1
|
Sager DF, Manz N, Manser S, Laubscher L, Stark AW, Schütze J, Heiniger PS, Markendorf S, Kaufmann PA, Gräni C, Buechel RR. Reproducibility of Left Ventricular Function Derived From Cardiac Magnetic Resonance and Gated 13N-Ammonia Positron Emission Tomography Myocardial Perfusion Imaging: A Head-to-Head Comparison Using Hybrid Positron Emission Tomography/Magnetic Resonance. Acad Radiol 2024; 31:1248-1255. [PMID: 37940426 DOI: 10.1016/j.acra.2023.10.030] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/24/2023] [Revised: 10/04/2023] [Accepted: 10/13/2023] [Indexed: 11/10/2023]
Abstract
RATIONALE AND OBJECTIVES Cardiac magnetic resonance (CMR) and gated 13N-ammonia positron emission tomography myocardial perfusion imaging (PET-MPI) offer accurate and highly comparable global left ventricular ejection fraction (LVEF) measurements. In addition to accuracy, however, reproducibility is crucial to avoid variations in LVEF assessment potentially negatively impacting treatment decisions. We performed a head-to-head comparison of the reproducibility of LVEF measurements derived from simultaneously acquired CMR and PET-MPI using different state-of-the-art commercially available software. MATERIALS AND METHODS 93 patients undergoing hybrid PET/MR were retrospectively included. LVEF was derived from CMR and PET-MPI at two separate core labs, using two state-of-the-art software packages for CMR (cvi42 and Medis Suite MR) and PET (QPET and CardIQ Physio). Intra- and inter-reader agreement was assessed using correlation and Bland-Altman (BA) analyses. RESULTS While intra- and inter-reader reproducibility of LVEF was high among both modalities and all software packages (r ≥ 0.87 and ICC≥0.91, all significant at p < 0.0001), LVEF derived from PET-MPI and analyzed with QPET outperformed all other analyses (intra-reader reproducibility: r = 0.99, ICC=0.99; inter-reader reproducibility: r = 0.98, ICC=1.00; Pearson correlations significantly higher than all others at p ≤ 0.0001). BA analyses showed smaller biases for LVEF derived from PET-MPI (-0.1% and +0.9% for intra-reader, -0.4% and -0.8% for inter-reader agreement) than those derived from CMR (+0.7% and +2.8% for intra-reader, -0.9% and -2.2% for inter-reader agreement) with similar results for BA limits of agreement. CONCLUSION Gated 13N-ammonia PET-MPI provides equivalent reproducibility of LVEF compared to CMR. It may offer a valid alternative to CMR for patients requiring LV functional assessment.
Collapse
Affiliation(s)
- Dominik F Sager
- Department of Nuclear Medicine, Cardiac Imaging , University Hospital of Zurich, Ramistrasse 100, CH-8091 Zurich, Switzerland (D.F.S., P.S.H., S.M., P.A.K., R.R.B.)
| | - Nico Manz
- Faculty of Medicine, University of Bern, Murtenstrasse 11, CH-3008 Bern, Switzerland (N.M., S.M.)
| | - Sarah Manser
- Faculty of Medicine, University of Bern, Murtenstrasse 11, CH-3008 Bern, Switzerland (N.M., S.M.)
| | - Lily Laubscher
- Department of Health Science and Technology, ETH Zurich, Ramistrasse 101, CH-8092 Zurich, Switzerland (L.L.)
| | - Anselm W Stark
- Department of Cardiology, University Hospital of Bern, Freiburgstrasse 15, CH-3010 Bern, Switzerland (A.W.S., J.S., C.G
| | - Jonathan Schütze
- Department of Cardiology, University Hospital of Bern, Freiburgstrasse 15, CH-3010 Bern, Switzerland (A.W.S., J.S., C.G
| | - Pascal S Heiniger
- Department of Nuclear Medicine, Cardiac Imaging , University Hospital of Zurich, Ramistrasse 100, CH-8091 Zurich, Switzerland (D.F.S., P.S.H., S.M., P.A.K., R.R.B.)
| | - Susanne Markendorf
- Department of Nuclear Medicine, Cardiac Imaging , University Hospital of Zurich, Ramistrasse 100, CH-8091 Zurich, Switzerland (D.F.S., P.S.H., S.M., P.A.K., R.R.B.)
| | - Philipp A Kaufmann
- Department of Nuclear Medicine, Cardiac Imaging , University Hospital of Zurich, Ramistrasse 100, CH-8091 Zurich, Switzerland (D.F.S., P.S.H., S.M., P.A.K., R.R.B.)
| | - Christoph Gräni
- Department of Cardiology, University Hospital of Bern, Freiburgstrasse 15, CH-3010 Bern, Switzerland (A.W.S., J.S., C.G
| | - Ronny R Buechel
- Department of Nuclear Medicine, Cardiac Imaging , University Hospital of Zurich, Ramistrasse 100, CH-8091 Zurich, Switzerland (D.F.S., P.S.H., S.M., P.A.K., R.R.B.).
| |
Collapse
|
2
|
Motwani M. 2022 Artificial intelligence primer for the nuclear cardiologist. J Nucl Cardiol 2023; 30:2441-2453. [PMID: 35854041 DOI: 10.1007/s12350-022-03049-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/15/2022] [Accepted: 06/14/2022] [Indexed: 10/17/2022]
Abstract
Driven by advances in computing power, the past decade has seen rapid developments in artificial intelligence (AI) which now offers potential enhancements to every aspect of nuclear cardiology workflow including acquisition, reconstruction, segmentation, direct image analysis, and interpretation; as well as facilitating clinical and imaging big-data integration for superior personalized risk stratification. To understand the relevance and potential of AI in their field, this review provides a primer for nuclear cardiologists in 2022. The aim is to explain terminology and provide a summary of key current implementations, challenges, and future aspirations of AI-based enhancements to nuclear cardiology.
Collapse
Affiliation(s)
- Manish Motwani
- Department of Cardiology, Manchester Heart Institute, Manchester Royal Infirmary, Manchester Heart Centre, Manchester University NHS Foundation Trust, Oxford Road, Manchester, UK.
- Institute of Cardiovascular Science, University of Manchester, Manchester, UK.
| |
Collapse
|
3
|
Alahdab F, El Shawi R, Ahmed AI, Han Y, Al-Mallah M. Patient-level explainable machine learning to predict major adverse cardiovascular events from SPECT MPI and CCTA imaging. PLoS One 2023; 18:e0291451. [PMID: 37967112 PMCID: PMC10651041 DOI: 10.1371/journal.pone.0291451] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2023] [Accepted: 08/30/2023] [Indexed: 11/17/2023] Open
Abstract
BACKGROUND Machine learning (ML) has shown promise in improving the risk prediction in non-invasive cardiovascular imaging, including SPECT MPI and coronary CT angiography. However, most algorithms used remain black boxes to clinicians in how they compute their predictions. Furthermore, objective consideration of the multitude of available clinical data, along with the visual and quantitative assessments from CCTA and SPECT, are critical for optimal patient risk stratification. We aim to provide an explainable ML approach to predict MACE using clinical, CCTA, and SPECT data. METHODS Consecutive patients who underwent clinically indicated CCTA and SPECT myocardial imaging for suspected CAD were included and followed up for MACEs. A MACE was defined as a composite outcome that included all-cause mortality, myocardial infarction, or late revascularization. We employed an Automated Machine Learning (AutoML) approach to predict MACE using clinical, CCTA, and SPECT data. Various mainstream models with different sets of hyperparameters have been explored, and critical predictors of risk are obtained using explainable techniques on the global and patient levels. Ten-fold cross-validation was used in training and evaluating the AutoML model. RESULTS A total of 956 patients were included (mean age 61.1 ±14.2 years, 54% men, 89% hypertension, 81% diabetes, 84% dyslipidemia). Obstructive CAD on CCTA and ischemia on SPECT were observed in 14% of patients, and 11% experienced MACE. ML prediction's sensitivity, specificity, and accuracy in predicting a MACE were 69.61%, 99.77%, and 96.54%, respectively. The top 10 global predictive features included 8 CCTA attributes (segment involvement score, number of vessels with severe plaque ≥70, ≥50% stenosis in the left marginal coronary artery, calcified plaque, ≥50% stenosis in the left circumflex coronary artery, plaque type in the left marginal coronary artery, stenosis degree in the second obtuse marginal of the left circumflex artery, and stenosis category in the marginals of the left circumflex artery) and 2 clinical features (past medical history of MI or left bundle branch block, being an ever smoker). CONCLUSION ML can accurately predict risk of developing a MACE in patients suspected of CAD undergoing SPECT MPI and CCTA. ML feature-ranking can also show, at a sample- as well as at a patient-level, which features are key in making such a prediction.
Collapse
Affiliation(s)
- Fares Alahdab
- Houston Methodist DeBakey Heart & Vascular Center, Houston, TX, United States of America
| | - Radwa El Shawi
- Institute of Computer Science, University of Tartu, Tartu, Estonia
| | - Ahmed Ibrahim Ahmed
- Houston Methodist DeBakey Heart & Vascular Center, Houston, TX, United States of America
| | - Yushui Han
- Houston Methodist DeBakey Heart & Vascular Center, Houston, TX, United States of America
| | - Mouaz Al-Mallah
- Houston Methodist DeBakey Heart & Vascular Center, Houston, TX, United States of America
| |
Collapse
|
4
|
Moskal P, Kubicz E, Grudzień G, Czerwiński E, Dulski K, Leszczyński B, Niedźwiecki S, Stępień EŁ. Developing a novel positronium biomarker for cardiac myxoma imaging. EJNMMI Phys 2023; 10:22. [PMID: 36959477 PMCID: PMC10036702 DOI: 10.1186/s40658-023-00543-w] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2021] [Accepted: 03/10/2023] [Indexed: 03/25/2023] Open
Abstract
PURPOSE Cardiac myxoma (CM), the most common cardiac tumor in adults, accounts for 50-75% of benign cardiac tumors. The diagnosis of CM is often elusive, especially in young stroke survivors and transthoracic echocardiography (TTE) is the initial technique for the differential diagnostics of CM. Less invasive cardiac computed tomography (CT) and magnetic resonance imaging (MRI) are not available for the majority of cardiac patients. Here, a robust imaging approach, ortho-Positronium (o-Ps) imaging, is presented to determine cardiac myxoma extracted from patients undergoing urgent cardiac surgery due to unexpected atrial masses. We aimed to assess if the o-Ps atom, produced copiously in intramolecular voids during the PET imaging, serves as a biomarker for CM diagnosing. METHODS Six perioperative CM and normal (adipose) tissue samples from patients, with primary diagnosis confirmed by the histopathology examination, were examined using positron annihilation lifetime spectroscopy (PALS) and micro-CT. Additionally, cell cultures and confocal microscopy techniques were used to picture cell morphology and origin. RESULTS We observed significant shortening in the mean o-Ps lifetime in tumor with compare to normal tissues: an average value of 1.92(02) ns and 2.72(05) ns for CM and the adipose tissue, respectively. Microscopic differences between tumor samples, confirmed in histopathology examination and micro-CT, did not influenced the major positronium imaging results. CONCLUSIONS Our findings, combined with o-Ps lifetime analysis, revealed the novel emerging positronium imaging marker (o-PS) for cardiovascular imaging. This method opens the new perspective to facilitate the quantitative in vivo assessment of intracardiac masses on a molecular (nanoscale) level.
Collapse
Affiliation(s)
- Paweł Moskal
- Department of Experimental Particle Physics and Applications, Marian Smoluchowski Institute of Physics, Faculty of Physics, Astronomy and Applied Computer Science, Jagiellonian University, Łojasiewicza 11, 30-348, Kraków, Poland.
- Total-Body Jagiellonian-PET Laboratory, Jagiellonian University, Kraków, Poland.
- Center for Theranostics, Jagiellonian University, Kraków, Poland.
| | - Ewelina Kubicz
- Total-Body Jagiellonian-PET Laboratory, Jagiellonian University, Kraków, Poland.
- Center for Theranostics, Jagiellonian University, Kraków, Poland.
- Department of Medical Physics, Marian Smoluchowski Institute of Physics, Faculty of Physics, Astronomy and Applied Computer Science, Jagiellonian University, Łojasiewicza 11, 30-348, Kraków, Poland.
| | - Grzegorz Grudzień
- Department of Cardiovascular Surgery and Transplantology, John Paul II Hospital, Kraków, Poland
- Department of Cardiovascular Surgery and Transplantology, Jagiellonian University Medical College, Kraków, Poland
| | - Eryk Czerwiński
- Department of Experimental Particle Physics and Applications, Marian Smoluchowski Institute of Physics, Faculty of Physics, Astronomy and Applied Computer Science, Jagiellonian University, Łojasiewicza 11, 30-348, Kraków, Poland
- Total-Body Jagiellonian-PET Laboratory, Jagiellonian University, Kraków, Poland
| | - Kamil Dulski
- Department of Experimental Particle Physics and Applications, Marian Smoluchowski Institute of Physics, Faculty of Physics, Astronomy and Applied Computer Science, Jagiellonian University, Łojasiewicza 11, 30-348, Kraków, Poland
- Total-Body Jagiellonian-PET Laboratory, Jagiellonian University, Kraków, Poland
| | - Bartosz Leszczyński
- Department of Medical Physics, Marian Smoluchowski Institute of Physics, Faculty of Physics, Astronomy and Applied Computer Science, Jagiellonian University, Łojasiewicza 11, 30-348, Kraków, Poland
| | - Szymon Niedźwiecki
- Department of Experimental Particle Physics and Applications, Marian Smoluchowski Institute of Physics, Faculty of Physics, Astronomy and Applied Computer Science, Jagiellonian University, Łojasiewicza 11, 30-348, Kraków, Poland
- Total-Body Jagiellonian-PET Laboratory, Jagiellonian University, Kraków, Poland
| | - Ewa Ł Stępień
- Total-Body Jagiellonian-PET Laboratory, Jagiellonian University, Kraków, Poland.
- Center for Theranostics, Jagiellonian University, Kraków, Poland.
- Department of Medical Physics, Marian Smoluchowski Institute of Physics, Faculty of Physics, Astronomy and Applied Computer Science, Jagiellonian University, Łojasiewicza 11, 30-348, Kraków, Poland.
| |
Collapse
|
5
|
Advances in Single-Photon Emission Computed Tomography. Cardiol Clin 2023; 41:117-127. [PMID: 37003670 DOI: 10.1016/j.ccl.2023.01.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/26/2023]
Abstract
The clinical presentation of coronary artery disease (CAD) has changed during the last 20 years with less ischemia on stress testing and more nonobstructive CAD on coronary angiography. Single-photon emission computed tomography (SPECT) myocardial perfusion imaging should include the measurement of myocardial flow reserve and assessment of coronary calcium for the diagnosis of nonobstructive CAD and coronary microvascular disease. SPECT/CT systems provide reliable attenuation correction for better specificity and low-dose CT for coronary calcium evaluation. SPECT MFR measurement is accurate, well validated, and repeatable.
Collapse
|
6
|
Wellnhofer E. Real-World and Regulatory Perspectives of Artificial Intelligence in Cardiovascular Imaging. Front Cardiovasc Med 2022; 9:890809. [PMID: 35935648 PMCID: PMC9354141 DOI: 10.3389/fcvm.2022.890809] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2022] [Accepted: 06/13/2022] [Indexed: 12/02/2022] Open
Abstract
Recent progress in digital health data recording, advances in computing power, and methodological approaches that extract information from data as artificial intelligence are expected to have a disruptive impact on technology in medicine. One of the potential benefits is the ability to extract new and essential insights from the vast amount of data generated during health care delivery every day. Cardiovascular imaging is boosted by new intelligent automatic methods to manage, process, segment, and analyze petabytes of image data exceeding historical manual capacities. Algorithms that learn from data raise new challenges for regulatory bodies. Partially autonomous behavior and adaptive modifications and a lack of transparency in deriving evidence from complex data pose considerable problems. Controlling new technologies requires new controlling techniques and ongoing regulatory research. All stakeholders must participate in the quest to find a fair balance between innovation and regulation. The regulatory approach to artificial intelligence must be risk-based and resilient. A focus on unknown emerging risks demands continuous surveillance and clinical evaluation during the total product life cycle. Since learning algorithms are data-driven, high-quality data is fundamental for good machine learning practice. Mining, processing, validation, governance, and data control must account for bias, error, inappropriate use, drifts, and shifts, particularly in real-world data. Regulators worldwide are tackling twenty-first century challenges raised by “learning” medical devices. Ethical concerns and regulatory approaches are presented. The paper concludes with a discussion on the future of responsible artificial intelligence.
Collapse
|
7
|
Rios R, Miller RJH, Manral N, Sharir T, Einstein AJ, Fish MB, Ruddy TD, Kaufmann PA, Sinusas AJ, Miller EJ, Bateman TM, Dorbala S, Di Carli M, Van Kriekinge SD, Kavanagh PB, Parekh T, Liang JX, Dey D, Berman DS, Slomka PJ. Handling missing values in machine learning to predict patient-specific risk of adverse cardiac events: Insights from REFINE SPECT registry. Comput Biol Med 2022; 145:105449. [PMID: 35381453 PMCID: PMC9117456 DOI: 10.1016/j.compbiomed.2022.105449] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2021] [Revised: 03/21/2022] [Accepted: 03/22/2022] [Indexed: 12/13/2022]
Abstract
BACKGROUND Machine learning (ML) models can improve prediction of major adverse cardiovascular events (MACE), but in clinical practice some values may be missing. We evaluated the influence of missing values in ML models for patient-specific prediction of MACE risk. METHODS We included 20,179 patients from the multicenter REFINE SPECT registry with MACE follow-up data. We evaluated seven methods for handling missing values: 1) removal of variables with missing values (ML-Remove), 2) imputation with median and unique category for continuous and categorical variables, respectively (ML-Traditional), 3) unique category for missing variables (ML-Unique), 4) cluster-based imputation (ML-Cluster), 5) regression-based imputation (ML-Regression), 6) missRanger imputation (ML-MR), and 7) multiple imputation (ML-MICE). We trained ML models with full data and simulated missing values in testing patients. Prediction performance was evaluated using area under the receiver-operating characteristic curve (AUC) and compared with a model without missing values (ML-All), expert visual diagnosis and total perfusion deficit (TPD). RESULTS During mean follow-up of 4.7 ± 1.5 years, 3,541 patients experienced at least one MACE (3.7% annualized risk). ML-All (reference model-no missing values) had AUC 0.799 for MACE risk prediction. All seven models with missing values had lower AUC (ML-Remove: 0.778, ML-MICE: 0.774, ML-Cluster: 0.771, ML-Traditional: 0.771, ML-Regression: 0.770, ML-MR: 0.766, and ML-Unique: 0.766; p < 0.01 for ML-Remove vs remaining methods). Stress TPD (AUC 0.698) and visual diagnosis (0.681) had the lowest AUCs. CONCLUSION Missing values reduce the accuracy of ML models when predicting MACE risk. Removing variables with missing values and retraining the model may yield superior patient-level prediction performance.
Collapse
Affiliation(s)
- Richard Rios
- Departments of Medicine (Division of Artificial Intelligence in Medicine), Imaging, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Universidad Nacional de Colombia, Sede de La Paz, GAUNAL, La Paz, Colombia
| | - Robert J H Miller
- Departments of Medicine (Division of Artificial Intelligence in Medicine), Imaging, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Department of Cardiac Sciences, University of Calgary, Calgary, AB, Canada
| | - Nipun Manral
- Departments of Medicine (Division of Artificial Intelligence in Medicine), Imaging, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, CA, USA
| | - Tali Sharir
- Department of Nuclear Cardiology, Assuta Medical Center, Tel Aviv, Israel; Faculty of Health Sciences, Ben Gurion University of the Negev, Beer Sheba, Israel
| | - Andrew J Einstein
- Division of Cardiology, Department of Medicine, Columbia University Irving Medical Center and New York-Presbyterian Hospital, New York, NY, USA; Department of Radiology, Columbia University Irving Medical Center and New York-Presbyterian Hospital, New York, NY, USA
| | - Mathews B Fish
- Department of Nuclear Medicine, Oregon Heart and Vascular Institute, Sacred Heart Medical Center, Springfield, OR, USA
| | - Terrence D Ruddy
- Division of Cardiology, University of Ottawa Heart Institute, Ottawa, ON, Canada
| | - Philipp A Kaufmann
- Department of Nuclear Medicine, Cardiac Imaging, University Hospital Zurich, Zurich, Switzerland
| | - Albert J Sinusas
- Department of Internal Medicine, Section of Cardiovascular Medicine, Yale University School of Medicine, New Haven, CT, USA
| | - Edward J Miller
- Department of Internal Medicine, Section of Cardiovascular Medicine, Yale University School of Medicine, New Haven, CT, USA
| | | | - Sharmila Dorbala
- Division of Nuclear Medicine and Molecular Imaging, Department of Radiology, Brigham and Women's Hospital, Boston, MA, USA
| | - Marcelo Di Carli
- Division of Nuclear Medicine and Molecular Imaging, Department of Radiology, Brigham and Women's Hospital, Boston, MA, USA
| | - Serge D Van Kriekinge
- Departments of Medicine (Division of Artificial Intelligence in Medicine), Imaging, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, CA, USA
| | - Paul B Kavanagh
- Departments of Medicine (Division of Artificial Intelligence in Medicine), Imaging, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, CA, USA
| | - Tejas Parekh
- Departments of Medicine (Division of Artificial Intelligence in Medicine), Imaging, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, CA, USA
| | - Joanna X Liang
- Departments of Medicine (Division of Artificial Intelligence in Medicine), Imaging, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, CA, USA
| | - Damini Dey
- Departments of Medicine (Division of Artificial Intelligence in Medicine), Imaging, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, CA, USA
| | - Daniel S Berman
- Departments of Medicine (Division of Artificial Intelligence in Medicine), Imaging, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, CA, USA
| | - Piotr J Slomka
- Departments of Medicine (Division of Artificial Intelligence in Medicine), Imaging, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
| |
Collapse
|
8
|
Applications of Generative Adversarial Networks (GANs) in Positron Emission Tomography (PET) imaging: A review. Eur J Nucl Med Mol Imaging 2022; 49:3717-3739. [PMID: 35451611 DOI: 10.1007/s00259-022-05805-w] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2021] [Accepted: 04/12/2022] [Indexed: 11/04/2022]
Abstract
PURPOSE This paper reviews recent applications of Generative Adversarial Networks (GANs) in Positron Emission Tomography (PET) imaging. Recent advances in Deep Learning (DL) and GANs catalysed the research of their applications in medical imaging modalities. As a result, several unique GAN topologies have emerged and been assessed in an experimental environment over the last two years. METHODS The present work extensively describes GAN architectures and their applications in PET imaging. The identification of relevant publications was performed via approved publication indexing websites and repositories. Web of Science, Scopus, and Google Scholar were the major sources of information. RESULTS The research identified a hundred articles that address PET imaging applications such as attenuation correction, de-noising, scatter correction, removal of artefacts, image fusion, high-dose image estimation, super-resolution, segmentation, and cross-modality synthesis. These applications are presented and accompanied by the corresponding research works. CONCLUSION GANs are rapidly employed in PET imaging tasks. However, specific limitations must be eliminated to reach their full potential and gain the medical community's trust in everyday clinical practice.
Collapse
|
9
|
Teuho J, Schultz J, Klén R, Knuuti J, Saraste A, Ono N, Kanaya S. Classification of ischemia from myocardial polar maps in 15O-H 2O cardiac perfusion imaging using a convolutional neural network. Sci Rep 2022; 12:2839. [PMID: 35181681 PMCID: PMC8857225 DOI: 10.1038/s41598-022-06604-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/08/2021] [Accepted: 02/03/2022] [Indexed: 12/02/2022] Open
Abstract
We implemented a two-dimensional convolutional neural network (CNN) for classification of polar maps extracted from Carimas (Turku PET Centre, Finland) software used for myocardial perfusion analysis. 138 polar maps from 15O–H2O stress perfusion study in JPEG format from patients classified as ischemic or non-ischemic based on finding obstructive coronary artery disease (CAD) on invasive coronary artery angiography were used. The CNN was evaluated against the clinical interpretation. The classification accuracy was evaluated with: accuracy (ACC), area under the receiver operating characteristic curve (AUC), F1 score (F1S), sensitivity (SEN), specificity (SPE) and precision (PRE). The CNN had a median ACC of 0.8261, AUC of 0.8058, F1S of 0.7647, SEN of 0.6500, SPE of 0.9615 and PRE of 0.9286. In comparison, clinical interpretation had ACC of 0.8696, AUC of 0.8558, F1S of 0.8333, SEN of 0.7500, SPE of 0.9615 and PRE of 0.9375. The CNN classified only 2 cases differently than the clinical interpretation. The clinical interpretation and CNN had similar accuracy in classifying false positives and true negatives. Classification of ischemia is feasible in 15O–H2O stress perfusion imaging using JPEG polar maps alone with a custom CNN and may be useful for the detection of obstructive CAD.
Collapse
Affiliation(s)
- Jarmo Teuho
- Data Science Center, Nara University of Science and Technology, Nara, Japan. .,Turku PET Centre, University of Turku, Turku, Finland. .,Turku PET Centre, Turku University Hospital, Turku, Finland.
| | - Jussi Schultz
- Turku PET Centre, Turku University Hospital, Turku, Finland
| | - Riku Klén
- Turku PET Centre, University of Turku, Turku, Finland.,Turku PET Centre, Turku University Hospital, Turku, Finland
| | - Juhani Knuuti
- Turku PET Centre, University of Turku, Turku, Finland.,Turku PET Centre, Turku University Hospital, Turku, Finland
| | - Antti Saraste
- Turku PET Centre, Turku University Hospital, Turku, Finland.,Heart Centre, Turku University Hospital and University of Turku, Turku, Finland
| | - Naoaki Ono
- Data Science Center, Nara University of Science and Technology, Nara, Japan.,Department of Science and Technology, Nara University of Science and Technology, Nara, Japan
| | - Shigehiko Kanaya
- Department of Science and Technology, Nara University of Science and Technology, Nara, Japan
| |
Collapse
|
10
|
Miller RJH, Singh A, Dey D, Slomka P. Artificial Intelligence and Cardiac PET/Computed Tomography Imaging. PET Clin 2021; 17:85-94. [PMID: 34809873 DOI: 10.1016/j.cpet.2021.06.011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Artificial intelligence is an important technology, with rapidly expanding applications for cardiac PET. We review the common terminology, including methods for training and testing, which are fundamental to understanding artificial intelligence. Next, we highlight applications to improve image acquisition, reconstruction, and segmentation. Computed tomographic imaging is commonly acquired in conjunction with PET and various artificial intelligence methods have been applied, including methods to automatically extract anatomic information or generate synthetic attenuation images. Last, we describe methods to automate disease diagnosis or risk stratification. This summary highlights the current and future clinical applications of artificial intelligence to cardiovascular PET imaging.
Collapse
Affiliation(s)
- Robert J H Miller
- Department of Cardiac Sciences, University of Calgary, GAA08 HRIC, 3230 Hospital Drive NW, Calgary AB, T2N 4Z6, Canada
| | - Ananya Singh
- Departments of Imaging and Medicine, Cedars-Sinai Medical Center, 8700 Beverly Blvd, Suite Metro 203, Los Angeles, CA 90048, USA
| | - Damini Dey
- Departments of Imaging and Medicine, Cedars-Sinai Medical Center, 8700 Beverly Blvd, Suite Metro 203, Los Angeles, CA 90048, USA
| | - Piotr Slomka
- Departments of Imaging and Medicine, Cedars-Sinai Medical Center, 8700 Beverly Blvd, Suite Metro 203, Los Angeles, CA 90048, USA.
| |
Collapse
|
11
|
de Souza Filho EM, Fernandes FDA, Portela MGR, Newlands PH, de Carvalho LND, Dos Santos TF, Dos Santos AASMD, Mesquita ET, Seixas FL, Mesquita CT, Gismondi RA. Machine Learning Algorithms to Detect Sex in Myocardial Perfusion Imaging. Front Cardiovasc Med 2021; 8:741679. [PMID: 34778403 PMCID: PMC8585770 DOI: 10.3389/fcvm.2021.741679] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2021] [Accepted: 10/06/2021] [Indexed: 11/30/2022] Open
Abstract
Myocardial perfusion imaging (MPI) is an essential tool used to diagnose and manage patients with suspected or known coronary artery disease. Additionally, the General Data Protection Regulation (GDPR) represents a milestone about individuals' data security concerns. On the other hand, Machine Learning (ML) has had several applications in the most diverse knowledge areas. It is conceived as a technology with huge potential to revolutionize health care. In this context, we developed ML models to evaluate their ability to distinguish an individual's sex from MPI assessment. We used 260 polar maps (140 men/120 women) to train ML algorithms from a database of patients referred to a university hospital for clinically indicated MPI from January 2016 to December 2018. We tested 07 different ML models, namely, Classification and Regression Tree (CART), Naive Bayes (NB), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Adaptive Boosting (AB), Random Forests (RF) and, Gradient Boosting (GB). We used a cross-validation strategy. Our work demonstrated that ML algorithms could perform well in assessing the sex of patients undergoing myocardial scintigraphy exams. All the models had accuracy greater than 82%. However, only SVM achieved 90%. KNN, RF, AB, GB had, respectively, 88, 86, 85, 83%. Accuracy standard deviation was lower in KNN, AB, and RF (0.06). SVM and RF had had the best area under the receiver operating characteristic curve (0.93), followed by GB (0.92), KNN (0.91), AB, and NB (0.9). SVM and AB achieved the best precision. Our results bring some challenges regarding the autonomy of patients who wish to keep sex information confidential and certainly add greater complexity to the debate about what data should be considered sensitive to the light of the GDPR.
Collapse
Affiliation(s)
- Erito Marques de Souza Filho
- Post-graduation in Cardiovascular Sciences, Universidade Federal Fluminense, Niterói, Brazil.,Department of Languages and Technologies, Universidade Federal Rural Do Rio de Janeiro, Rio de Janeiro, Brazil
| | - Fernando de Amorim Fernandes
- Post-graduation in Cardiovascular Sciences, Universidade Federal Fluminense, Niterói, Brazil.,Department of Nuclear Medicine, Hospital Universitário Antônio Pedro, Universidade Federal Fluminense, Niterói, Brazil
| | | | | | | | - Tadeu Francisco Dos Santos
- Department of Nuclear Medicine, Hospital Universitário Antônio Pedro, Universidade Federal Fluminense, Niterói, Brazil
| | | | - Evandro Tinoco Mesquita
- Post-graduation in Cardiovascular Sciences, Universidade Federal Fluminense, Niterói, Brazil
| | - Flávio Luiz Seixas
- Institute of Computing, Universidade Federal Fluminense, Niterói, Brazil
| | - Claudio Tinoco Mesquita
- Post-graduation in Cardiovascular Sciences, Universidade Federal Fluminense, Niterói, Brazil
| | | |
Collapse
|
12
|
Zhou J, Du M, Chang S, Chen Z. Artificial intelligence in echocardiography: detection, functional evaluation, and disease diagnosis. Cardiovasc Ultrasound 2021; 19:29. [PMID: 34416899 PMCID: PMC8379752 DOI: 10.1186/s12947-021-00261-2] [Citation(s) in RCA: 35] [Impact Index Per Article: 11.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/26/2021] [Accepted: 08/05/2021] [Indexed: 12/21/2022] Open
Abstract
Ultrasound is one of the most important examinations for clinical diagnosis of cardiovascular diseases. The speed of image movements driven by the frequency of the beating heart is faster than that of other organs. This particularity of echocardiography poses a challenge for sonographers to diagnose accurately. However, artificial intelligence for detection, functional evaluation, and disease diagnosis has gradually become an alternative for accurate diagnosis and treatment using echocardiography. This work discusses the current application of artificial intelligence in echocardiography technology, its limitations, and future development directions.
Collapse
Affiliation(s)
- Jia Zhou
- The First Affiliated Hospital, Medical Imaging Centre, Hengyang Medical School, University of South China, 69 Chuanshan Road, Hengyang, 421001, China
| | - Meng Du
- Institute of Medical Imaging, University of South China, Hengyang, China
| | - Shuai Chang
- The First Affiliated Hospital, Medical Imaging Centre, Hengyang Medical School, University of South China, 69 Chuanshan Road, Hengyang, 421001, China
| | - Zhiyi Chen
- The First Affiliated Hospital, Medical Imaging Centre, Hengyang Medical School, University of South China, 69 Chuanshan Road, Hengyang, 421001, China.
- Institute of Medical Imaging, University of South China, Hengyang, China.
| |
Collapse
|
13
|
Guo Y, Zhang Y, Lyu T, Prosperi M, Wang F, Xu H, Bian J. The application of artificial intelligence and data integration in COVID-19 studies: a scoping review. J Am Med Inform Assoc 2021; 28:2050-2067. [PMID: 34151987 PMCID: PMC8344463 DOI: 10.1093/jamia/ocab098] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/07/2021] [Revised: 05/03/2021] [Accepted: 05/06/2021] [Indexed: 12/23/2022] Open
Abstract
Objective To summarize how artificial intelligence (AI) is being applied in COVID-19 research and determine whether these AI applications integrated heterogenous data from different sources for modeling. Materials and Methods We searched 2 major COVID-19 literature databases, the National Institutes of Health’s LitCovid and the World Health Organization’s COVID-19 database on March 9, 2021. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guideline, 2 reviewers independently reviewed all the articles in 2 rounds of screening. Results In the 794 studies included in the final qualitative analysis, we identified 7 key COVID-19 research areas in which AI was applied, including disease forecasting, medical imaging-based diagnosis and prognosis, early detection and prognosis (non-imaging), drug repurposing and early drug discovery, social media data analysis, genomic, transcriptomic, and proteomic data analysis, and other COVID-19 research topics. We also found that there was a lack of heterogenous data integration in these AI applications. Discussion Risk factors relevant to COVID-19 outcomes exist in heterogeneous data sources, including electronic health records, surveillance systems, sociodemographic datasets, and many more. However, most AI applications in COVID-19 research adopted a single-sourced approach that could omit important risk factors and thus lead to biased algorithms. Integrating heterogeneous data for modeling will help realize the full potential of AI algorithms, improve precision, and reduce bias. Conclusion There is a lack of data integration in the AI applications in COVID-19 research and a need for a multilevel AI framework that supports the analysis of heterogeneous data from different sources.
Collapse
Affiliation(s)
- Yi Guo
- Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida, Gainesville, Florida, USA.,Cancer Informatics Shared Resource, University of Florida Health Cancer Center, Gainesville, Florida, USA
| | - Yahan Zhang
- Department of Pharmaceutical Outcomes and Policy, College of Pharmacy, University of Florida, Gainesville, Florida, USA
| | - Tianchen Lyu
- Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida, Gainesville, Florida, USA.,Cancer Informatics Shared Resource, University of Florida Health Cancer Center, Gainesville, Florida, USA
| | - Mattia Prosperi
- Department of Epidemiology, College of Public Health and Health Professions & College of Medicine, University of Florida, Gainesville, Florida, USA
| | - Fei Wang
- Department of Population Health Sciences, Weill Cornell Medicine, New York, New York, USA
| | - Hua Xu
- School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, Texas, USA
| | - Jiang Bian
- Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida, Gainesville, Florida, USA.,Cancer Informatics Shared Resource, University of Florida Health Cancer Center, Gainesville, Florida, USA
| |
Collapse
|
14
|
Al-Taie Z, Liu D, Mitchem JB, Papageorgiou C, Kaifi JT, Warren WC, Shyu CR. Explainable artificial intelligence in high-throughput drug repositioning for subgroup stratifications with interventionable potential. J Biomed Inform 2021; 118:103792. [PMID: 33915273 DOI: 10.1016/j.jbi.2021.103792] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2020] [Revised: 03/26/2021] [Accepted: 04/21/2021] [Indexed: 01/02/2023]
Abstract
Enabling precision medicine requires developing robust patient stratification methods as well as drugs tailored to homogeneous subgroups of patients from a heterogeneous population. Developing de novo drugs is expensive and time consuming with an ultimately low FDA approval rate. These limitations make developing new drugs for a small portion of a disease population unfeasible. Therefore, drug repositioning is an essential alternative for developing new drugs for a disease subpopulation. This shows the importance of developing data-driven approaches that find druggable homogeneous subgroups within the disease population and reposition the drugs for these subgroups. In this study, we developed an explainable AI approach for patient stratification and drug repositioning. Contrast pattern mining and network analysis were used to discover homogeneous subgroups within a disease population. For each subgroup, a biomedical network analysis was done to find the drugs that are most relevant to a given subgroup of patients. The set of candidate drugs for each subgroup was ranked using an aggregated drug score assigned to each drug. The proposed method represents a human-in-the-loop framework, where medical experts use the data-driven results to generate hypotheses and obtain insights into potential therapeutic candidates for patients who belong to a subgroup. Colorectal cancer (CRC) was used as a case study. Patients' phenotypic and genotypic data was utilized with a heterogeneous knowledge base because it gives a multi-view perspective for finding new indications for drugs outside of their original use. Our analysis of the top candidate drugs for the subgroups identified by medical experts showed that most of these drugs are cancer-related, and most of them have the potential to be a CRC regimen based on studies in the literature.
Collapse
Affiliation(s)
- Zainab Al-Taie
- Institute for Data Science & Informatics, University of Missouri, Columbia, MO 65211, USA; Department of Computer Science, College of Science for Women, University of Baghdad, Baghdad, Iraq
| | - Danlu Liu
- Electrical Engineering and Computer Science Department, University of Missouri, Columbia, MO 65211, USA
| | - Jonathan B Mitchem
- Institute for Data Science & Informatics, University of Missouri, Columbia, MO 65211, USA; Department of Surgery, School of Medicine, University of Missouri, Columbia, MO 65212, USA; Harry S. Truman Memorial Veterans' Hospital, Columbia, MO 65201, USA.
| | - Christos Papageorgiou
- Department of Surgery, School of Medicine, University of Missouri, Columbia, MO 65212, USA
| | - Jussuf T Kaifi
- Department of Surgery, School of Medicine, University of Missouri, Columbia, MO 65212, USA; Harry S. Truman Memorial Veterans' Hospital, Columbia, MO 65201, USA
| | - Wesley C Warren
- Institute for Data Science & Informatics, University of Missouri, Columbia, MO 65211, USA; Department of Surgery, School of Medicine, University of Missouri, Columbia, MO 65212, USA; Department of Animal Sciences, Bond Life Sciences Center, University of Missouri, 1201 Rollins Street, Columbia, MO 65211, USA
| | - Chi-Ren Shyu
- Institute for Data Science & Informatics, University of Missouri, Columbia, MO 65211, USA; Electrical Engineering and Computer Science Department, University of Missouri, Columbia, MO 65211, USA; Department of Medicine, School of Medicine, University of Missouri, Columbia, MO 65212, USA.
| |
Collapse
|
15
|
Bouchelouche K, Sathekge MM. Letter from the Editors. Semin Nucl Med 2021; 51:99-101. [PMID: 33509375 DOI: 10.1053/j.semnuclmed.2020.11.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
|
16
|
Slomka PJ, Moody JB, Miller RJH, Renaud JM, Ficaro EP, Garcia EV. Quantitative clinical nuclear cardiology, part 2: Evolving/emerging applications. J Nucl Cardiol 2021; 28:115-127. [PMID: 33067750 DOI: 10.1007/s12350-020-02337-4] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2020] [Accepted: 07/28/2020] [Indexed: 02/07/2023]
Abstract
Quantitative analysis has been applied extensively to image processing and interpretation in nuclear cardiology to improve disease diagnosis and risk stratification. This is Part 2 of a two-part continuing medical education article, which will review the potential clinical role for emerging quantitative analysis tools. The article will describe advanced methods for quantifying dyssynchrony, ventricular function and perfusion, and hybrid imaging analysis. This article discusses evolving methods to measure myocardial blood flow with positron emission tomography and single-photon emission computed tomography. Novel quantitative assessments of myocardial viability, microcalcification and in patients with cardiac sarcoidosis and cardiac amyloidosis will also be described. Lastly, we will review the potential role for artificial intelligence to improve image analysis, disease diagnosis, and risk prediction. The potential clinical role for all these novel techniques will be highlighted as well as methods to optimize their implementation.
Collapse
Affiliation(s)
- Piotr J Slomka
- Department of Imaging (Division of Nuclear Medicine), Medicine, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
| | | | - Robert J H Miller
- Department of Imaging (Division of Nuclear Medicine), Medicine, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, CA, USA
- Department of Cardiac Sciences, University of Calgary, Calgary, AB, Canada
| | | | - Edward P Ficaro
- INVIA Medical Imaging Solutions, Ann Arbor, MI, USA
- Division of Cardiology, Department of Internal Medicine, University of Michigan, Ann Arbor, MI, USA
| | - Ernest V Garcia
- Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA, USA
| |
Collapse
|
17
|
Slomka PJ, Moody JB, Miller RJH, Renaud JM, Ficaro EP, Garcia EV. Quantitative clinical nuclear cardiology, part 2: Evolving/emerging applications. J Nucl Med 2020; 62:168-176. [PMID: 33067339 DOI: 10.2967/jnumed.120.242537] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2020] [Accepted: 07/28/2020] [Indexed: 01/15/2023] Open
Abstract
Quantitative analysis has been applied extensively to image processing and interpretation in nuclear cardiology to improve disease diagnosis and risk stratification. This is Part 2 of a two-part continuing medical education article, which will review the potential clinical role for emerging quantitative analysis tools. The article will describe advanced methods for quantifying dyssynchrony, ventricular function and perfusion, and hybrid imaging analysis. This article discusses evolving methods to measure myocardial blood flow with positron emission tomography and single-photon emission computed tomography. Novel quantitative assessments of myocardial viability, microcalcification and in patients with cardiac sarcoidosis and cardiac amyloidosis will also be described. Lastly, we will review the potential role for artificial intelligence to improve image analysis, disease diagnosis, and risk prediction. The potential clinical role for all these novel techniques will be highlighted as well as methods to optimize their implementation. (J Nucl Cardiol 2020).
Collapse
Affiliation(s)
- Piotr J Slomka
- Department of Imaging (Division of Nuclear Medicine), Medicine, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, CA
| | | | - Robert J H Miller
- Department of Imaging (Division of Nuclear Medicine), Medicine, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, CA.,Department of Cardiac Sciences, University of Calgary, Calgary, AB, Canada
| | | | - Edward P Ficaro
- INVIA Medical Imaging Solutions, Ann Arbor, MI.,Division of Cardiology, Department of Internal Medicine, University of Michigan, Ann Arbor, MI; and
| | - Ernest V Garcia
- Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA
| |
Collapse
|
18
|
Bouchelouche K, Sathekge MM. Letter from the Editors. Semin Nucl Med 2020; 50:281-282. [PMID: 32540025 DOI: 10.1053/j.semnuclmed.2020.03.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
|