Follow Your Heart: Landmark-Guided Transducer Pose Scoring for Point-of-Care Echocardiography
Authors: Zaiyang Guo, Jessie N. Dong, Filippos Bellos, Jilei Hao, Emily J. MacKay, Trevor Chan, Shir Goldfinger, Sethu Reddy, +3 more
Organizations: ⋆University of Pennsylvania, Philadelphia, PA, USA · † University of Michigan, Ann Anbor, MI, USA · § Central Michigan University, Mt Pleasant, MI, USA
Point-of-care transthoracic echocardiography (TTE) makes it possible to assess a patient's cardiac function in almost any setting. A critical step in the TTE exam is acquisition of the apical 4-chamber (A4CH) view, which is used to evaluate clinically impactful measurements such as left ventricular ejection fraction (LVEF). However, optimizing transducer pose for high-quality image acquisition and subsequent measurement is a challenging task, particularly for novice users. In this work, we present a multi-task network that provides feedback cues for A4CH view acquisition and automatically estimates LVEF in high-quality A4CH images. The network cascades a transducer pose scoring module and an uncertainty-aware LV landmark detector with automated LVEF estimation. A strength is that network training and inference do not require cumbersome or costly setups for transducer position tracking. We evaluate performance on point-of-care TTE data acquired with a spatially dense "sweep" protocol around the optimal A4CH view. The results demonstrate the network's ability to determine when the transducer pose is on target, close to target, or far from target based on the images alone, while generating visual landmark cues that guide anatomical interpretation and orientation. In conclusion, we demonstrate a promising strategy to provide guidance for A4CH view acquisition, which may be useful when deploying point-of-care TTE in limited resource settings.
Figures & tables
Figure 1: A. Overview of the multi-task network. TTE video frames are first passed through the landmark detector. The images and predicted landmarks then pass through the pose scoring module to be classified as green, yellow, or red. Optimal ”green” clips are then passed to an automated LVEF estimator. B. Each TTE sweep starts with the transducer in the optimal A4CH pose and drifts away from the optimal pose. Ground truth pose categories (green, yellow, red) are manually assigned and mapped to a numeric pose score.
Figure 2: A. Predicted and ground truth landmarks B. Predicted landmarks displayed with prediction uncertainty C. Key landmark output passed on to pose scoring module
Criterion
Deduction (points)
LV free wall not visible
-1
RV free wall not visible
-0.5
LA entirely/partially out of view
-2 / -1
RA not visible
-0.5
Aorta clearly visible (apical 5-chamber view)
-1
Other significant signal dropout
-0.5
Table 1: Pose scoring criteria for TTE frames.
Images + Landmarks
Images Only
Landmarks Only
ResNet18 Regression
ResNet18 + LLaMA
ResNet18 Regression
ResNet18 + LLaMA
ResNet18 Regression
ResNet18 + LLaMA
Fold 1
0.71
0.73
0.69
0.72
0.64
0.63
Fold 2
0.72
0.72
0.71
0.73
0.64
0.67
Fold 3
0.68
0.69
0.66
0.67
0.60
0.62
Fold 4
0.69
0.71
0.68
0.73
0.61
0.69
Fold 5
0.63
0.69
0.68
0.72
0.61
0.65
Table 2: Test accuracy of the transducer pose scoring module
Figure 3: Overall confusion matrix and corresponding examples of misclassified TTE frames using images and landmarks.
Point-of-care transthoracic echocardiography (TTE) enables cardiac assessment in virtually any clinical setting, yet its diagnostic utility remains constrained by the expertise required for image acquisition and interpretation. Visual question answering (VQA) offers a promising paradigm for bridging this expertise gap through interactive clinical assistance, but existing echocardiography VQA datasets are limited in scale, restricted to high-quality images, and only cover a few views. We introduce EchoVQA, the first large-scale VQA dataset for echocardiography, comprising 14,299 images and 74,819 question-answer pairs. The dataset integrates public sources (EchoNet-Dynamic, CAMUS) with our own point-of-care acquisitions from two handheld probes (Lumify, Clarius), spanning diverse views and including both high-quality and suboptimal images. Uniquely, EchoVQA includes acquisition guidance questions to help users optimize transducer positioning toward a diagnostic apical 4-chamber view for left ventricular ejection fraction estimation -- a challenging task for novice operators in point-of-care settings. We further develop a parameter-efficient method based on multimodal learnable prompts achieving state-of-the-art performance on most benchmarks, including EchoVQA, with significantly less trainable parameters than existing state-of-the-art approaches.
Filippos Bellos, Yutong Li, Jessie N Dong +6
University of Michigan · University of Pennsylvania · Independent Scientist
We introduce Echo-POSED, a self-supervised framework for real-time transthoracic echocardiography (TTE) guidance that recommends probe adjustments directly from 2D ultrasound images, without the need for expert-labelled views or tracked probe trajectories. Instead, it trains on 2D views sliced from routinely acquired 3D echocardiography volumes, enforcing equivariance to probe motions while remaining invariant to cardiac phase, yielding a pose representation on SO(3)×SO(3). Across a held-out split and public external 3D--TTE datasets (including vendor shift), Echo-POSED maintains geometric consistency under virtual perturbations and enables intra- and inter-patient guidance simulations, achieving a combined mean angular error of 8.2 degrees between the guided and target views in intra-patient simulations with cardiac motion.
Elias Stenhede, Edvart Grüner Bjerke, Joanna Sulkowska +4
Medical Technology & E-Health, Akershus University Hospital, Norway · Department of Technology Systems, University of Oslo, Norway · K.G. Jebsen Center for Cardiac Biomarkers, University of Oslo, Norway +3
Left ventricular ejection fraction (LVEF) is a primary marker of cardiac function. However, routine estimation from endocardial measurements requires manual delineation at end-diastole (ED) and end-systole (ES), a process that is time-consuming and subject to inter-observer variability. Reliable automation is especially valuable for point-of-care ultrasound (POCUS), where computational resources are limited and acquisition quality varies. We propose Echo-E3Net, an anatomy-guided spatio-temporal network that explicitly embeds cardiac anatomy into LVEF prediction. A dual-phase Endocardial Border Detector (E2CBD) uses phase-specific cross-attention to localize ED/ES endocardial landmarks and produce phase-aware landmark embeddings, while an Endocardial Feature Aggregator (E2FA) fuses these embeddings with global statistical descriptors of deep feature maps to refine EF regression. Training is guided by a lightweight geometric loss that uses ED and ES endocardial landmarks to regularize EF prediction. On EchoNet-Dynamic and a PSAX subset of EchoNet-Pediatric, Echo-E3Net attains competitive performance using only 1.55M parameters and 8.05 GFLOPs, an order-of-magnitude compute reduction versus recent baselines, supporting real-time deployment. Our code is publicly available at https://github.com/moeinheidari7829/Echo-E3Net.
University of British Columbia, Vancouver, BC, Canada · University of Regensburg, Regensburg, Germany · Iran University of Science and Technology, Tehran, Iran +1