Christina L. Luong

Subacute aortic dissection presenting as heart failure due to aortic valve insufficiency and right coronary artery dissection

Hediyeh Vaseli, Rosalind Groenewoud, Edward Percy, Christina L. Luong

Subacute thoracic aortic aneurysm dissection (TAAD) often presents with a clinical profile distinct from its acute form, which can closely mimic common cardiac conditions, risking diagnostic delay. We report a case of subacute TAAD presenting initially with progressive dyspnoea due to severe …

ca (code pays fourni par la source)

Clinical and Echocardiographic Characteristics of Neuroendocrine Tumours and Carcinoid Heart Disease: Insights from a Contemporary Canadian Cohort

J.S. Yoon, Cynthia Yeung, Jeffrey D. Wong, Janine Mazengarb et autres

Background Neuroendocrine tumours (NETs) are uncommon cancers that secrete vasoactive hormones. Around half of metastatic small bowel NETs develop carcinoid syndrome and historically up to 50% develop carcinoid heart disease (CHD). We evaluated clinical characteristics, echocardiographic features, and outcomes of patients with …

ca (code pays fourni par la source)

Shift happens: a fairness-oriented framework for medical classification under hidden bias

Minh Nguyen Nhat To, Diane Kim, Mohamed Harmanani, Paul Wilson et autres

ca (code pays fourni par la source)

Optimizing Point-of-Care Ultrasound Video Acquisition for Probabilistic Multi-Task Heart Failure Detection

Armin Saadat, Nima Hashemi, Bahar Khodabakhshian, Michael Y. Tsang et autres

Purpose: Echocardiography with point-of-care ultrasound (POCUS) must support clinical decision-making under tight bedside time and operator-effort constraints. We introduce a personalized data acquisition strategy in which an RL agent, given a partially observed multi-view study, selects the next view to acquire or …

Optimizing Point-of-Care Ultrasound Video Acquisition for Probabilistic Multi-Task Heart Failure Detection

Armin Saadat, Nima Hashemi, Bahar Khodabakhshian, Michael Y. Tsang et autres

Purpose: Echocardiography with point-of-care ultrasound (POCUS) must support clinical decision-making under tight bedside time and operator-effort constraints. We introduce a personalized data acquisition strategy in which an RL agent, given a partially observed multi-view study, selects the next view to acquire or …

Cardiac cycle-aware segmentation of the left ventricle in echocardiography videos

Baraa Abdelsamad, Bassant Medhat, Tarek Elghareb, Raghav Goyal et autres

Impact of a Fully Integrated “1-Click” Automated Left Ventricular Ejection Fraction Tool on Echocardiography Reporting

Parshan Mashhourinejad, Darwin F. Yeung, Michael Tsang, Teresa S.M. Tsang et autres

Background: The Simpson's Biplane Method (SBM) is the recommended standard for clinical reporting of left ventricular ejection fraction (LVEF). However, visual estimation of LVEF is common practice. Automated tools for SBM offer rapid, reproducible volumetric LVEF calculations, but their real-world impact on …

ca (code pays fourni par la source)

Point Tracking as a Temporal Cue for Robust Myocardial Segmentation in Echocardiography Videos

Bahar Khodabakhshian, Nima Hashemi, Armin Saadat, Zahra Gholami et autres

Purpose: Myocardium segmentation in echocardiography videos is a challenging task due to low contrast, noise, and anatomical variability. Traditional deep learning models either process frames independently, ignoring temporal information, or rely on memory-based feature propagation, which accumulates error over time. Methods: We …

Point Tracking as a Temporal Cue for Robust Myocardial Segmentation in Echocardiography Videos

Bahar Khodabakhshian, Nima Hashemi, Armin Saadat, Zahra Gholami et autres

Purpose: Myocardium segmentation in echocardiography videos is a challenging task due to low contrast, noise, and anatomical variability. Traditional deep learning models either process frames independently, ignoring temporal information, or rely on memory-based feature propagation, which accumulates error over time. Methods: We …

ca (code pays fourni par la source)

ProtoEFNet: Dynamic Prototype Learning for Inherently Interpretable Ejection Fraction Estimation in Echocardiography

Yeganeh Ghamary, Victoria Wu, Hooman Vaseli, Christina L. Luong et autres

dk, ca (code pays fourni par la source)

ProtoEFNet: Dynamic Prototype Learning for Inherently Interpretable Ejection Fraction Estimation in Echocardiography

Yeganeh Ghamary, Victoria Wu, Hooman Vaseli, Christina L. Luong et autres

Ejection fraction (EF) is a crucial metric for assessing cardiac function and diagnosing conditions such as heart failure. Traditionally, EF estimation requires manual tracing and domain expertise, making the process time-consuming and subject to interobserver variability. Most current deep learning methods for …

HiProtoNet: Hyperbolic Hierarchy-Aware Part Prototypes for Aortic Stenosis Severity Classification

Hooman Vaseli, Victoria Wu, Michael Y. C. Tsang, Ang Nan Gu et autres

ca (code pays fourni par la source)