Native T1 Map**-Based Radiomics for Noninvasive Prediction of the Therapeutic Effect of Pulmonary Arterial Hypertension
Abstract
:1. Introduction
2. Materials and Methods
2.1. Patient Population
2.2. CMR Examination
2.3. CMR Imaging Analysis
2.4. Radiomics Features Extraction
2.5. Radiomics Model Construction
2.6. Statistical Analysis
3. Results
3.1. Clinical and Conventional CMR Characteristics
3.2. Radiomics Model Construction and Evaluation
4. Discussion
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Ruopp, N.F.; Cockrill, B.A. Diagnosis and Treatment of Pulmonary Arterial Hypertension: A Review. JAMA 2022, 327, 1379–1391. [Google Scholar] [CrossRef] [PubMed]
- **g, Z.-C.; Xu, X.-Q.; Han, Z.-Y.; Wu, Y.; Deng, K.-W.; Wang, H.; Wang, Z.-W.; Cheng, X.-S.; Xu, B.; Hu, S.-S.; et al. Registry and Survival Study in Chinese Patients With Idiopathic and Familial Pulmonary Arterial Hypertension. Chest 2007, 132, 373–379. [Google Scholar] [CrossRef] [PubMed]
- Zhang, R.; Dai, L.-Z.; ** and Extracellular Volume (ECV) in clinical practice: A comprehensive review. J. Cardiovasc. Magn. Reson. 2016, 18, 89. [Google Scholar] [CrossRef] [Green Version]
- Roller, F.C.; Harth, S.; Schneider, C.; Krombach, G.A. T1, T2 Map** and Extracellular Volume Fraction (ECV): Application, Value and Further Perspectives in Myocardial Inflammation and Cardiomyopathies. RoFo 2015, 187, 760–770. [Google Scholar] [CrossRef] [Green Version]
- Alabed, S.; Saunders, L.; Garg, P.; Shahin, Y.; Alandejani, F.; Rolf, A.; Puntmann, V.O.; Nagel, E.; Wild, J.M.; Kiely, D.G.; et al. Myocardial T1-map** and extracellular volume in pulmonary arterial hypertension: A systematic review and meta-analysis. Magn. Reson. Imaging 2021, 79, 66–75. [Google Scholar] [CrossRef]
- Reiter, U.; Reiter, G.; Kovacs, G.; Adelsmayr, G.; Greiser, A.; Olschewski, H.; Fuchsjäger, M. Native myocardial T1 map** in pulmonary hypertension: Correlations with cardiac function and hemodynamics. Eur. Radiol. 2017, 27, 157–166. [Google Scholar] [CrossRef] [PubMed]
- Raisi-Estabragh, Z.; Izquierdo, C.; Campello, V.M.; Martin-Isla, C.; Jaggi, A.; Harvey, N.C.; Lekadir, K.; E Petersen, S. Cardiac magnetic resonance radiomics: Basic principles and clinical perspectives. Eur. Heart J. Cardiovasc. Imaging 2020, 21, 349–356. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Raisi-Estabragh, Z.; Gkontra, P.; Jaggi, A.; Cooper, J.; Augusto, J.; Bhuva, A.N.; Davies, R.H.; Manisty, C.H.; Moon, J.C.; Munroe, P.B.; et al. Repeatability of Cardiac Magnetic Resonance Radiomics: A Multi-Centre Multi-Vendor Test-Retest Study. Front. Cardiovasc. Med. 2020, 7, 586236. [Google Scholar] [CrossRef] [PubMed]
- Lambin, P.; Leijenaar, R.T.H.; Deist, T.M.; Peerlings, J.; de Jong, E.E.C.; van Timmeren, J.; Sanduleanu, S.; Larue, R.T.H.M.; Even, A.J.G.; Jochems, A.; et al. Radiomics: The bridge between medical imaging and personalized medicine. Nat. Rev. Clin. Oncol. 2017, 14, 749–762. [Google Scholar] [CrossRef] [Green Version]
- van Timmeren, J.E.; Cester, D.; Tanadini-Lang, S.; Alkadhi, H.; Baessler, B. Radiomics in medical imaging—“how-to” guide and critical reflection. Insights Imaging 2020, 11, 91. [Google Scholar] [CrossRef]
- Avanzo, M.; Stancanello, J.; El Naqa, I. Beyond imaging: The promise of radiomics. Phys. Medica 2017, 38, 122–139. [Google Scholar] [CrossRef]
- Martin-Isla, C.; Campello, V.M.; Izquierdo, C.; Raisi-Estabragh, Z.; Baeßler, B.; Petersen, S.E.; Lekadir, K. Image-Based Cardiac Diagnosis with Machine Learning: A Review. Front. Cardiovasc. Med. 2020, 7, 1. [Google Scholar] [CrossRef] [Green Version]
- Jiang, B.; Guo, N.; Ge, Y.; Zhang, L.; Oudkerk, M.; ** with right ventricular function and pulmonary haemodynamics in patients with chronic thromboembolic pulmonary hypertension before and after balloon pulmonary angioplasty. Eur. Radiol. 2019, 29, 1565–1573. [Google Scholar] [CrossRef]
- Nitsche, C.; Kammerlander, A.A.; Binder, C.; Duca, F.; Aschauer, S.; Koschutnik, M.; Snidat, A.; Beitzke, B.; Loewe, C.; Bonderman, D.; et al. Native T1 time of right ventricular insertion points by cardiac magnetic resonance: Relation with invasive haemodynamics and outcome in heart failure with preserved ejection fraction. Eur. Heart J. Cardiovasc. Imaging 2020, 21, 683–691. [Google Scholar] [CrossRef]
- Kim, P.K.; Hong, Y.J.; Im, D.J.; Suh, Y.J.; Park, C.H.; Kim, J.Y.; Chang, S.; Lee, H.-J.; Hur, J.; Kim, Y.J.; et al. Myocardial T1 and T2 Map**: Techniques and Clinical Applications. Korean J. Radiol. 2017, 18, 113–131. [Google Scholar] [CrossRef] [PubMed]
- Son, J.; Hong, Y.J.; Kim, S.; Han, K.; Lee, H.-J.; Hur, J.; Kim, Y.J.; Choi, B.W. Radiomics Feature Analysis Using Native T1 Map** for Discriminating between Cardiac Tumors and Thrombi. Acad. Radiol. 2021, 29, S1–S8. [Google Scholar] [CrossRef] [PubMed]
- Saunders, L.C.; Johns, C.S.; Stewart, N.J.; Oram, C.J.E.; Capener, D.A.; Puntmann, V.O.; Elliot, C.A.; Condliffe, R.C.; Kiely, D.G.; Graves, M.J.; et al. Diagnostic and prognostic significance of cardiovascular magnetic resonance native myocardial T1 map** in patients with pulmonary hypertension. J. Cardiovasc. Magn. Reson. 2018, 20, 78. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Liu, D.; Liu, F.; **: Diagnostic and Predictive Performance for Myocardial Injury in Acute ST-Segment-Elevation Myocardial Infarction. Korean J. Radiol. 2020, 22, 535–546. [Google Scholar] [CrossRef]
- Neisius, U.; El-Rewaidy, H.; Nakamori, S.; Rodriguez, J.; Manning, W.J.; Nezafat, R. Radiomic Analysis of Myocardial Native T1 Imaging Discriminates between Hypertensive Heart Disease and Hypertrophic Cardiomyopathy. JACC Cardiovasc. Imaging 2019, 12, 1946–1954. [Google Scholar] [CrossRef]
Parameter | Effective Group, n = 33 | Ineffective Group, n = 22 | p |
---|---|---|---|
Age, yrs | 33 ± 17 | 32 ± 12 | 0.977 |
Gender | 0.157 | ||
Females (%) | 29 (87.88) | 16 (72.73) | |
Males (%) | 4 (12.12) | 6 (27.27) | |
Baseline risk status | 0.022 | ||
Low-risk (%) | 20 (60.60) | 5 (22.73) | |
Intermediate-risk (%) | 10 (30.30) | 13 (59.09) | |
High-risk (%) | 3 (9.10) | 4 (18.18) | |
RHC parameters | |||
Mean pulmonary arterial pressure (mmHg) | 43.36 ± 12.19 | 52.86 ± 16.82 | 0.018 |
Pulmonary arterial wedge pressure (mmHg) | 7.88 ± 2.46 | 11.00 ± 10.29 | 0.100 |
Pulmonary vessel resistance (WU) | 7.86 ± 4.56 | 11.05 ± 5.98 | 0.031 |
Cardiac functional parameters | |||
LVEF (%) | 61.30 ± 8.45 | 62.96 ± 11.81 | 0.545 |
LV SV index (mL/m2) | 43.39 ± 17.27 | 37.49 ± 13.02 | 0.179 |
LV EDV index (mL/m2) | 63.49 ± 15.04 | 58.97 ± 13.34 | 0.261 |
LV ESV index (mL/m2) | 43.39 ± 17.27 | 37.49 ± 13.01 | 0.527 |
RVEF (%) | 42.41 ± 9.77 | 38.53 ± 12.26 | 0.199 |
RV SV index (mL/m2) | 48.60 ± 19.13 | 48.57 ± 18.96 | 0.996 |
RV EDV index (mL/m2) | 113.41 ± 34.38 | 118.95 ± 28.59 | 0.541 |
RV ESV index (mL/m2) | 67.16 ± 28.88 | 82.81 ± 49.60 | 0.145 |
Native T1 time ARVIP (ms) | 1411.18 ± 108.86 | 1435.98 ± 98.46 | 0.395 |
Native T1 time IRVIP (ms) | 1436.58 ± 115.21 | 1455.00 ± 69.74 | 0.505 |
Parameter | Training Cohort, n = 44 | Test Cohort, n = 11 | p |
---|---|---|---|
Age, yrs | 33 ± 16 | 32 ± 10 | 0.897 |
Gender | 0.387 | ||
Females (%) | 35 (79.55) | 10 (90.91) | |
Males (%) | 9 (20.45) | 1 (9.09) | |
Baseline risk status | 0.530 | ||
Low-risk (%) | 19 (43.18) | 6 (54.55) | |
Intermediate-risk (%) | 20 (45.45) | 3 (27.27) | |
High-risk (%) | 5 (11.37) | 2 (18.18) | |
RHC parameters | |||
Mean pulmonary arterial pressure (mmHg) | 48.74 ± 15.45 | 40.91 ± 10.15 | 0.118 |
Pulmonary arterial wedge pressure(mmHg) | 9.41 ± 7.43 | 7.82 ± 2.094 | 0.488 |
Pulmonary vessel resistance (WU) | 9.90 ± 5.58 | 6.25 ± 3.23 | 0.009 |
Cardiac functional parameters | |||
LVEF (%) | 62.61 ± 9.35 | 59.38 ± 11.85 | 0.336 |
LV SV index (mL/m2) | 41.64 ± 16.76 | 38.59 ± 11.872 | 0.573 |
LV EDV index (mL/m2) | 62.68 ± 15.37 | 57.69 ± 9.34 | 0.309 |
LV ESV index (mL/m2) | 24.28 ± 8.32 | 23.28 ± 7.44 | 0.719 |
RVEF (%) | 40.78 ± 11.13 | 41.16 ± 10.43 | 0.920 |
RV SV index (mL/m2) | 49.69 ± 20.20 | 44.20 ± 12.07 | 0.393 |
RV EDV index (mL/m2) | 120.08 ± 32.08 | 95.69 ± 24.65 | 0.029 |
RV ESV index (mL/m2) | 72.56 ± 28.77 | 76.86 ± 67.70 | 0.746 |
Native T1 time ARVIP (ms) | 1417.70 ± 106.51 | 1434.55 ± 100.32 | 0.629 |
Native T1 time IRVIP (ms) | 1428.52 ± 101.21 | 1505.64 ± 62.19 | 0.020 |
Cut-Off Value | AUC | Accuracy | Specificity | Sensitivity | PPV | NPV | |
---|---|---|---|---|---|---|---|
Training cohort | 0.589 | 0.955 | 0.909 | 0.889 | 0.962 | 0.892 | 0.9375 |
Test cohort | 0.589 | 0.893 | 0.818 | 1.000 | 0.714 | 1.000 | 0.667 |
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
Wang, Y.; Lin, L.; Li, X.; Cao, J.; Wang, J.; **g, Z.-C.; Li, S.; Liu, H.; Wang, X.; **, Z.-Y.; et al. Native T1 Map**-Based Radiomics for Noninvasive Prediction of the Therapeutic Effect of Pulmonary Arterial Hypertension. Diagnostics 2022, 12, 2492. https://doi.org/10.3390/diagnostics12102492
Wang Y, Lin L, Li X, Cao J, Wang J, **g Z-C, Li S, Liu H, Wang X, ** Z-Y, et al. Native T1 Map**-Based Radiomics for Noninvasive Prediction of the Therapeutic Effect of Pulmonary Arterial Hypertension. Diagnostics. 2022; 12(10):2492. https://doi.org/10.3390/diagnostics12102492
Chicago/Turabian StyleWang, Yue, Lu Lin, **ao Li, Jian Cao, Jian Wang, Zhi-Cheng **g, Sen Li, Hao Liu, **n Wang, Zheng-Yu **, and et al. 2022. "Native T1 Map**-Based Radiomics for Noninvasive Prediction of the Therapeutic Effect of Pulmonary Arterial Hypertension" Diagnostics 12, no. 10: 2492. https://doi.org/10.3390/diagnostics12102492