Validating Deep Learning to Distinguish Takotsubo Syndrome From Acute Myocardial Infarction—Beware of Shortcuts, Human Supervision Required

Wehbe, Ramsey M.; Thomas, James D.

doi:10.1001/jamacardio.2022.0193

Cited by 9 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning could be applied to LV flow fields for disease identification, similar to reported analyses of structural images (Tromp et al, 2022;Wehbe et al, 2023) . Contrastive POD (cPOD) could remove background LV flow features shared by healthy and diseased subjects, potentially improving cohort separability or identify subpopulations in DCM or HCM (Abid et al, 2018).…”

Section: Limitations and Future Workmentioning

confidence: 98%

Deriving Explainable Metrics of Left Ventricular Flow by Reduced-Order Modeling and Classification

Borja,

Martinez-Legazpi,

Nguyen

et al. 2023

Preprint

View full text Add to dashboard Cite

BackgroundExtracting explainable flow metrics is a bottleneck to the clinical translation of advanced cardiac flow imaging modalities. We hypothesized that reduced-order models (ROMs) of intraventricular flow are a suitable strategy for deriving simple and interpretable clinical metrics suitable for further assessments. Combined with machine learning (ML) flow-based ROMs could provide new insight to help diagnose and risk-stratify patients.MethodsWe analyzed 2D color-Doppler echocardiograms of 81 non-ischemic dilated cardiomyopathy (DCM) patients, 51 hypertrophic cardiomyopathy (HCM) patients, and 77 normal volunteers (Control). We applied proper orthogonal decomposition (POD) to build patient-specific and cohort-specific ROMs of LV flow. Each ROM aggregates a low number of components representing a spatially dependent velocity map modulated along the cardiac cycle by a time-dependent coefficient. We tested three classifiers using deliberately simple ML analyses of these ROMs with varying supervision levels. In supervised models, hyperparameter gridsearch was used to derive the ROMs that maximize classification power. The classifiers were blinded to LV chamber geometry and function. We ran vector flow mapping on the color-Doppler sequences to help visualize flow patterns and interpret the ML results.ResultsPOD-based ROMs stably represented each cohort through 10-fold cross-validation. The principal POD mode captured >80% of the flow kinetic energy (KE) in all cohorts and represented the LV filling/emptying jets. Mode 2 represented the diastolic vortex and its KE contribution ranged from <1% (HCM) to 13% (DCM). Semi-unsupervised classification using patient-specific ROMs revealed that the KE ratio of these two principal modes, the vortex-to-jet (V2J) energy ratio, is a simple, interpretable metric that discriminates DCM, HCM, and Control patients. Receiver operating characteristic curves using V2J as classifier had areas under the curve of 0.81, 0.91, and 0.95 for distinguishing HCM vs. Control, DCM vs. Control, and DCM vs. HCM, respectively.ConclusionsModal decomposition of cardiac flow can be used to create ROMs of normal and pathological flow patterns, uncovering simple interpretable flow metrics with power to discriminate disease states, and particularly suitable for further processing using ML.

show abstract

Section: Limitations and Future Workmentioning

confidence: 98%

Deriving Explainable Metrics of Left Ventricular Flow by Reduced-Order Modeling and Classification

Borja,

Martinez-Legazpi,

Nguyen

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Several studies have shown how the use of AI Echo can minimize the known limitations of these approaches. 40–42,44,47,50,51…”

Section: Ai Echo For Image Interpretationmentioning

confidence: 99%

Closing the Last Mile Gap in Access to Multimodality Imaging in Rural Settings: Design of the Imaging Core of the Risk Underlying Rural Areas Longitudinal Study

Fazlalizadeh,

Khan,

Fox

et al. 2024

Circ: Cardiovascular Imaging

Self Cite

View full text Add to dashboard Cite

Achieving optimal cardiovascular health in rural populations can be challenging for several reasons including decreased access to care with limited availability of imaging modalities, specialist physicians, and other important health care team members. Therefore, innovative solutions are needed to optimize health care and address cardiovascular health disparities in rural areas. Mobile examination units can bring imaging technology to underserved or remote communities with limited access to health care services. Mobile examination units can be equipped with a wide array of assessment tools and multiple imaging modalities such as computed tomography scanning and echocardiography. The detailed structural assessment of cardiovascular and lung pathology, as well as the detection of extracardiac pathology afforded by computed tomography imaging combined with the functional and hemodynamic assessments acquired by echocardiography, yield deep phenotyping of heart and lung disease for populations historically underrepresented in epidemiological studies. Moreover, by bringing the mobile examination unit to local communities, innovative approaches are now possible including engagement with local professionals to perform these imaging assessments, thereby augmenting local expertise and experience. However, several challenges exist before mobile examination unit–based examinations can be effectively integrated into the rural health care setting including standardizing acquisition protocols, maintaining consistent image quality, and addressing ethical and privacy considerations. Herein, we discuss the potential importance of cardiac multimodality imaging to improve cardiovascular health in rural regions, outline the emerging experience in this field, highlight important current challenges, and offer solutions based on our experience in the RURAL (Risk Underlying Rural Areas Longitudinal) cohort study.

show abstract

“…Thus, it is critical to assess final model performance on a separate holdout test set (preferably from an external source) that the model was never exposed to during the entire research and development process (eAppendix 6 and eTable 3 in the Supplement). Failure to do so can result in falsely optimistic performance estimates and/or failure to recognize a model that has overfit to irrelevant features called shortcuts (eg, scanner metadata or manufacturer logos) . Detailed guidance on the design, implementation, and evaluation of DL models for CVI have been previously published as part of the Proposed Requirements for Cardiovascular Imaging-Related Machine Learning Evaluation (PRIME) checklist …”

Section: Training and Evaluating A Deep Learning Modelmentioning

confidence: 99%

Deep Learning for Cardiovascular Imaging

Wehbe,

Katsaggelos,

Hammond

et al. 2023

JAMA Cardiol

Self Cite

View full text Add to dashboard Cite

ImportanceArtificial 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.ObservationsAt 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 RelevanceDeep 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.

show abstract

Validating Deep Learning to Distinguish Takotsubo Syndrome From Acute Myocardial Infarction—Beware of Shortcuts, Human Supervision Required

Cited by 9 publications

References 10 publications

Deriving Explainable Metrics of Left Ventricular Flow by Reduced-Order Modeling and Classification

Deriving Explainable Metrics of Left Ventricular Flow by Reduced-Order Modeling and Classification

Closing the Last Mile Gap in Access to Multimodality Imaging in Rural Settings: Design of the Imaging Core of the Risk Underlying Rural Areas Longitudinal Study

Deep Learning for Cardiovascular Imaging

Contact Info

Product

Resources

About