1
|
Zhang J, Dawkins A. Artificial Intelligence in Ultrasound Imaging: Where Are We Now? Ultrasound Q 2024; 40:93-97. [PMID: 38842384 DOI: 10.1097/ruq.0000000000000680] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/07/2024]
Affiliation(s)
- Jie Zhang
- From the Department of Radiology, University of Kentucky, Lexington, KY
| | | |
Collapse
|
2
|
Magboo VPC, Magboo MSA. SPECT-MPI for Coronary Artery Disease: A Deep Learning Approach. ACTA MEDICA PHILIPPINA 2024; 58:67-75. [PMID: 38812768 PMCID: PMC11132284 DOI: 10.47895/amp.vi0.7582] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 05/31/2024]
Abstract
Background Worldwide, coronary artery disease (CAD) is a leading cause of mortality and morbidity and remains to be a top health priority in many countries. A non-invasive imaging modality for diagnosis of CAD such as single photon emission computed tomography-myocardial perfusion imaging (SPECT-MPI) is usually requested by cardiologists as it displays radiotracer distribution in the heart reflecting myocardial perfusion. The interpretation of SPECT-MPI is done visually by a nuclear medicine physician and is largely dependent on his clinical experience and showing significant inter-observer variability. Objective The aim of the study is to apply a deep learning approach in the classification of SPECT-MPI for perfusion abnormalities using convolutional neural networks (CNN). Methods A publicly available anonymized SPECT-MPI from a machine learning repository (https://www.kaggle.com/selcankaplan/spect-mpi) was used in this study involving 192 patients who underwent stress-test-rest Tc99m MPI. An exploratory approach of CNN hyperparameter selection to search for optimum neural network model was utilized with particular focus on various dropouts (0.2, 0.5, 0.7), batch sizes (8, 16, 32, 64), and number of dense nodes (32, 64, 128, 256). The base CNN model was also compared with the commonly used pre-trained CNNs in medical images such as VGG16, InceptionV3, DenseNet121 and ResNet50. All simulations experiments were performed in Kaggle using TensorFlow 2.6.0., Keras 2.6.0, and Python language 3.7.10. Results The best performing base CNN model with parameters consisting of 0.7 dropout, batch size 8, and 32 dense nodes generated the highest normalized Matthews Correlation Coefficient at 0.909 and obtained 93.75% accuracy, 96.00% sensitivity, 96.00% precision, and 96.00% F1-score. It also obtained higher classification performance as compared to the pre-trained architectures. Conclusions The results suggest that deep learning approaches through the use of CNN models can be deployed by nuclear medicine physicians in their clinical practice to further augment their decision skills in the interpretation of SPECT-MPI tests. These CNN models can also be used as a dependable and valid second opinion that can aid physicians as a decision-support tool as well as serve as teaching or learning materials for the less-experienced physicians particularly those still in their training career. These highlights the clinical utility of deep learning approaches through CNN models in the practice of nuclear cardiology.
Collapse
Affiliation(s)
- Vincent Peter C Magboo
- Department of Physical Sciences and Mathematics, College of Arts and Sciences, University of the Philippines Manila
| | - Ma Sheila A Magboo
- Department of Physical Sciences and Mathematics, College of Arts and Sciences, University of the Philippines Manila
| |
Collapse
|
3
|
Gennari AG, Rossi A, De Cecco CN, van Assen M, Sartoretti T, Giannopoulos AA, Schwyzer M, Huellner MW, Messerli M. Artificial intelligence in coronary artery calcium score: rationale, different approaches, and outcomes. Int J Cardiovasc Imaging 2024; 40:951-966. [PMID: 38700819 PMCID: PMC11147943 DOI: 10.1007/s10554-024-03080-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/27/2024] [Accepted: 03/09/2024] [Indexed: 06/05/2024]
Abstract
Almost 35 years after its introduction, coronary artery calcium score (CACS) not only survived technological advances but became one of the cornerstones of contemporary cardiovascular imaging. Its simplicity and quantitative nature established it as one of the most robust approaches for atherosclerotic cardiovascular disease risk stratification in primary prevention and a powerful tool to guide therapeutic choices. Groundbreaking advances in computational models and computer power translated into a surge of artificial intelligence (AI)-based approaches directly or indirectly linked to CACS analysis. This review aims to provide essential knowledge on the AI-based techniques currently applied to CACS, setting the stage for a holistic analysis of the use of these techniques in coronary artery calcium imaging. While the focus of the review will be detailing the evidence, strengths, and limitations of end-to-end CACS algorithms in electrocardiography-gated and non-gated scans, the current role of deep-learning image reconstructions, segmentation techniques, and combined applications such as simultaneous coronary artery calcium and pulmonary nodule segmentation, will also be discussed.
Collapse
Affiliation(s)
- Antonio G Gennari
- Department of Nuclear Medicine, University Hospital Zurich, Rämistrasse 100, Zurich, 8091, Switzerland
- University of Zurich, Zurich, Switzerland
| | - Alexia Rossi
- Department of Nuclear Medicine, University Hospital Zurich, Rämistrasse 100, Zurich, 8091, Switzerland
- University of Zurich, Zurich, Switzerland
| | - Carlo N De Cecco
- Division of Cardiothoracic Imaging, Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA, USA
- Translational Laboratory for Cardiothoracic Imaging and Artificial Intelligence, Emory University, Atlanta, GA, USA
| | - Marly van Assen
- Translational Laboratory for Cardiothoracic Imaging and Artificial Intelligence, Emory University, Atlanta, GA, USA
| | - Thomas Sartoretti
- Department of Nuclear Medicine, University Hospital Zurich, Rämistrasse 100, Zurich, 8091, Switzerland
- University of Zurich, Zurich, Switzerland
| | - Andreas A Giannopoulos
- Department of Nuclear Medicine, University Hospital Zurich, Rämistrasse 100, Zurich, 8091, Switzerland
| | - Moritz Schwyzer
- Department of Nuclear Medicine, University Hospital Zurich, Rämistrasse 100, Zurich, 8091, Switzerland
- University of Zurich, Zurich, Switzerland
| | - Martin W Huellner
- Department of Nuclear Medicine, University Hospital Zurich, Rämistrasse 100, Zurich, 8091, Switzerland
- University of Zurich, Zurich, Switzerland
| | - Michael Messerli
- Department of Nuclear Medicine, University Hospital Zurich, Rämistrasse 100, Zurich, 8091, Switzerland.
- University of Zurich, Zurich, Switzerland.
| |
Collapse
|
4
|
Barris B, Karp A, Jacobs M, Frishman WH. Harnessing the Power of AI: A Comprehensive Review of Left Ventricular Ejection Fraction Assessment With Echocardiography. Cardiol Rev 2024:00045415-990000000-00237. [PMID: 38520327 DOI: 10.1097/crd.0000000000000691] [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: 03/25/2024]
Abstract
The quantification of left ventricular ejection fraction (LVEF) has important clinical utility in the assessment of cardiac function and is vital for the diagnosis of cardiovascular diseases. A transthoracic echocardiogram serves as the most commonly used tool for LVEF assessment for several reasons, including, its noninvasive nature, great safety profile, real-time image processing ability, portability, and cost-effectiveness. However, transthoracic echocardiogram is highly dependent on the clinical skill of the sonographer and interpreting physician. Moreover, even amongst well-trained clinicians, significant interobserver variability exists in the quantification of LVEF. In search of possible solutions, the usage of artificial intelligence (AI) has been increasingly tested in the clinical setting. While AI-derived ejection fraction is in the preliminary stages of development, it has shown promise in its ability to rapidly quantify LVEF, decrease variability, increase accuracy, and utilize higher-order processing capabilities. This review will delineate the latest advancements of AI in evaluating LVEF through echocardiography and explore the challenges and future trajectory of this emerging domain.
Collapse
Affiliation(s)
- Ben Barris
- From the Department of Medicine, Westchester Medical Center, Valhalla, NY
| | - Avrohom Karp
- From the Department of Medicine, Westchester Medical Center, Valhalla, NY
| | - Menachem Jacobs
- Department of Medicine, SUNY Downstate Medical Center, Brooklyn, NY
| | - William H Frishman
- From the Department of Medicine, Westchester Medical Center, Valhalla, NY
| |
Collapse
|
5
|
Khenkina N, Aimo A, Fabiani I, Masci PG, Sagris D, Williams SE, Mavraganis G, Chen HS, Wintermark M, Michel P, Ntaios G, Georgiopoulos G. Magnetic resonance imaging for diagnostic workup of embolic stroke of undetermined source: A systematic review. Int J Stroke 2024; 19:293-304. [PMID: 37435743 DOI: 10.1177/17474930231189946] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/13/2023]
Abstract
BACKGROUND Embolic stroke of undetermined source (ESUS) refers to ischemic stroke where the underlying cause of thromboembolism cannot be found despite the recommended diagnostic workup. Unidentified source of emboli hinders clinical decision-making and patient management with detrimental consequences on long-term prognosis. The rapid development and versatility of magnetic resonance imaging (MRI) make it an appealing addition to the diagnostic routine of patients with ESUS for the assessment of potential vascular and cardiac embolic sources. AIMS To review the use of MRI in the identification of cardiac and vascular embolic sources in ESUS and to assess the reclassification value of MRI examinations added to the conventional workup of ESUS. SUMMARY OF REVIEW We reviewed the use of cardiac and vascular MRI for the identification of a variety of embolic sources associated with ESUS, including atrial cardiomyopathy, left ventricular pathologies, and supracervical atherosclerosis in carotid and intracranial arteries and in distal thoracic aorta. The additional reclassification after MRI examinations added to the workup of patients with ESUS ranged from 6.1% to 82.3% and varied depending on the combination of imaging modalities. CONCLUSION MRI techniques allow us to identify additional cardiac and vascular embolic sources and may further decrease the prevalence of patients with the diagnosis of ESUS.
Collapse
Affiliation(s)
- Natallia Khenkina
- Postgraduate School of Diagnostic and Interventional Radiology, University of Milan, Milan, Italy
| | - Alberto Aimo
- Institute of Life Sciences, Scuola Superiore Sant'Anna, Pisa, Italy
- Cardiology Division, Fondazione Toscana Gabriele Monasterio, Pisa, Italy
| | - Iacopo Fabiani
- Cardiology Division, Fondazione Toscana Gabriele Monasterio, Pisa, Italy
| | - Pier Giorgio Masci
- School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK
| | - Dimitrios Sagris
- Liverpool Centre of Cardiovascular Sciences, University of Liverpool, Liverpool, UK
| | | | - George Mavraganis
- Department of Clinical Therapeutics, National and Kapodistrian University of Athens, Athens, Greece
| | - Hui-Sheng Chen
- Department of Neurology, General Hospital of Northern Theater Command, Shenyang, China
| | - Max Wintermark
- Department of Radiology, Stanford University, Stanford, CA, USA
| | - Patrik Michel
- Stroke Center, Neurology Service, Department of Clinical Neurosciences, Lausanne University Hospital, Lausanne, Switzerland
| | - George Ntaios
- Department of Internal Medicine, Faculty of Medicine, School of Health Sciences, University of Thessaly, Larissa, Greece
| | - Georgios Georgiopoulos
- School of Biomedical Engineering & Imaging Sciences, King's College London, London, UK
- Department of Clinical Therapeutics, National and Kapodistrian University of Athens, Athens, Greece
| |
Collapse
|
6
|
Cau R, Pisu F, Suri JS, Montisci R, Gatti M, Mannelli L, Gong X, Saba L. Artificial Intelligence in the Differential Diagnosis of Cardiomyopathy Phenotypes. Diagnostics (Basel) 2024; 14:156. [PMID: 38248033 PMCID: PMC11154548 DOI: 10.3390/diagnostics14020156] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/12/2023] [Revised: 01/03/2024] [Accepted: 01/08/2024] [Indexed: 01/23/2024] Open
Abstract
Artificial intelligence (AI) is rapidly being applied to the medical field, especially in the cardiovascular domain. AI approaches have demonstrated their applicability in the detection, diagnosis, and management of several cardiovascular diseases, enhancing disease stratification and typing. Cardiomyopathies are a leading cause of heart failure and life-threatening ventricular arrhythmias. Identifying the etiologies is fundamental for the management and diagnostic pathway of these heart muscle diseases, requiring the integration of various data, including personal and family history, clinical examination, electrocardiography, and laboratory investigations, as well as multimodality imaging, making the clinical diagnosis challenging. In this scenario, AI has demonstrated its capability to capture subtle connections from a multitude of multiparametric datasets, enabling the discovery of hidden relationships in data and handling more complex tasks than traditional methods. This review aims to present a comprehensive overview of the main concepts related to AI and its subset. Additionally, we review the existing literature on AI-based models in the differential diagnosis of cardiomyopathy phenotypes, and we finally examine the advantages and limitations of these AI approaches.
Collapse
Affiliation(s)
- Riccardo Cau
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), di Cagliari-Polo di Monserrato s.s. 554 Monserrato, 09045 Cagliari, Italy; (R.C.); (F.P.)
| | - Francesco Pisu
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), di Cagliari-Polo di Monserrato s.s. 554 Monserrato, 09045 Cagliari, Italy; (R.C.); (F.P.)
| | - Jasjit S. Suri
- Stroke Monitoring and Diagnostic Division, AtheroPoin™, Roseville, CA 95661, USA;
| | - Roberta Montisci
- Department of Cardiology, Azienda Ospedaliero Universitaria (A.O.U.), di Cagliari-Polo di Monserrato s.s. 554 Monserrato, 09045 Cagliari, Italy;
| | - Marco Gatti
- Department of Radiology, Università degli Studi di Torino, 10129 Turin, Italy;
| | | | - Xiangyang Gong
- Radiology Department, Zhejiang Provincial People’s Hospital, Affiliated People’s Hospital, Hangzhou Medical College, Hangzhou 310014, China;
| | - Luca Saba
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), di Cagliari-Polo di Monserrato s.s. 554 Monserrato, 09045 Cagliari, Italy; (R.C.); (F.P.)
| |
Collapse
|
7
|
Saba L, Scicolone R, Johansson E, Nardi V, Lanzino G, Kakkos SK, Pontone G, Annoni AD, Paraskevas KI, Fox AJ. Quantifying Carotid Stenosis: History, Current Applications, Limitations, and Potential: How Imaging Is Changing the Scenario. Life (Basel) 2024; 14:73. [PMID: 38255688 PMCID: PMC10821425 DOI: 10.3390/life14010073] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/05/2023] [Revised: 12/24/2023] [Accepted: 12/29/2023] [Indexed: 01/24/2024] Open
Abstract
Carotid artery stenosis is a major cause of morbidity and mortality. The journey to understanding carotid disease has developed over time and radiology has a pivotal role in diagnosis, risk stratification and therapeutic management. This paper reviews the history of diagnostic imaging in carotid disease, its evolution towards its current applications in the clinical and research fields, and the potential of new technologies to aid clinicians in identifying the disease and tailoring medical and surgical treatment.
Collapse
Affiliation(s)
- Luca Saba
- Department of Radiology, University of Cagliari, 09042 Cagliari, Italy;
| | - Roberta Scicolone
- Department of Radiology, University of Cagliari, 09042 Cagliari, Italy;
| | - Elias Johansson
- Neuroscience and Physiology, Sahlgrenska Academy, 41390 Gothenburg, Sweden;
| | - Valentina Nardi
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN 55905, USA;
| | - Giuseppe Lanzino
- Department of Neurologic Surgery, Mayo Clinic, Rochester, MN 55905, USA;
| | - Stavros K. Kakkos
- Department of Vascular Surgery, University of Patras, 26504 Patras, Greece;
| | - Gianluca Pontone
- Centro Cardiologico Monzino IRCCS, Via C. Parea 4, 20138 Milan, Italy; (G.P.); (A.D.A.)
- Department of Biomedical, Surgical and Dental Sciences, University of Milan, 20122 Milan, Italy
| | - Andrea D. Annoni
- Centro Cardiologico Monzino IRCCS, Via C. Parea 4, 20138 Milan, Italy; (G.P.); (A.D.A.)
| | | | - Allan J. Fox
- Department of Medical Imaging, Neuroradiology Section, Sunnybrook Health Sciences Centre, University of Toronto, Toronto, ON M4N 3M5, Canada;
| |
Collapse
|
8
|
Perone F, Bernardi M, Redheuil A, Mafrica D, Conte E, Spadafora L, Ecarnot F, Tokgozoglu L, Santos-Gallego CG, Kaiser SE, Fogacci F, Sabouret A, Bhatt DL, Paneni F, Banach M, Santos R, Biondi Zoccai G, Ray KK, Sabouret P. Role of Cardiovascular Imaging in Risk Assessment: Recent Advances, Gaps in Evidence, and Future Directions. J Clin Med 2023; 12:5563. [PMID: 37685628 PMCID: PMC10487991 DOI: 10.3390/jcm12175563] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2023] [Revised: 08/14/2023] [Accepted: 08/23/2023] [Indexed: 09/10/2023] Open
Abstract
Optimal risk assessment for primary prevention remains highly challenging. Recent registries have highlighted major discrepancies between guidelines and daily practice. Although guidelines have improved over time and provide updated risk scores, they still fail to identify a significant proportion of at-risk individuals, who then miss out on effective prevention measures until their initial ischemic events. Cardiovascular imaging is progressively assuming an increasingly pivotal role, playing a crucial part in enhancing the meticulous categorization of individuals according to their risk profiles, thus enabling the customization of precise therapeutic strategies for patients with increased cardiovascular risks. For the most part, the current approach to patients with atherosclerotic cardiovascular disease (ASCVD) is homogeneous. However, data from registries (e.g., REACH, CORONOR) and randomized clinical trials (e.g., COMPASS, FOURIER, and ODYSSEY outcomes) highlight heterogeneity in the risks of recurrent ischemic events, which are especially higher in patients with poly-vascular disease and/or multivessel coronary disease. This indicates the need for a more individualized strategy and further research to improve definitions of individual residual risk, with a view of intensifying treatments in the subgroups with very high residual risk. In this narrative review, we discuss advances in cardiovascular imaging, its current place in the guidelines, the gaps in evidence, and perspectives for primary and secondary prevention to improve risk assessment and therapeutic strategies using cardiovascular imaging.
Collapse
Affiliation(s)
- Francesco Perone
- Cardiac Rehabilitation Unit, Rehabilitation Clinic “Villa delle Magnolie”, Castel Morrone, 81020 Caserta, Italy;
| | - Marco Bernardi
- Department of Clinical, Internal Medicine, Anesthesiology and Cardiovascular Sciences, Sapienza University of Rome, 00185 Rome, Italy; (M.B.); (D.M.); (L.S.)
| | - Alban Redheuil
- Laboratoire d’Imagerie Biomédicale, Sorbonne University, INSERM 1146, CNRS 7371, 75005 Paris, France;
| | - Dario Mafrica
- Department of Clinical, Internal Medicine, Anesthesiology and Cardiovascular Sciences, Sapienza University of Rome, 00185 Rome, Italy; (M.B.); (D.M.); (L.S.)
| | - Edoardo Conte
- Cardiology Department, Galeazzi-Sant’Ambrogio Hospital IRCCS, 20100 Milan, Italy;
| | - Luigi Spadafora
- Department of Clinical, Internal Medicine, Anesthesiology and Cardiovascular Sciences, Sapienza University of Rome, 00185 Rome, Italy; (M.B.); (D.M.); (L.S.)
| | - Fiona Ecarnot
- Department of Cardiology, University Hospital Besancon, University of Franche-Comté, 25000 Besancon, France;
| | - Lale Tokgozoglu
- Department of Cardiology, Medical Faculty, Hacettepe University, 06230 Ankara, Turkey;
| | - Carlos G. Santos-Gallego
- Atherothrombosis Research Unit, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA;
- Mount Sinai Heart, Icahn School of Medicine at Mount Sinai Health System, New York, NY 10029, USA;
| | - Sergio Emanuel Kaiser
- Discipline of Clinical and Experimental Pathophysiology, Rio de Janeiro State University, Rio de Janeiro 23070-200, Brazil;
| | - Federica Fogacci
- Hypertension and Cardiovascular Risk Research Group, Medical and Surgical Sciences Department, Alma Mater Studiorum University of Bologna, 40126 Bologna, Italy;
| | | | - Deepak L. Bhatt
- Mount Sinai Heart, Icahn School of Medicine at Mount Sinai Health System, New York, NY 10029, USA;
| | - Francesco Paneni
- Department of Cardiology, University Heart Center, University Hospital Zurich, 8091 Zurich, Switzerland;
- Center for Translational and Experimental Cardiology (CTEC), University Hospital Zurich and University of Zurich, 8091 Zurich, Switzerland
| | - Maciej Banach
- Department of Preventive Cardiology and Lipidology, Medical University of Lodz (MUL), Rzgowska 281/289, 93-338 Lodz, Poland;
- Cardiovascular Research Centre, University of Zielona Gora, 65-417 Zielona Gora, Poland
| | - Raul Santos
- Heart Institute, University of Sao Paulo Medical School, São Paulo 05403-903, Brazil;
| | - Giuseppe Biondi Zoccai
- Department of Medical-Surgical Sciences and Biotechnologies, Sapienza University of Rome, 00185 Roma, Italy;
- Mediterranea Cardiocentro, 80122 Napoli, Italy
| | - Kausik K. Ray
- Imperial Centre for Cardiovascular Disease Prevention and Imperial Clinical Trials Unit, Department of Public Health and Primary Care, Imperial College London, London SW7 2BX, UK;
| | - Pierre Sabouret
- Heart Institute, Cardiology Department, Paris and National College of French Cardiologists, Pitié-Salpétrière Hospital, Sorbonne University, 75013 Paris, France
| |
Collapse
|
9
|
Cau R, Pisu F, Suri JS, Mannelli L, Scaglione M, Masala S, Saba L. Artificial Intelligence Applications in Cardiovascular Magnetic Resonance Imaging: Are We on the Path to Avoiding the Administration of Contrast Media? Diagnostics (Basel) 2023; 13:2061. [PMID: 37370956 PMCID: PMC10297403 DOI: 10.3390/diagnostics13122061] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2023] [Revised: 06/10/2023] [Accepted: 06/12/2023] [Indexed: 06/29/2023] Open
Abstract
In recent years, cardiovascular imaging examinations have experienced exponential growth due to technological innovation, and this trend is consistent with the most recent chest pain guidelines. Contrast media have a crucial role in cardiovascular magnetic resonance (CMR) imaging, allowing for more precise characterization of different cardiovascular diseases. However, contrast media have contraindications and side effects that limit their clinical application in determinant patients. The application of artificial intelligence (AI)-based techniques to CMR imaging has led to the development of non-contrast models. These AI models utilize non-contrast imaging data, either independently or in combination with clinical and demographic data, as input to generate diagnostic or prognostic algorithms. In this review, we provide an overview of the main concepts pertaining to AI, review the existing literature on non-contrast AI models in CMR, and finally, discuss the strengths and limitations of these AI models and their possible future development.
Collapse
Affiliation(s)
- Riccardo Cau
- Department of Radiology, University Hospital of Cagliari, 09042 Monserrato, Italy; (R.C.); (F.P.)
| | - Francesco Pisu
- Department of Radiology, University Hospital of Cagliari, 09042 Monserrato, Italy; (R.C.); (F.P.)
| | - Jasjit S. Suri
- Stroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA 95661, USA;
| | | | - Mariano Scaglione
- Department of Radiology, University Hospital of Sassari, 07100 Sassari, Italy; (M.S.); (S.M.)
| | - Salvatore Masala
- Department of Radiology, University Hospital of Sassari, 07100 Sassari, Italy; (M.S.); (S.M.)
| | - Luca Saba
- Department of Radiology, University Hospital of Cagliari, 09042 Monserrato, Italy; (R.C.); (F.P.)
| |
Collapse
|
10
|
Tore D, Faletti R, Gaetani C, Bozzo E, Biondo A, Carisio A, Menchini F, Miccolis M, Papa FP, Trovato M, Fonio P, Gatti M. Cardiac magnetic resonance of hypertrophic heart phenotype: A review. Heliyon 2023; 9:e17336. [PMID: 37441401 PMCID: PMC10333467 DOI: 10.1016/j.heliyon.2023.e17336] [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: 12/31/2022] [Revised: 06/05/2023] [Accepted: 06/14/2023] [Indexed: 07/15/2023] Open
Abstract
Hypertrophic heart phenotype is characterized by an abnormal left ventricular (LV) thickening. A hypertrophic phenotype can develop as adaptive response in many different conditions such as aortic stenosis, hypertension, athletic training, infiltrative heart muscle diseases, storage disorders and metabolic disorders. Hypertrophic cardiomyopathy (HCM) is the most frequent primary cardiomyopathy (CMP) and a genetical cause of cardiac hypertrophy. It requires the exclusion of any other cause of LV hypertrophy. Cardiac magnetic resonance (CMR) is a comprehensive imaging technique that allows a detailed evaluation of myocardial diseases. It provides reproducible measurements and myocardial tissue characterization. In clinical practice CMR is increasingly used to confirm the presence of ventricular hypertrophy, to detect the underlying cause of the phenotype and more recently as an efficient prognostic tool. This article aims to provide a detailed overview of the applications of CMR in the setting of hypertrophic heart phenotype and its role in the diagnostic workflow of such condition.
Collapse
Affiliation(s)
- Davide Tore
- Radiology Unit, Department of Surgical Sciences, AOU Città della Salute e della Scienza di Torino, University of Turin, Turin, Italy
| | - Riccardo Faletti
- Radiology Unit, Department of Surgical Sciences, AOU Città della Salute e della Scienza di Torino, University of Turin, Turin, Italy
| | - Clara Gaetani
- Radiology Unit, Department of Surgical Sciences, AOU Città della Salute e della Scienza di Torino, University of Turin, Turin, Italy
| | - Elena Bozzo
- Radiology Unit, Department of Surgical Sciences, AOU Città della Salute e della Scienza di Torino, University of Turin, Turin, Italy
| | - Andrea Biondo
- Radiology Unit, Department of Surgical Sciences, AOU Città della Salute e della Scienza di Torino, University of Turin, Turin, Italy
| | - Andrea Carisio
- Radiology Unit, Department of Surgical Sciences, AOU Città della Salute e della Scienza di Torino, University of Turin, Turin, Italy
| | - Francesca Menchini
- Radiology Unit, Department of Surgical Sciences, AOU Città della Salute e della Scienza di Torino, University of Turin, Turin, Italy
| | - Maria Miccolis
- Radiology Unit, Department of Surgical Sciences, AOU Città della Salute e della Scienza di Torino, University of Turin, Turin, Italy
| | - Francesco Pio Papa
- Radiology Unit, Department of Surgical Sciences, AOU Città della Salute e della Scienza di Torino, University of Turin, Turin, Italy
| | - Martina Trovato
- Radiology Unit, Department of Surgical Sciences, AOU Città della Salute e della Scienza di Torino, University of Turin, Turin, Italy
| | - Paolo Fonio
- Radiology Unit, Department of Surgical Sciences, AOU Città della Salute e della Scienza di Torino, University of Turin, Turin, Italy
| | - Marco Gatti
- Radiology Unit, Department of Surgical Sciences, AOU Città della Salute e della Scienza di Torino, University of Turin, Turin, Italy
| |
Collapse
|
11
|
Cau R, Pisu F, Porcu M, Cademartiri F, Montisci R, Bassareo P, Muscogiuri G, Amadu A, Sironi S, Esposito A, Suri JS, Saba L. Machine learning approach in diagnosing Takotsubo cardiomyopathy: The role of the combined evaluation of atrial and ventricular strain, and parametric mapping. Int J Cardiol 2023; 373:124-133. [PMID: 36410545 DOI: 10.1016/j.ijcard.2022.11.021] [Citation(s) in RCA: 13] [Impact Index Per Article: 13.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/27/2022] [Revised: 10/23/2022] [Accepted: 11/15/2022] [Indexed: 11/19/2022]
Abstract
BACKGROUND Cardiac magnetic resonance (CMR) with late gadolinium enhancement (LGE) is a key diagnostic tool in the differential diagnosis between non-ischemic cause of cardiac chest pain. Some patients are not eligible for a gadolinium contrast-enhanced CMR; in this scenario, the diagnosis remains challenging without invasive examination. Our purpose was to derive a machine learning model integrating some non-contrast CMR parameters and demographic factors to identify Takotsubo cardiomyopathy (TTC) in subjects with cardiac chest pain. MATERIAL AND METHODS Three groups of patients were retrospectively studied: TTC, acute myocarditis, and healthy controls. Global and regional left ventricular longitudinal, circumferential, and radial strain (RS) analysis included were assessed. Reservoir, conduit, and booster bi-atrial functions were evaluated by tissue-tracking. Parametric mapping values were also assessed in all the patients. Five different tree-based ensemble learning algorithms were tested concerning their ability in recognizing TTC in a fully cross-validated framework. RESULTS The CMR-based machine learning (ML) ensemble model, by using the Extremely Randomized Trees algorithm with Elastic Net feature selection, showed a sensitivity of 92% (95% CI 78-100), specificity of 86% (95% CI 80-92) and area under the ROC of 0.94 (95% CI 0.90-0.99) in diagnosing TTC. Among non-contrast CMR parameters, the Shapley additive explanations analysis revealed that left atrial (LA) strain and strain rate were the top imaging markers in identifying TTC patients. CONCLUSIONS Our study demonstrated that using a tree-based ensemble learning algorithm on non-contrast CMR parameters and demographic factors enables the identification of subjects with TTC with good diagnostic accuracy. TRANSLATIONAL OUTLOOK Our results suggest that non-contrast CMR features can be implemented in a ML model to accurately identify TTC subjects. This model could be a valuable tool for aiding in the diagnosis of subjects with a contraindication to the contrast media. Furthermore, the left atrial conduit strain and strain rate were imaging markers that had a strong impact on TTC identification. Further prospective and longitudinal studies are needed to validate these findings and assess predictive performance in different cohorts, such as those with different ethnicities, and social backgrounds and undergoing different treatments.
Collapse
Affiliation(s)
- Riccardo Cau
- Department of Radiology, Azienda Ospedaliero Universitaria, Monserrato (Cagliari), Italy
| | - Francesco Pisu
- Department of Radiology, Azienda Ospedaliero Universitaria, Monserrato (Cagliari), Italy
| | - Michele Porcu
- Department of Radiology, Azienda Ospedaliero Universitaria, Monserrato (Cagliari), Italy
| | | | - Roberta Montisci
- Department of Cardiology, Azienda Ospedaliero Universitaria, Monserrato (Cagliari), Italy
| | - Pierpaolo Bassareo
- University College of Dublin, Mater Misericordiae University Hospital and Our Lady's Children's Hospital, Crumlin, Dublin, Ireland
| | - Giuseppe Muscogiuri
- Department of Radiology, IRCCS Istituto Auxologico Italiano, San Luca Hospital, Milan, Italy; University Milano Bicocca, Italy
| | | | - Sandro Sironi
- Department of Radiology, University of Milan-Bicocca, Milan, Italy
| | | | - Jasjit S Suri
- Stroke Monitoring and Diagnosis Division, AtheroPoint(tm) Roseville, CA, USA
| | - Luca Saba
- Department of Radiology, Azienda Ospedaliero Universitaria, Monserrato (Cagliari), Italy.
| |
Collapse
|