.; Della Porta, M.G.; Forni, G.L.; Piperno, A.; Santini, V.; Angelucci, E. Iron-Mediated Tissue Damage in Acquired Ineffective Erythropoiesis Disease: It’s More a Matter of Burden or More of Exposure to Toxic Iron Form? Leuk. Res. 2022, 114, 106792. [Google Scholar] [CrossRef] [PubMed]
- Udani, K.; Chris-Olaiya, A.; Ohadugha, C.; Malik, A.; Sansbury, J.; Paari, D. Cardiovascular Manifestations in Hospitalized Patients with Hemochromatosis in the United States. Int. J. Cardiol. 2021, 342, 117–124. [Google Scholar] [CrossRef] [PubMed]
- Kremastinos, D.T.; Farmakis, D. Iron Overload Cardiomyopathy in Clinical Practice. Circulation 2011, 124, 2253–2263. [Google Scholar] [CrossRef] [PubMed]
- Pennell, D.J.; Udelson, J.E.; Arai, A.E.; Bozkurt, B.; Cohen, A.R.; Galanello, R.; Hoffman, T.M.; Kiernan, M.S.; Lerakis, S.; Piga, A.; et al. Cardiovascular Function and Treatment in β-Thalassemia Major: A Consensus Statement from the American Heart Association. Circulation 2013, 128, 281–308. [Google Scholar] [CrossRef] [PubMed]
- Wood, J.C.; Otto-Duessel, M.; Aguilar, M.; Nick, H.; Nelson, M.D.; Coates, T.D.; Pollack, H.; Moats, R. Cardiac Iron Determines Cardiac T2*, T2, and T1 in the Gerbil Model of Iron Cardiomyopathy. Circulation 2005, 112, 535–543. [Google Scholar] [CrossRef] [PubMed]
- Meloni, A.; Rienhoff, H.Y.; Jones, A.; Pepe, A.; Lombardi, M.; Wood, J.C. Cardiac R2* Values Are Independent of the Image Analysis Approach Employed: Algorithms for Cardiac R2* Assessment. Magn. Reson. Med. 2014, 72, 485–491. [Google Scholar] [CrossRef] [PubMed]
- Westwood, M.; Anderson, L.J.; Firmin, D.N.; Gatehouse, P.D.; Charrier, C.C.; Wonke, B.; Pennell, D.J. A Single Breath-Hold Multiecho T2* Cardiovascular Magnetic Resonance Technique for Diagnosis of Myocardial Iron Overload. J. Magn. Reson. Imaging 2003, 18, 33–39. [Google Scholar] [CrossRef]
- Pepe, A.; Positano, V.; Santarelli, M.F.; Sorrentino, F.; Cracolici, E.; De Marchi, D.; Maggio, A.; Midiri, M.; Landini, L.; Lombardi, M. Multislice Multiecho T2* Cardiovascular Magnetic Resonance for Detection of the Heterogeneous Distribution of Myocardial Iron Overload. J. Magn. Reson. Imaging 2006, 23, 662–668. [Google Scholar] [CrossRef]
- Meloni, A.; Positano, V.; Pepe, A.; Rossi, G.; Dell’Amico, M.; Salvatori, C.; Keilberg, P.; Filosa, A.; Sallustio, G.; Midiri, M.; et al. Preferential Patterns of Myocardial Iron Overload by Multislice Multiecho T*2 CMR in Thalassemia Major Patients. Magn. Reson. Med. 2010, 64, 211–219. [Google Scholar] [CrossRef]
- Cerqueira, M.D.; Weissman, N.J.; Dilsizian, V.; Jacobs, A.K.; Kaul, S.; Laskey, W.K.; Pennell, D.J.; Rumberger, J.A.; Ryan, T.; Verani, M.S.; et al. Standardized Myocardial Segmentation and Nomenclature for Tomographic Imaging of the Heart. A Statement for Healthcare Professionals from the Cardiac Imaging Committee of the Council on Clinical Cardiology of the American Heart Association. Circulation 2002, 105, 539–542. [Google Scholar] [CrossRef] [Green Version]
- Schmidhuber, J. Deep Learning in Neural Networks: An Overview. Neural Netw. 2015, 61, 85–117. [Google Scholar] [CrossRef] [PubMed]
- Litjens, G.; Kooi, T.; Bejnordi, B.E.; Setio, A.A.A.; Ciompi, F.; Ghafoorian, M.; van der Laak, J.A.W.M.; van Ginneken, B.; Sánchez, C.I. A Survey on Deep Learning in Medical Image Analysis. Med. Image Anal. 2017, 42, 60–88. [Google Scholar] [CrossRef] [PubMed]
- Hosny, A.; Parmar, C.; Quackenbush, J.; Schwartz, L.H.; Aerts, H.J.W.L. Artificial Intelligence in Radiology. Nat. Rev. Cancer 2018, 18, 500–510. [Google Scholar] [CrossRef] [PubMed]
- Yamashita, R.; Nishio, M.; Do, R.K.G.; Togashi, K. Convolutional Neural Networks: An Overview and Application in Radiology. Insights Imaging 2018, 9, 611–629. [Google Scholar] [CrossRef] [PubMed]
- Shelhamer, E.; Long, J.; Darrell, T. Fully Convolutional Networks for Semantic Segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 39, 640–651. [Google Scholar] [CrossRef]
- Leiner, T.; Rueckert, D.; Suinesiaputra, A.; Baeßler, B.; Nezafat, R.; Išgum, I.; Young, A.A. Machine Learning in Cardiovascular Magnetic Resonance: Basic Concepts and Applications. J. Cardiovasc. Magn. Reson. Off. J. Soc. Cardiovasc. Magn. Reson. 2019, 21, 61. [Google Scholar] [CrossRef]
- Blansit, K.; Retson, T.; Masutani, E.; Bahrami, N.; Hsiao, A. Deep Learning-Based Prescription of Cardiac MRI Planes. Radiol. Artif. Intell. 2019, 1, e180069. [Google Scholar] [CrossRef]
- Qi, H.; Hajhosseiny, R.; Cruz, G.; Kuestner, T.; Kunze, K.; Neji, R.; Botnar, R.; Prieto, C. End-to-End Deep Learning Nonrigid Motion-Corrected Reconstruction for Highly Accelerated Free-Breathing Coronary MRA. Magn. Reson. Med. 2021, 86, 1983–1996. [Google Scholar] [CrossRef]
- Sandino, C.M.; Lai, P.; Vasanawala, S.S.; Cheng, J.Y. Accelerating Cardiac Cine MRI Using a Deep Learning-Based ESPIRiT Reconstruction. Magn. Reson. Med. 2021, 85, 152–167. [Google Scholar] [CrossRef]
- Bernard, O.; Lalande, A.; Zotti, C.; Cervenansky, F.; Yang, X.; Heng, P.-A.; Cetin, I.; Lekadir, K.; Camara, O.; Gonzalez Ballester, M.A.; et al. Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved? IEEE Trans. Med. Imaging 2018, 37, 2514–2525. [Google Scholar] [CrossRef]
- Martini, N.; Aimo, A.; Barison, A.; Della Latta, D.; Vergaro, G.; Aquaro, G.D.; Ripoli, A.; Emdin, M.; Chiappino, D. Deep Learning to Diagnose Cardiac Amyloidosis from Cardiovascular Magnetic Resonance. J. Cardiovasc. Magn. Reson. Off. J. Soc. Cardiovasc. Magn. Reson. 2020, 22, 84. [Google Scholar] [CrossRef] [PubMed]
- Romaguera, L.V.; Romero, F.P.; Fernandes Costa Filho, C.F.; Fernandes Costa, M.G. Myocardial Segmentation in Cardiac Magnetic Resonance Images Using Fully Convolutional Neural Networks. Biomed. Signal Process. Control 2018, 44, 48–57. [Google Scholar] [CrossRef]
- Fadil, H.; Totman, J.J.; Hausenloy, D.J.; Ho, H.-H.; Joseph, P.; Low, A.F.-H.; Richards, A.M.; Chan, M.Y.; Marchesseau, S. A Deep Learning Pipeline for Automatic Analysis of Multi-Scan Cardiovascular Magnetic Resonance. J. Cardiovasc. Magn. Reson. 2021, 23, 47. [Google Scholar] [CrossRef] [PubMed]
- Bai, W.; Sinclair, M.; Tarroni, G.; Oktay, O.; Rajchl, M.; Vaillant, G.; Lee, A.M.; Aung, N.; Lukaschuk, E.; Sanghvi, M.M.; et al. Automated Cardiovascular Magnetic Resonance Image Analysis with Fully Convolutional Networks. J. Cardiovasc. Magn. Reson. Off. J. Soc. Cardiovasc. Magn. Reson. 2018, 20, 65. [Google Scholar] [CrossRef]
- Ramazzotti, A.; Pepe, A.; Positano, V.; Rossi, G.; De Marchi, D.; Brizi, M.G.; Luciani, A.; Midiri, M.; Sallustio, G.; Valeri, G.; et al. Multicenter Validation of the Magnetic Resonance T2* Technique for Segmental and Global Quantification of Myocardial Iron. J. Magn. Reson. Imaging 2009, 30, 62–68. [Google Scholar] [CrossRef] [PubMed]
- Meloni, A.; Ramazzotti, A.; Positano, V.; Salvatori, C.; Mangione, M.; Marcheschi, P.; Favilli, B.; De Marchi, D.; Prato, S.; Pepe, A.; et al. Evaluation of a Web-Based Network for Reproducible T2* MRI Assessment of Iron Overload in Thalassemia. Int. J. Med. Inf. 2009, 78, 503–512. [Google Scholar] [CrossRef]
- Positano, V.; Pepe, A.; Santarelli, M.F.; Scattini, B.; De Marchi, D.; Ramazzotti, A.; Forni, G.; Borgna-Pignatti, C.; Lai, M.E.; Midiri, M.; et al. Standardized T2* Map of Normal Human Heartin Vivo to Correct T2* Segmental Artefacts. NMR Biomed. 2007, 20, 578–590. [Google Scholar] [CrossRef]
- Positano, V.; Meloni, A.; Santarelli, M.F.; Gerardi, C.; Bitti, P.P.; Cirotto, C.; De Marchi, D.; Salvatori, C.; Landini, L.; Pepe, A. Fast Generation of T2* Maps in the Entire Range of Clinical Interest: Application to Thalassemia Major Patients. Comput. Biol. Med. 2015, 56, 200–210. [Google Scholar] [CrossRef]
- Ronneberger, O.; Fischer, P.; Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation 2015. In Proceedings of the MICCAI 2015: Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015, Munich, Germany, 5–9 October 2015; Springer: Cham, Switzerland, 2015. [Google Scholar]
- Zijdenbos, A.P.; Dawant, B.M.; Margolin, R.A.; Palmer, A.C. Morphometric Analysis of White Matter Lesions in MR Images: Method and Validation. IEEE Trans. Med. Imaging 1994, 13, 716–724. [Google Scholar] [CrossRef]
- Carillo, V.; Cozzarini, C.; Perna, L.; Calandra, M.; Gianolini, S.; Rancati, T.; Spinelli, A.E.; Vavassori, V.; Villa, S.; Valdagni, R.; et al. Contouring Variability of the Penile Bulb on CT Images: Quantitative Assessment Using a Generalized Concordance Index. Int. J. Radiat. Oncol. Biol. Phys. 2012, 84, 841–846. [Google Scholar] [CrossRef]
- Rosner, B. Multisample Inference. In Fundamentals of Biostatistics; Duxbury: Pacific Grove, CA, USA, 2000; pp. 511–576. [Google Scholar]
- Chen, C.; Qin, C.; Qiu, H.; Tarroni, G.; Duan, J.; Bai, W.; Rueckert, D. Deep Learning for Cardiac Image Segmentation: A Review. Front. Cardiovasc. Med. 2020, 7, 25. [Google Scholar] [CrossRef] [PubMed]
- Avendi, M.R.; 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, 108–119. [Google Scholar] [CrossRef] [PubMed]
- Bratt, A.; Kim, J.; Pollie, M.; Beecy, A.N.; Tehrani, N.H.; Codella, N.; Perez-Johnston, R.; Palumbo, M.C.; Alakbarli, J.; Colizza, W.; et al. Machine Learning Derived Segmentation of Phase Velocity Encoded Cardiovascular Magnetic Resonance for Fully Automated Aortic Flow Quantification. J. Cardiovasc. Magn. Reson. Off. J. Soc. Cardiovasc. Magn. Reson. 2019, 21, 1. [Google Scholar] [CrossRef]
- Xue, H.; Davies, R.H.; Brown, L.A.E.; Knott, K.D.; Kotecha, T.; Fontana, M.; Plein, S.; Moon, J.C.; Kellman, P. Automated Inline Analysis of Myocardial Perfusion MRI with Deep Learning. Radiol. Artif. Intell. 2020, 2, e200009. [Google Scholar] [CrossRef]
- Ankenbrand, M.J.; Lohr, D.; Schlötelburg, W.; Reiter, T.; Wech, T.; Schreiber, L.M. Deep Learning-based Cardiac Cine Segmentation: Transfer Learning Application to 7T Ultrahigh-field MRI. Magn. Reson. Med. 2021, 86, 2179–2191. [Google Scholar] [CrossRef] [PubMed]
- Wood, J.C.; Ghugre, N. Magnetic Resonance Imaging Assessment of Excess Iron in Thalassemia, Sickle Cell Disease and Other Iron Overload Diseases. Hemoglobin 2008, 32, 85–96. [Google Scholar] [CrossRef]
- Augusto, J.B.; Davies, R.H.; Bhuva, A.N.; Knott, K.D.; Seraphim, A.; Alfarih, M.; Lau, C.; Hughes, R.K.; Lopes, L.R.; Shiwani, H.; et al. Diagnosis and Risk Stratification in Hypertrophic Cardiomyopathy Using Machine Learning Wall Thickness Measurement: A Comparison with Human Test-Retest Performance. Lancet Digit. Health 2021, 3, e20–e28. [Google Scholar] [CrossRef]
- He, T.; Gatehouse, P.D.; Kirk, P.; Tanner, M.A.; Smith, G.C.; Keegan, J.; Mohiaddin, R.H.; Pennell, D.J.; Firmin, D.N. Black-Blood T2* Technique for Myocardial Iron Measurement in Thalassemia. J. Magn. Reson. Imaging 2007, 25, 1205–1209. [Google Scholar] [CrossRef]
Segment/Myoc/LV | DSC | APD [mm] | HD [mm] | AE [°] |
---|---|---|---|---|
1: basal anterior | 0.795 ± 0.086 | 0.42 ± 0.29 | 3.25 ± 1.60 | 3.44 ± 3.78 |
2: basal anteroseptal | 0.794 ± 0.081 | 0.41 ± 0.26 | 3.68 ± 1.72 | 2.81 ± 3.22 |
3: basal inferoseptal | 0.805 ± 0.084 | 0.37 ± 0.24 | 3.31 ± 1.86 | 2.98 ± 3.17 |
4: basal inferior | 0.807 ± 0.101 | 0.38 ± 0.31 | 3.11 ± 1.34 | 2.36 ± 2.59 |
5: basal inferolateral | 0.767 ± 0.191 | 0.57 ± 0.88 | 3.44 ± 2.28 | 3.90 ± 3.46 |
6: basal anterolateral | 0.741 ± 0.186 | 0.63 ± 0.76 | 3.39 ± 1.93 | 3.27 ± 2.57 |
7: medium anterior | 0.746 ± 0.157 | 0.57 ± 0.52 | 3.87 ± 1.86 | 3.87 ± 4.91 |
8: medium anteroseptal | 0.772 ± 0.096 | 0.44 ± 0.28 | 3.39 ± 1.06 | 3.49 ± 3.19 |
9: medium inferoseptal | 0.787 ± 0.145 | 0.44 ± 0.52 | 3.32 ± 1.45 | 3.31 ± 3.31 |
10: medium inferior | 0.764 ± 0.146 | 0.53 ± 0.53 | 3.58 ± 1.77 | 3.45 ± 4.51 |
11: medium inferolateral | 0.752 ± 0.160 | 0.61 ± 0.70 | 4.04 ± 2.32 | 3.27 ± 4.94 |
12: medium anterolateral | 0.754 ± 0.203 | 0.64 ± 0.93 | 3.76 ± 2.38 | 4.23 ± 5.39 |
13: apical anterior | 0.762 ± 0.129 | 0.54 ± 0.48 | 4.09 ± 2.05 | 5.84 ± 5.65 |
14: apical septal | 0.775 ± 0.096 | 0.47 ± 0.35 | 4.06 ± 1.73 | 5.01 ± 5.78 |
15: apical inferior | 0.762 ± 0.133 | 0.53 ± 0.50 | 4.11 ± 2.11 | 5.56 ± 5.48 |
16: apical lateral | 0.730 ± 0.168 | 0.68 ± 0.68 | 4.43 ± 2.43 | 7.08 ± 6.12 |
Myoc: basal | 0.819 ± 0.087 | 1.94 ± 0.92 | 13.18 ± 4.78 | 3.13 ± 2.27 |
Myoc: mid-ventricular | 0.802 ± 0.095 | 2.11 ± 0.96 | 13.31 ± 5.81 | 3.60 ± 3.77 |
Myoc: apical | 0.802 ± 0.090 | 2.12 ± 1.00 | 13.58 ± 6.51 | 5.87 ± 4.35 |
LV: basal | 0.927 ± 0.032 | 2.44 ± 1.73 | 13.45 ± 8.39 | n.a. |
LV: mid-ventricular | 0.907 ± 0.044 | 3.06 ± 2.01 | 16.32 ± 7.32 | n.a. |
LV: apical | 0.911 ± 0.043 | 2.24 ± 1.29 | 13.23 ± 5.77 | n.a |
Segment | Bland Altman Bias (Limits of Agreement) [ms] | Correlation (R; p-Value) | ICC (95%CI) | CoV (%) |
---|---|---|---|---|
1: basal anterior | −0.97 (−5.15 to 3.1) | R = 0.955; p < 0.0001 | 0.994 (0.983–0.998) | 5.42 |
2: basal anteroseptal | −0.38 (−4.13 to 3.37) | R = 0.977; p < 0.0001 | 0.996 (0.990–0.998) | 4.12 |
3: basal inferoseptal | 0.09 (−3.64 to 3.83) | R = 0.982; p < 0.0001 | 0.996 (0.990–0.998) | 3.97 |
4: basal inferior | 0.10 (−2.63 to 2.83) | R = 0.992; p < 0.0001 | 0.997 (0.993–0.999) | 3.42 |
5: basal inferolateral | 1.11 (−5.63 to 7.85) | R = 0.919; p < 0.0001 | 0.971 (0.928–0.989) | 9.99 |
6: basal anterolateral | −0.09 (−4.05 to 3.86) | R = 0.953; p < 0.0001 | 0.994 (0.985–0.998) | 4.56 |
7: medium anterior | −1.09 (−7.19 to 5.01) | R = 0.962; p < 0.0001 | 0.987 (0.966–0.995) | 8.37 |
8: medium anteroseptal | −0.64 (−4.45 to 3.17) | R = 0.992; p < 0.0001 | 0.995 (0.987–0.998) | 4.67 |
9: medium inferoseptal | −0.97 (−4.28 to 2.35) | R = 0.995; p < 0.0001 | 0.996 (0.986–0.999) | 4.17 |
10: medium inferior | −1.46 (−5.57 to 2.63) | R = 0.988; p < 0.0001 | 0.992 (0.964–0.997) | 6.77 |
11: medium inferolateral | −0.74 (−6.02 to 4.55) | R = 0.961; p < 0.0001 | 0.986 (0.966–0.995) | 7.64 |
12: medium anterolateral | −1.03 (−5.54 to 3.48) | R = 0.979; p < 0.0001 | 0.990 (0.974–0.996) | 6.32 |
13: apical anterior | −0.08 (−5.37 to 5.21) | R = 0.982; p < 0.0001 | 0.992 (0.979–0.997) | 6.71 |
14: apical septal | −0.41 (−3.68 to 2.86) | R = 0.991; p < 0.0001 | 0.997 (0.993–0.999) | 3.87 |
15: apical inferior | −0.09 (−5.26 to 5.07) | R = 0.991; p < 0.0001 | 0.993 (0.982–0.997) | 6.61 |
16: apical lateral | 0.92 (−4.65 to 6.49) | R = 0.961; p < 0.0001 | 0.988 (0.969–0.995) | 6.93 |
Global | −0.36 (−2.14 to 1.42) | R = 0.992; p < 0.0001 | 0.998 (0.996–0.999) | 0.233 |
Sensitivity (%) | Specificity (%) | Positive Predictive Value (%) | Negative Predictive Value (%) | Accuracy (%) | |
---|---|---|---|---|---|
1: basal anterior | 100 | 100 | 100 | 100 | 100 |
2: basal anteroseptal | 100 | 100 | 100 | 100 | 100 |
3: basal inferoseptal | 100 | 100 | 100 | 100 | 100 |
4: basal inferior | 80.00 | 100 | 100 | 93.75 | 95.00 |
5: basal inferolateral | 85.71 | 100 | 100 | 92.86 | 95.00 |
6: basal anterolateral | 100 | 100 | 100 | 100 | 100 |
7: medium anterior | 75.00 | 100 | 100 | 85.71 | 90.00 |
8: medium anteroseptal | 66.67 | 100 | 100 | 87.50 | 90.00 |
9: medium inferoseptal | 100 | 100 | 100 | 100 | 100 |
10: medium inferior | 71.43 | 100 | 100 | 86.67 | 90.00 |
11: medium inferolateral | 85.71 | 92.31 | 85.71 | 92.31 | 90.00 |
12: medium anterolateral | 83.33 | 100 | 100 | 93.33 | 95.00 |
13: apical anterior | 85.71 | 100 | 100 | 92.86 | 95.00 |
14: apical septal | 80.00 | 100 | 100 | 93.75 | 95.00 |
15: apical inferior | 85.71 | 100 | 100 | 92.86 | 95.00 |
16: apical lateral | 100 | 94.12 | 75.00 | 100 | 95.00 |
global | 100 | 100 | 100 | 100 | 100 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Martini, N.; Meloni, A.; Positano, V.; Latta, D.D.; Keilberg, P.; Pistoia, L.; Spasiano, A.; Casini, T.; Barone, A.; Massa, A.; et al. Fully Automated Regional Analysis of Myocardial T2* Values for Iron Quantification Using Deep Learning. Electronics 2022, 11, 2749. https://doi.org/10.3390/electronics11172749
Martini N, Meloni A, Positano V, Latta DD, Keilberg P, Pistoia L, Spasiano A, Casini T, Barone A, Massa A, et al. Fully Automated Regional Analysis of Myocardial T2* Values for Iron Quantification Using Deep Learning. Electronics. 2022; 11(17):2749. https://doi.org/10.3390/electronics11172749
Chicago/Turabian StyleMartini, Nicola, Antonella Meloni, Vincenzo Positano, Daniele Della Latta, Petra Keilberg, Laura Pistoia, Anna Spasiano, Tommaso Casini, Angelica Barone, Antonella Massa, and et al. 2022. "Fully Automated Regional Analysis of Myocardial T2* Values for Iron Quantification Using Deep Learning" Electronics 11, no. 17: 2749. https://doi.org/10.3390/electronics11172749
APA StyleMartini, N., Meloni, A., Positano, V., Latta, D. D., Keilberg, P., Pistoia, L., Spasiano, A., Casini, T., Barone, A., Massa, A., Ripoli, A., & Cademartiri, F. (2022). Fully Automated Regional Analysis of Myocardial T2* Values for Iron Quantification Using Deep Learning. Electronics, 11(17), 2749. https://doi.org/10.3390/electronics11172749