1
|
Seetharam K, Thyagaturu H, Ferreira GL, Patel A, Patel C, Elahi A, Pachulski R, Shah J, Mir P, Thodimela A, Pala M, Thet Z, Hamirani Y. Broadening Perspectives of Artificial Intelligence in Echocardiography. Cardiol Ther 2024; 13:267-279. [PMID: 38703292 PMCID: PMC11093957 DOI: 10.1007/s40119-024-00368-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/13/2023] [Accepted: 04/11/2024] [Indexed: 05/06/2024] Open
Abstract
Echocardiography frequently serves as the first-line treatment of diagnostic imaging for several pathological entities in cardiology. Artificial intelligence (AI) has been growing substantially in information technology and various commercial industries. Machine learning (ML), a branch of AI, has been shown to expand the capabilities and potential of echocardiography. ML algorithms expand the field of echocardiography by automated assessment of the ejection fraction and left ventricular function, integrating novel approaches such as speckle tracking or tissue Doppler echocardiography or vector flow mapping, improved phenotyping, distinguishing between cardiac conditions, and incorporating information from mobile health and genomics. In this review article, we assess the impact of AI and ML in echocardiography.
Collapse
Affiliation(s)
- Karthik Seetharam
- Division of Cardiovascular Disease, West Virgina University, Heart and Vascular Institute, 1 Medical Center Drive, Morgantown, WV, 26506, USA.
- Wyckoff Heights Medical Center, Brooklyn, NY, USA.
| | - Harshith Thyagaturu
- Division of Cardiovascular Disease, West Virgina University, Heart and Vascular Institute, 1 Medical Center Drive, Morgantown, WV, 26506, USA
| | | | - Aditya Patel
- Wyckoff Heights Medical Center, Brooklyn, NY, USA
| | - Chinmay Patel
- University of Pittsburg Medical Center, Harrisburg, PA, USA
| | - Asim Elahi
- Wyckoff Heights Medical Center, Brooklyn, NY, USA
| | - Roman Pachulski
- St. John's Episcopal Hospital - South Shore, New York, NY, USA
| | - Jilan Shah
- Wyckoff Heights Medical Center, Brooklyn, NY, USA
| | - Parvez Mir
- Wyckoff Heights Medical Center, Brooklyn, NY, USA
| | | | - Manya Pala
- Wyckoff Heights Medical Center, Brooklyn, NY, USA
| | - Zeyar Thet
- Wyckoff Heights Medical Center, Brooklyn, NY, USA
| | - Yasmin Hamirani
- Robert Woods Johnson University Hospital/Rutgers University, New Brusnwick, NJ, USA
| |
Collapse
|
2
|
Alajrami E, Ng T, Jevsikov J, Naidoo P, Fernandes P, Azarmehr N, Dinmohammadi F, Shun-Shin MJ, Dadashi Serej N, Francis DP, Zolgharni M. Active learning for left ventricle segmentation in echocardiography. Comput Methods Programs Biomed 2024; 248:108111. [PMID: 38479147 DOI: 10.1016/j.cmpb.2024.108111] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/29/2023] [Revised: 02/21/2024] [Accepted: 03/01/2024] [Indexed: 04/02/2024]
Abstract
BACKGROUND AND OBJECTIVE Training deep learning models for medical image segmentation require large annotated datasets, which can be expensive and time-consuming to create. Active learning is a promising approach to reduce this burden by strategically selecting the most informative samples for segmentation. This study investigates the use of active learning for efficient left ventricle segmentation in echocardiography with sparse expert annotations. METHODS We adapt and evaluate various sampling techniques, demonstrating their effectiveness in judiciously selecting samples for segmentation. Additionally, we introduce a novel strategy, Optimised Representativeness Sampling, which combines feature-based outliers with the most representative samples to enhance annotation efficiency. RESULTS Our findings demonstrate a substantial reduction in annotation costs, achieving a remarkable 99% upper bound performance while utilising only 20% of the labelled data. This equates to a reduction of 1680 images needing annotation within our dataset. When applied to a publicly available dataset, our approach yielded a remarkable 70% reduction in required annotation efforts, representing a significant advancement compared to baseline active learning strategies, which achieved only a 50% reduction. Our experiments highlight the nuanced performance of diverse sampling strategies across datasets within the same domain. CONCLUSIONS The study provides a cost-effective approach to tackle the challenges of limited expert annotations in echocardiography. By introducing a distinct dataset, made publicly available for research purposes, our work contributes to the field's understanding of efficient annotation strategies in medical image segmentation.
Collapse
Affiliation(s)
- Eman Alajrami
- Intelligent Sensing and Vision, University of West London, London, UK.
| | - Tiffany Ng
- National Heart and Lung Institute, Imperial College London, London, UK
| | - Jevgeni Jevsikov
- Intelligent Sensing and Vision, University of West London, London, UK; National Heart and Lung Institute, Imperial College London, London, UK
| | - Preshen Naidoo
- Intelligent Sensing and Vision, University of West London, London, UK
| | | | - Neda Azarmehr
- Intelligent Sensing and Vision, University of West London, London, UK
| | | | | | | | - Darrel P Francis
- National Heart and Lung Institute, Imperial College London, London, UK
| | - Massoud Zolgharni
- Intelligent Sensing and Vision, University of West London, London, UK; National Heart and Lung Institute, Imperial College London, London, UK
| |
Collapse
|
3
|
Stowell CC, Kallassy V, Lane B, Abbott J, Borgeat K, Connolly D, Domenech O, Dukes‐McEwan J, Ferasin L, Del Palacio JF, Linney C, Matos JN, Spalla I, Summerfield N, Vezzosi T, Howard JP, Shun‐Shin MJ, Francis DP, Fuentes VL. Automated echocardiographic left ventricular dimension assessment in dogs using artificial intelligence: Development and validation. J Vet Intern Med 2024; 38:922-930. [PMID: 38362960 PMCID: PMC10937473 DOI: 10.1111/jvim.17012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/27/2023] [Accepted: 01/26/2024] [Indexed: 02/17/2024] Open
Abstract
BACKGROUND Artificial intelligence (AI) could improve accuracy and reproducibility of echocardiographic measurements in dogs. HYPOTHESIS A neural network can be trained to measure echocardiographic left ventricular (LV) linear dimensions in dogs. ANIMALS Training dataset: 1398 frames from 461 canine echocardiograms from a single specialist center. VALIDATION 50 additional echocardiograms from the same center. METHODS Training dataset: a right parasternal 4-chamber long axis frame from each study, labeled by 1 of 18 echocardiographers, marking anterior and posterior points of the septum and free wall. VALIDATION DATASET End-diastolic and end-systolic frames from 50 studies, annotated twice (blindly) by 13 experts, producing 26 measurements of each site from each frame. The neural network also made these measurements. We quantified its accuracy as the deviation from the expert consensus, using the individual-expert deviation from consensus as context for acceptable variation. The deviation of the AI measurement away from the expert consensus was assessed on each individual frame and compared with the root-mean-square-variation of the individual expert opinions away from that consensus. RESULTS For the septum in end-diastole, individual expert opinions deviated by 0.12 cm from the consensus, while the AI deviated by 0.11 cm (P = .61). For LVD, the corresponding values were 0.20 cm for experts and 0.13 cm for AI (P = .65); for the free wall, experts 0.20 cm, AI 0.13 cm (P < .01). In end-systole, there were no differences between individual expert and AI performances. CONCLUSIONS AND CLINICAL IMPORTANCE An artificial intelligence network can be trained to adequately measure linear LV dimensions, with performance indistinguishable from that of experts.
Collapse
Affiliation(s)
| | | | - Beth Lane
- National Heart and Lung Institute (NHLI)Imperial CollegeLondonUK
| | - Jonathan Abbott
- Department of Small Animal Clinical Sciences, College of Veterinary MedicineUniversity of TennesseeKnoxvilleTennesseeUSA
| | - Kieran Borgeat
- Department of CardiologyEastcott Veterinary ReferralsSwindonUK
| | - David Connolly
- Clinical Science and ServicesRoyal Veterinary CollegeLondonUK
| | - Oriol Domenech
- Cardiology DepartmentIstituto Veterinario di NovaraNovaraItaly
| | - Joanna Dukes‐McEwan
- Department of Small Animal Clinical Science, School of Veterinary ScienceUniversity of LiverpoolLiverpoolUK
| | - Luca Ferasin
- Specialist Veterinary Cardiology ConsultancyFour MarksNewburyUK
| | | | - Chris Linney
- Cardiology DepartmentParagon Veterinary ReferralsWakefieldUK
| | - Jose Novo Matos
- Department of Veterinary MedicineUniversity of CambridgeCambridgeUK
| | - Ilaria Spalla
- Cardiology DepartmentOspedale Veterinario San FrancescoMilanItaly
| | | | - Tommaso Vezzosi
- Department of Veterinary SciencesUniversity of PisaPisaItaly
| | - James P. Howard
- National Heart and Lung Institute (NHLI)Imperial CollegeLondonUK
| | | | | | | |
Collapse
|
4
|
Zamzmi G, Hsu LY, Rajaraman S, Li W, Sachdev V, Antani S. Evaluation of an artificial intelligence-based system for echocardiographic estimation of right atrial pressure. Int J Cardiovasc Imaging 2023; 39:2437-2450. [PMID: 37682418 PMCID: PMC10692014 DOI: 10.1007/s10554-023-02941-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/06/2023] [Accepted: 08/18/2023] [Indexed: 09/09/2023]
Abstract
Current noninvasive estimation of right atrial pressure (RAP) by inferior vena cava (IVC) measurement during echocardiography may have significant inter-rater variability due to different levels of observers' experience. Therefore, there is a need to develop new approaches to decrease the variability of IVC analysis and RAP estimation. This study aims to develop a fully automated artificial intelligence (AI)-based system for automated IVC analysis and RAP estimation. We presented a multi-stage AI system to identify the IVC view, select good quality images, delineate the IVC region and quantify its thickness, enabling temporal tracking of its diameter and collapsibility changes. The automated system was trained and tested on expert manual IVC and RAP reference measurements obtained from 255 patients during routine clinical workflow. The performance was evaluated using Pearson correlation and Bland-Altman analysis for IVC values, as well as macro accuracy and chi-square test for RAP values. Our results show an excellent agreement (r=0.96) between automatically computed versus manually measured IVC values, and Bland-Altman analysis showed a small bias of [Formula: see text]0.33 mm. Further, there is an excellent agreement ([Formula: see text]) between automatically estimated versus manually derived RAP values with a macro accuracy of 0.85. The proposed AI-based system accurately quantified IVC diameter, collapsibility index, both are used for RAP estimation. This automated system could serve as a paradigm to perform IVC analysis in routine echocardiography and support various cardiac diagnostic applications.
Collapse
Affiliation(s)
- Ghada Zamzmi
- National Library of Medicine, National Institutes of Health, 8600 Rockville Pike, Bethesda, MD, 20894, USA
| | - Li-Yueh Hsu
- Clinical Center, National Institutes of Health, 10 Center Dr, Bethesda, MD, 20892, USA.
| | - Sivaramakrishnan Rajaraman
- National Library of Medicine, National Institutes of Health, 8600 Rockville Pike, Bethesda, MD, 20894, USA
| | - Wen Li
- National Heart, Lung, and Blood Institute, National Institutes of Health, 9000 Rockville Pike, Bethesda, MD, 20892, USA
| | - Vandana Sachdev
- National Heart, Lung, and Blood Institute, National Institutes of Health, 9000 Rockville Pike, Bethesda, MD, 20892, USA
| | - Sameer Antani
- National Library of Medicine, National Institutes of Health, 8600 Rockville Pike, Bethesda, MD, 20894, USA.
| |
Collapse
|
5
|
Wehbe RM, Katsaggelos AK, Hammond KJ, Hong H, Ahmad FS, Ouyang D, Shah SJ, McCarthy PM, Thomas JD. Deep Learning for Cardiovascular Imaging: A Review. JAMA Cardiol 2023; 8:1089-1098. [PMID: 37728933 DOI: 10.1001/jamacardio.2023.3142] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 09/22/2023]
Abstract
Importance Artificial intelligence (AI), driven by advances in deep learning (DL), has the potential to reshape the field of cardiovascular imaging (CVI). While DL for CVI is still in its infancy, research is accelerating to aid in the acquisition, processing, and/or interpretation of CVI across various modalities, with several commercial products already in clinical use. It is imperative that cardiovascular imagers are familiar with DL systems, including a basic understanding of how they work, their relative strengths compared with other automated systems, and possible pitfalls in their implementation. The goal of this article is to review the methodology and application of DL to CVI in a simple, digestible fashion toward demystifying this emerging technology. Observations At its core, DL is simply the application of a series of tunable mathematical operations that translate input data into a desired output. Based on artificial neural networks that are inspired by the human nervous system, there are several types of DL architectures suited to different tasks; convolutional neural networks are particularly adept at extracting valuable information from CVI data. We survey some of the notable applications of DL to tasks across the spectrum of CVI modalities. We also discuss challenges in the development and implementation of DL systems, including avoiding overfitting, preventing systematic bias, improving explainability, and fostering a human-machine partnership. Finally, we conclude with a vision of the future of DL for CVI. Conclusions and Relevance Deep learning has the potential to meaningfully affect the field of CVI. Rather than a threat, DL could be seen as a partner to cardiovascular imagers in reducing technical burden and improving efficiency and quality of care. High-quality prospective evidence is still needed to demonstrate how the benefits of DL CVI systems may outweigh the risks.
Collapse
Affiliation(s)
- Ramsey M Wehbe
- Division of Cardiology, Department of Medicine & Biomedical Informatics Center, Medical University of South Carolina, Charleston
- Division of Cardiology, Department of Medicine, Northwestern University Feinberg School of Medicine, Chicago, Illinois
| | - Aggelos K Katsaggelos
- Department of Computer and Electrical Engineering, Northwestern University, Evanston, Illinois
| | - Kristian J Hammond
- Department of Computer Science, Northwestern University, Evanston, Illinois
| | - Ha Hong
- Medtronic, Minneapolis, Minnesota
| | - Faraz S Ahmad
- Division of Cardiology, Department of Medicine, Northwestern University Feinberg School of Medicine, Chicago, Illinois
- Center for Health Information Partnerships, Institute for Public Health and Medicine, Northwestern University Feinberg School of Medicine, Chicago, Illinois
- Center for Artificial Intelligence, Northwestern Medicine Bluhm Cardiovascular Institute, Chicago, Illinois
| | - David Ouyang
- Division of Cardiology, Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, California
| | - Sanjiv J Shah
- Division of Cardiology, Department of Medicine, Northwestern University Feinberg School of Medicine, Chicago, Illinois
- Center for Artificial Intelligence, Northwestern Medicine Bluhm Cardiovascular Institute, Chicago, Illinois
| | - Patrick M McCarthy
- Division of Cardiac Surgery, Department of Surgery, Northwestern University Feinberg School of Medicine, Chicago, Illinois
- Center for Artificial Intelligence, Northwestern Medicine Bluhm Cardiovascular Institute, Chicago, Illinois
| | - James D Thomas
- Division of Cardiology, Department of Medicine, Northwestern University Feinberg School of Medicine, Chicago, Illinois
- Center for Artificial Intelligence, Northwestern Medicine Bluhm Cardiovascular Institute, Chicago, Illinois
| |
Collapse
|
6
|
Zha SZ, Rogstadkjernet M, Klæboe LG, Skulstad H, Singstad BJ, Gilbert A, Edvardsen T, Samset E, Brekke PH. Deep learning for automated left ventricular outflow tract diameter measurements in 2D echocardiography. Cardiovasc Ultrasound 2023; 21:19. [PMID: 37833731 PMCID: PMC10571406 DOI: 10.1186/s12947-023-00317-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/16/2023] [Accepted: 10/02/2023] [Indexed: 10/15/2023] Open
Abstract
BACKGROUND Measurement of the left ventricular outflow tract diameter (LVOTd) in echocardiography is a common source of error when used to calculate the stroke volume. The aim of this study is to assess whether a deep learning (DL) model, trained on a clinical echocardiographic dataset, can perform automatic LVOTd measurements on par with expert cardiologists. METHODS Data consisted of 649 consecutive transthoracic echocardiographic examinations of patients with coronary artery disease admitted to a university hospital. 1304 LVOTd measurements in the parasternal long axis (PLAX) and zoomed parasternal long axis views (ZPLAX) were collected, with each patient having 1-6 measurements per examination. Data quality control was performed by an expert cardiologist, and spatial geometry data was preserved for each LVOTd measurement to convert DL predictions into metric units. A convolutional neural network based on the U-Net was used as the DL model. RESULTS The mean absolute LVOTd error was 1.04 (95% confidence interval [CI] 0.90-1.19) mm for DL predictions on the test set. The mean relative LVOTd errors across all data subgroups ranged from 3.8 to 5.1% for the test set. Generally, the DL model had superior performance on the ZPLAX view compared to the PLAX view. DL model precision for patients with repeated LVOTd measurements had a mean coefficient of variation of 2.2 (95% CI 1.6-2.7) %, which was comparable to the clinicians for the test set. CONCLUSION DL for automatic LVOTd measurements in PLAX and ZPLAX views is feasible when trained on a limited clinical dataset. While the DL predicted LVOTd measurements were within the expected range of clinical inter-observer variability, the robustness of the DL model requires validation on independent datasets. Future experiments using temporal information and anatomical constraints could improve valvular identification and reduce outliers, which are challenges that must be addressed before clinical utilization.
Collapse
Affiliation(s)
| | | | | | - Helge Skulstad
- University of Oslo, Oslo, Norway
- Oslo University Hospital, Rikshospitalet, Oslo, Norway
| | | | | | - Thor Edvardsen
- University of Oslo, Oslo, Norway
- Oslo University Hospital, Rikshospitalet, Oslo, Norway
| | - Eigil Samset
- University of Oslo, Oslo, Norway
- GE HealthCare, Oslo, Norway
| | | |
Collapse
|
7
|
Seligman H, Patel SB, Alloula A, Howard JP, Cook CM, Ahmad Y, de Waard GA, Pinto ME, van de Hoef TP, Rahman H, Kelshiker MA, Rajkumar CA, Foley M, Nowbar AN, Mehta S, Toulemonde M, Tang MX, Al-Lamee R, Sen S, Cole G, Nijjer S, Escaned J, Van Royen N, Francis DP, Shun-Shin MJ, Petraco R. Development of artificial intelligence tools for invasive Doppler-based coronary microvascular assessment. Eur Heart J Digit Health 2023; 4:291-301. [PMID: 37538145 PMCID: PMC10393887 DOI: 10.1093/ehjdh/ztad030] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/06/2022] [Revised: 03/16/2023] [Indexed: 08/05/2023]
Abstract
Aims Coronary flow reserve (CFR) assessment has proven clinical utility, but Doppler-based methods are sensitive to noise and operator bias, limiting their clinical applicability. The objective of the study is to expand the adoption of invasive Doppler CFR, through the development of artificial intelligence (AI) algorithms to automatically quantify coronary Doppler quality and track flow velocity. Methods and results A neural network was trained on images extracted from coronary Doppler flow recordings to score signal quality and derive values for coronary flow velocity and CFR. The outputs were independently validated against expert consensus. Artificial intelligence successfully quantified Doppler signal quality, with high agreement with expert consensus (Spearman's rho: 0.94), and within individual experts. Artificial intelligence automatically tracked flow velocity with superior numerical agreement against experts, when compared with the current console algorithm [AI flow vs. expert flow bias -1.68 cm/s, 95% confidence interval (CI) -2.13 to -1.23 cm/s, P < 0.001 with limits of agreement (LOA) -4.03 to 0.68 cm/s; console flow vs. expert flow bias -2.63 cm/s, 95% CI -3.74 to -1.52, P < 0.001, 95% LOA -8.45 to -3.19 cm/s]. Artificial intelligence yielded more precise CFR values [median absolute difference (MAD) against expert CFR: 4.0% for AI and 7.4% for console]. Artificial intelligence tracked lower-quality Doppler signals with lower variability (MAD against expert CFR 8.3% for AI and 16.7% for console). Conclusion An AI-based system, trained by experts and independently validated, could assign a quality score to Doppler traces and derive coronary flow velocity and CFR. By making Doppler CFR more automated, precise, and operator-independent, AI could expand the clinical applicability of coronary microvascular assessment.
Collapse
Affiliation(s)
- Henry Seligman
- National Heart and Lung Institute, Imperial College London, B Block, Hammersmith Hospital, London W12 0HS, UK
- Royal Brompton and Harefield Hospitals, Guy's and St Thomas' NHS Foundation Trust, London, UK
| | - Sapna B Patel
- National Heart and Lung Institute, Imperial College London, B Block, Hammersmith Hospital, London W12 0HS, UK
| | - Anissa Alloula
- National Heart and Lung Institute, Imperial College London, B Block, Hammersmith Hospital, London W12 0HS, UK
| | - James P Howard
- National Heart and Lung Institute, Imperial College London, B Block, Hammersmith Hospital, London W12 0HS, UK
- Imperial College Healthcare NHS Trust, Hammersmith Hospital, London W12 0HS, UK
| | - Christopher M Cook
- Essex Cardiothoracic Centre, Basildon, Essex, UK
- Anglia Ruskin University, Chelmsford, UK
| | - Yousif Ahmad
- Yale School of Medicine, Yale University, New Haven, Connecticut, USA
| | - Guus A de Waard
- Heart Centre, Amsterdam University Medical Centre, Amsterdam, The Netherlands
| | - Mauro Echavarría Pinto
- Hospital General ISSSTE Queretaro, Faculty of Medicine, Autonomous University of Queretaro, Querétaro, Mexico
| | - Tim P van de Hoef
- Heart Centre, Amsterdam University Medical Centre, Amsterdam, The Netherlands
| | - Haseeb Rahman
- The British Heart Foundation Centre of Excellence and the National Institute for Health and Care Research Biomedical Research Centre at the School of Cardiovascular Medicine and Sciences, Kings College Medical School, St Thomas Hospital, London, UK
| | - Mihir A Kelshiker
- National Heart and Lung Institute, Imperial College London, B Block, Hammersmith Hospital, London W12 0HS, UK
- Imperial College Healthcare NHS Trust, Hammersmith Hospital, London W12 0HS, UK
| | - Christopher A Rajkumar
- National Heart and Lung Institute, Imperial College London, B Block, Hammersmith Hospital, London W12 0HS, UK
- Imperial College Healthcare NHS Trust, Hammersmith Hospital, London W12 0HS, UK
| | - Michael Foley
- National Heart and Lung Institute, Imperial College London, B Block, Hammersmith Hospital, London W12 0HS, UK
- Imperial College Healthcare NHS Trust, Hammersmith Hospital, London W12 0HS, UK
| | - Alexandra N Nowbar
- National Heart and Lung Institute, Imperial College London, B Block, Hammersmith Hospital, London W12 0HS, UK
| | - Samay Mehta
- National Heart and Lung Institute, Imperial College London, B Block, Hammersmith Hospital, London W12 0HS, UK
| | | | - Meng-Xing Tang
- Department of Engineering, Imperial College London, London, UK
| | - Rasha Al-Lamee
- National Heart and Lung Institute, Imperial College London, B Block, Hammersmith Hospital, London W12 0HS, UK
- Imperial College Healthcare NHS Trust, Hammersmith Hospital, London W12 0HS, UK
| | - Sayan Sen
- National Heart and Lung Institute, Imperial College London, B Block, Hammersmith Hospital, London W12 0HS, UK
- Imperial College Healthcare NHS Trust, Hammersmith Hospital, London W12 0HS, UK
| | - Graham Cole
- National Heart and Lung Institute, Imperial College London, B Block, Hammersmith Hospital, London W12 0HS, UK
- Imperial College Healthcare NHS Trust, Hammersmith Hospital, London W12 0HS, UK
| | - Sukhjinder Nijjer
- National Heart and Lung Institute, Imperial College London, B Block, Hammersmith Hospital, London W12 0HS, UK
- Imperial College Healthcare NHS Trust, Hammersmith Hospital, London W12 0HS, UK
| | - Javier Escaned
- Hospital Clínico San Carlos IDISSC and Universidad Complutense de Madrid, Madrid, Spain
| | - Niels Van Royen
- Radboud Institute for Molecular Life Sciences, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Darrel P Francis
- National Heart and Lung Institute, Imperial College London, B Block, Hammersmith Hospital, London W12 0HS, UK
- Imperial College Healthcare NHS Trust, Hammersmith Hospital, London W12 0HS, UK
| | - Matthew J Shun-Shin
- National Heart and Lung Institute, Imperial College London, B Block, Hammersmith Hospital, London W12 0HS, UK
- Imperial College Healthcare NHS Trust, Hammersmith Hospital, London W12 0HS, UK
| | - Ricardo Petraco
- National Heart and Lung Institute, Imperial College London, B Block, Hammersmith Hospital, London W12 0HS, UK
- Imperial College Healthcare NHS Trust, Hammersmith Hospital, London W12 0HS, UK
| |
Collapse
|
8
|
Zaman S, Vimalesvaran K, Howard JP, Chappell D, Varela M, Peters NS, Francis DP, Bharath AA, Linton NWF, Cole GD. Efficient labelling for efficient deep learning: the benefit of a multiple-image-ranking method to generate high volume training data applied to ventricular slice level classification in cardiac MRI. J Med Artif Intell 2023; 6:4. [PMID: 37346802 PMCID: PMC7614685 DOI: 10.21037/jmai-22-55] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Indexed: 06/23/2023]
Abstract
Background Getting the most value from expert clinicians' limited labelling time is a major challenge for artificial intelligence (AI) development in clinical imaging. We present a novel method for ground-truth labelling of cardiac magnetic resonance imaging (CMR) image data by leveraging multiple clinician experts ranking multiple images on a single ordinal axis, rather than manual labelling of one image at a time. We apply this strategy to train a deep learning (DL) model to classify the anatomical position of CMR images. This allows the automated removal of slices that do not contain the left ventricular (LV) myocardium. Methods Anonymised LV short-axis slices from 300 random scans (3,552 individual images) were extracted. Each image's anatomical position relative to the LV was labelled using two different strategies performed for 5 hours each: (I) 'one-image-at-a-time': each image labelled according to its position: 'too basal', 'LV', or 'too apical' individually by one of three experts; and (II) 'multiple-image-ranking': three independent experts ordered slices according to their relative position from 'most-basal' to 'most apical' in batches of eight until each image had been viewed at least 3 times. Two convolutional neural networks were trained for a three-way classification task (each model using data from one labelling strategy). The models' performance was evaluated by accuracy, F1-score, and area under the receiver operating characteristics curve (ROC AUC). Results After excluding images with artefact, 3,323 images were labelled by both strategies. The model trained using labels from the 'multiple-image-ranking strategy' performed better than the model using the 'one-image-at-a-time' labelling strategy (accuracy 86% vs. 72%, P=0.02; F1-score 0.86 vs. 0.75; ROC AUC 0.95 vs. 0.86). For expert clinicians performing this task manually the intra-observer variability was low (Cohen's κ=0.90), but the inter-observer variability was higher (Cohen's κ=0.77). Conclusions We present proof of concept that, given the same clinician labelling effort, comparing multiple images side-by-side using a 'multiple-image-ranking' strategy achieves ground truth labels for DL more accurately than by classifying images individually. We demonstrate a potential clinical application: the automatic removal of unrequired CMR images. This leads to increased efficiency by focussing human and machine attention on images which are needed to answer clinical questions.
Collapse
Affiliation(s)
- Sameer Zaman
- National Heart and Lung Institute, Imperial College London, London, UK
- Imperial College Healthcare NHS Trust, London, UK
- AI for Healthcare Centre for Doctoral Training, Imperial College London, London, UK
| | - Kavitha Vimalesvaran
- National Heart and Lung Institute, Imperial College London, London, UK
- Imperial College Healthcare NHS Trust, London, UK
- AI for Healthcare Centre for Doctoral Training, Imperial College London, London, UK
| | - James P. Howard
- National Heart and Lung Institute, Imperial College London, London, UK
- Imperial College Healthcare NHS Trust, London, UK
| | - Digby Chappell
- AI for Healthcare Centre for Doctoral Training, Imperial College London, London, UK
| | - Marta Varela
- National Heart and Lung Institute, Imperial College London, London, UK
| | | | - Darrel P. Francis
- National Heart and Lung Institute, Imperial College London, London, UK
| | - Anil A. Bharath
- Department of Bioengineering, Imperial College London, London, UK
| | - Nick W. F. Linton
- Imperial College Healthcare NHS Trust, London, UK
- Department of Bioengineering, Imperial College London, London, UK
| | - Graham D. Cole
- Imperial College Healthcare NHS Trust, London, UK
- Department of Bioengineering, Imperial College London, London, UK
| |
Collapse
|
9
|
Hagio T, Murthy VL. Deep learning: Opening a third eye to myocardial perfusion imaging. J Nucl Cardiol 2022; 29:3311-3314. [PMID: 35554868 DOI: 10.1007/s12350-022-02959-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/08/2022] [Accepted: 03/09/2022] [Indexed: 01/18/2023]
Affiliation(s)
- Tomoe Hagio
- INVIA Medical Imaging Solutions, 3025 Boardwalk St, Suite 200, Ann Arbor, MI, 48108, USA.
| | - Venkatesh L Murthy
- Division of Cardiovascular Medicine, Department of Internal Medicine, University of Michigan, Ann Arbor, MI, USA
| |
Collapse
|
10
|
Duffy G, Cheng PP, Yuan N, He B, Kwan AC, Shun-Shin MJ, Alexander KM, Ebinger J, Lungren MP, Rader F, Liang DH, Schnittger I, Ashley EA, Zou JY, Patel J, Witteles R, Cheng S, Ouyang D. High-Throughput Precision Phenotyping of Left Ventricular Hypertrophy With Cardiovascular Deep Learning. JAMA Cardiol 2022; 7:386-395. [PMID: 35195663 PMCID: PMC9008505 DOI: 10.1001/jamacardio.2021.6059] [Citation(s) in RCA: 51] [Impact Index Per Article: 25.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/31/2022]
Abstract
IMPORTANCE Early detection and characterization of increased left ventricular (LV) wall thickness can markedly impact patient care but is limited by under-recognition of hypertrophy, measurement error and variability, and difficulty differentiating causes of increased wall thickness, such as hypertrophy, cardiomyopathy, and cardiac amyloidosis. OBJECTIVE To assess the accuracy of a deep learning workflow in quantifying ventricular hypertrophy and predicting the cause of increased LV wall thickness. DESIGN, SETTINGS, AND PARTICIPANTS This cohort study included physician-curated cohorts from the Stanford Amyloid Center and Cedars-Sinai Medical Center (CSMC) Advanced Heart Disease Clinic for cardiac amyloidosis and the Stanford Center for Inherited Cardiovascular Disease and the CSMC Hypertrophic Cardiomyopathy Clinic for hypertrophic cardiomyopathy from January 1, 2008, to December 31, 2020. The deep learning algorithm was trained and tested on retrospectively obtained independent echocardiogram videos from Stanford Healthcare, CSMC, and the Unity Imaging Collaborative. MAIN OUTCOMES AND MEASURES The main outcome was the accuracy of the deep learning algorithm in measuring left ventricular dimensions and identifying patients with increased LV wall thickness diagnosed with hypertrophic cardiomyopathy and cardiac amyloidosis. RESULTS The study included 23 745 patients: 12 001 from Stanford Health Care (6509 [54.2%] female; mean [SD] age, 61.6 [17.4] years) and 1309 from CSMC (808 [61.7%] female; mean [SD] age, 62.8 [17.2] years) with parasternal long-axis videos and 8084 from Stanford Health Care (4201 [54.0%] female; mean [SD] age, 69.1 [16.8] years) and 2351 from CSMS (6509 [54.2%] female; mean [SD] age, 69.6 [14.7] years) with apical 4-chamber videos. The deep learning algorithm accurately measured intraventricular wall thickness (mean absolute error [MAE], 1.2 mm; 95% CI, 1.1-1.3 mm), LV diameter (MAE, 2.4 mm; 95% CI, 2.2-2.6 mm), and posterior wall thickness (MAE, 1.4 mm; 95% CI, 1.2-1.5 mm) and classified cardiac amyloidosis (area under the curve [AUC], 0.83) and hypertrophic cardiomyopathy (AUC, 0.98) separately from other causes of LV hypertrophy. In external data sets from independent domestic and international health care systems, the deep learning algorithm accurately quantified ventricular parameters (domestic: R2, 0.96; international: R2, 0.90). For the domestic data set, the MAE was 1.7 mm (95% CI, 1.6-1.8 mm) for intraventricular septum thickness, 3.8 mm (95% CI, 3.5-4.0 mm) for LV internal dimension, and 1.8 mm (95% CI, 1.7-2.0 mm) for LV posterior wall thickness. For the international data set, the MAE was 1.7 mm (95% CI, 1.5-2.0 mm) for intraventricular septum thickness, 2.9 mm (95% CI, 2.4-3.3 mm) for LV internal dimension, and 2.3 mm (95% CI, 1.9-2.7 mm) for LV posterior wall thickness. The deep learning algorithm accurately detected cardiac amyloidosis (AUC, 0.79) and hypertrophic cardiomyopathy (AUC, 0.89) in the domestic external validation site. CONCLUSIONS AND RELEVANCE In this cohort study, the deep learning model accurately identified subtle changes in LV wall geometric measurements and the causes of hypertrophy. Unlike with human experts, the deep learning workflow is fully automated, allowing for reproducible, precise measurements, and may provide a foundation for precision diagnosis of cardiac hypertrophy.
Collapse
Affiliation(s)
- Grant Duffy
- Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, California
| | - Paul P. Cheng
- Department of Medicine, Division of Cardiology, Stanford University, Stanford, California
| | - Neal Yuan
- Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, California
| | - Bryan He
- Department of Computer Science, Stanford University, Stanford, California
| | - Alan C. Kwan
- Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, California
| | - Matthew J. Shun-Shin
- National Heart and Lung Institute, Imperial College London, London, United Kingdom
| | - Kevin M. Alexander
- Department of Medicine, Division of Cardiology, Stanford University, Stanford, California
| | - Joseph Ebinger
- Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, California
| | | | - Florian Rader
- Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, California
| | - David H. Liang
- Department of Medicine, Division of Cardiology, Stanford University, Stanford, California
| | - Ingela Schnittger
- Department of Medicine, Division of Cardiology, Stanford University, Stanford, California
| | - Euan A. Ashley
- Department of Medicine, Division of Cardiology, Stanford University, Stanford, California
| | - James Y. Zou
- Department of Computer Science, Stanford University, Stanford, California,Department of Biomedical Data Science, Stanford University, Stanford, California
| | - Jignesh Patel
- Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, California
| | - Ronald Witteles
- Department of Medicine, Division of Cardiology, Stanford University, Stanford, California
| | - Susan Cheng
- Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, California
| | - David Ouyang
- Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, California,Division of Artificial Intelligence in Medicine, Cedars-Sinai Medical Center, Los Angeles, California
| |
Collapse
|
11
|
Vergani V, Razavi R, Puyol-Antón E, Ruijsink B. Deep Learning for Classification and Selection of Cine CMR Images to Achieve Fully Automated Quality-Controlled CMR Analysis From Scanner to Report. Front Cardiovasc Med 2021; 8:742640. [PMID: 34722674 PMCID: PMC8551568 DOI: 10.3389/fcvm.2021.742640] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/16/2021] [Accepted: 09/09/2021] [Indexed: 01/03/2023] Open
Abstract
Introduction: Deep learning demonstrates great promise for automated analysis of CMR. However, existing limitations, such as insufficient quality control and selection of target acquisitions from the full CMR exam, are holding back the introduction of deep learning tools in the clinical environment. This study aimed to develop a framework for automated detection and quality-controlled selection of standard cine sequences images from clinical CMR exams, prior to analysis of cardiac function. Materials and Methods: Retrospective study of 3,827 subjects that underwent CMR imaging. We used a total of 119,285 CMR acquisitions, acquired with scanners of different magnetic field strengths and from different vendors (1.5T Siemens and 1.5T and 3.0T Phillips). We developed a framework to select one good acquisition for each conventional cine class. The framework consisted of a first pre-processing step to exclude still acquisitions; two sequential convolutional neural networks (CNN), the first (CNNclass) to classify acquisitions in standard cine views (2/3/4-chamber and short axis), the second (CNNQC) to classify acquisitions according to image quality and orientation; a final algorithm to select one good acquisition of each class. For each CNN component, 7 state-of-the-art architectures were trained for 200 epochs, with cross entropy loss and data augmentation. Data were divided into 80% for training, 10% for validation, and 10% for testing. Results: CNNclass selected cine CMR acquisitions with accuracy ranging from 0.989 to 0.998. Accuracy of CNNQC reached 0.861 for 2-chamber, 0.806 for 3-chamber, and 0.859 for 4-chamber. The complete framework was presented with 379 new full CMR studies, not used for CNN training/validation/testing, and selected one good 2-, 3-, and 4-chamber acquisition from each study with sensitivity to detect erroneous cases of 89.7, 93.2, and 93.9%, respectively. Conclusions: We developed an accurate quality-controlled framework for automated selection of cine acquisitions prior to image analysis. This framework is robust and generalizable as it was developed on multivendor data and could be used at the beginning of a pipeline for automated cine CMR analysis to obtain full automatization from scanner to report.
Collapse
Affiliation(s)
- Vittoria Vergani
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
| | - Reza Razavi
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom.,Department of Adult and Paediatric Cardiology, Guy's and St. Thomas' NHS Foundation Trust, London, United Kingdom
| | - Esther Puyol-Antón
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
| | - Bram Ruijsink
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom.,Department of Cardiology, Division of Heart and Lungs, University Medical Centre Utrecht, Utrecht, Netherlands
| |
Collapse
|