Evaluating self-supervised echocardiographic representations across downstream extraction strategies for left-ventricular segmentation and ejection fraction estimation
Authors: Sylwia Majchrowska, Philip Teare
Organizations: aR&D Data ScienceSylwiaSkills &Majchrowskaa,Partnership, DataPhilipScienceTeareb& AI, BioPharma R&D, AstraZeneca, Pepparedsleden 1, Mölndal, 431 83, Sweden · bCentre for AI, Data Science & AI, BioPharma R&D, AstraZeneca, BiomedicalJun Campus, 1 Francis Crick Ave, Trumpington, Cambridge, CB2 0AA, UK
Abstract
Self-supervised learning (SSL) is increasingly used in medical imaging to reduce annotation requirements, but representation quality is often judged using a single downstream evaluation setting. For dense clinical tasks, this can confound representation quality with the capacity of the downstream model used to recover task-relevant information. We present a systematic evaluation of self-supervised representations for left-ventricular segmentation and ejection fraction (EF) estimation from apical four-chamber echocardiography on EchoNet-Dynamic. Rather than relying on a single downstream probe, we compare a hierarchy of extraction strategies with increasing expressivity: heuristic extraction without mask-supervised training, frozen linear probes, frozen lightweight decoder probes, and partial fine-tuning. We apply this framework to two complementary representation families: generic frozen self-DIstillation with NO labels (DINOv3) features and a task-adapted dense self-supervised representation, Bootstrap Your Own Segmentation (BYOS). In both families, heuristic extraction substantially understated what was recoverable from the frozen representation. For DINOv3, performance improved from Dice 0.684 and EF mean absolute error (MAE) 13.01 under heuristic extraction to Dice 0.906 and EF MAE 9.65 with a frozen lightweight decoder, approaching a supervised U-Net baseline (Dice 0.915, EF MAE 9.72). For BYOS, performance improved from Dice 0.687 and EF MAE 17.83 under heuristic extraction to Dice 0.902 and EF MAE 8.74 with a frozen lightweight decoder. These results show that conclusions about self-supervised representation quality in dense echocardiographic analysis depend strongly on the downstream extraction strategy used for evaluation. We therefore argue that multi-strategy evaluation is an important methodological consideration for SSL in dense medical image analysis.
Accurate estimation of left ventricular ejection fraction (EF) from echocardiography is central to cardiovascular care, and deep learning enables automated EF prediction from echocardiographic video. Because EF is clinically derived from left-ventricular (LV) volumes, a widely held intuition is that explicit LV segmentation should improve prediction. We introduce a quantitative criterion, the segmentation ceiling, that makes this testable: from EF as a normalized difference of end-diastolic and end-systolic volumes, we derive in closed form how per-frame segmentation area error propagates into EF error, and thus the accuracy a mask must reach before it can improve on direct regression. Using EchoNet-Dynamic, a UniFormer-S backbone, and the empirically measured within-patient error correlation, the criterion places the break-even near 10% per-frame area error, whereas a representative segmenter operates at roughly 14%, above the ceiling. Consistent with this, four strategies for injecting segmentation or area information (a predicted-mask channel, end-diastolic/end-systolic clip sampling, and per-bin and amplitude area-consistency objectives) fail to beat a raw-video baseline; ground-truth masks help only through label leakage. Input representation thus not being the limit, we identify generalization as the practical lever: weight averaging with strong augmentation attains a test R^2 of 0.806 (MAE 4.08) under a matched dense-clip protocol, comparable to an R(2+1)D baseline (0.811) while tightening the validation-to-test gap. Finally, a heteroscedastic beta-NLL formulation yields informative, well-calibrated per-prediction uncertainty, larger for clinically harder low-EF cases, where Monte-Carlo dropout does not. The segmentation ceiling gives a concrete design criterion for when mask-guided EF estimation is worthwhile, plus a simple, uncertainty-aware recipe for EF regression.
Farshid Farhadi Khouzani, Paul La Plante, Bryar Mustafa Shareef +1
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.
We present, to the best of our knowledge, the first publicly available resource for predicting left ventricular ejection fraction (EF) from parasternal long-axis (PLAX) echocardiography. Because no PLAX-EF datasets previously existed, our work focuses on an innovative data generation strategy to overcome this scarcity. By leveraging a time-based correlation between clinical notes and echocardiographic videos, combined with fine-tuning view classifiers and proxy labeling, we created a labeled dataset of over 25,000 PLAX videos. This enables us to train the first reproducible PLAX EF model, achieving a mean absolute error (MAE) of 6.86%. Given that apical four-chamber (A4C) methods, the clinical standard, report MAE values of 6%-7%, our results demonstrate that EF estimation from PLAX views is both feasible and clinically relevant. This surpasses the performance of existing methods and provides a clinically relevant solution for situations where apical views may not be feasible. Going further, we demonstrate that combining PLAX and A4C predictions via simple unweighted late fusion improves both single-view baselines to a 6.37% MAE, underscoring the value of multi-view integration. To promote continued research, we release the dataset labels, trained models, and runnable demos on GitHub, Hugging Face, and Google Colab: https://github.com/Jeffrey4899/PLAX_EF_Labels_202509