# The segmentation ceiling: why explicit left-ventricular masks do not improve learned ejection-fraction regression

arXiv: https://arxiv.org/abs/2609.19730 · HTML: https://mlsanity.com/paper/2609.19730/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 17 Sep 2026.

## Builds on (most cited first, 10 of 10)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning](https://mlsanity.com/paper/2201.04676/) (2022)
- [Ultrasound Video Transformers for Cardiac Ejection Fraction Estimation](https://mlsanity.com/paper/2107.00977/) (2021)
- [EchoCoTr: Estimation of the Left Ventricular Ejection Fraction from Spatiotemporal Echocardiography](https://mlsanity.com/paper/2209.04242/) (2022)
- [EchoJEPA: A Latent Predictive Foundation Model for Echocardiography](https://mlsanity.com/paper/2602.02603/) (2026)
- [Uncertainty Propagation for Echocardiography Clinical Metric Estimation via Contour Sampling](https://mlsanity.com/paper/2502.12713/) (2025)
- [Hierarchical Spatio-temporal Segmentation Network for Ejection Fraction Estimation in Echocardiography Videos](https://mlsanity.com/paper/2508.18681/) (2025)
- [Generative Regression for Left Ventricular Ejection Fraction Estimation from Echocardiography Video](https://mlsanity.com/paper/2602.08202/) (2026)

## Abstract (arXiv)

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.