AI 中文总结
提出分割天花板标准，证明显式左心室分割掩膜难以提升射血分数回归性能，并给出不确定性感知的EF回归方案。
AI 中文摘要
从超声心动图准确估计左心室射血分数（EF）是心血管诊疗的核心，深度学习使得从超声心动图视频自动预测EF成为可能。由于EF在临床上由左心室（LV）容积推导而来，一个普遍直觉是显式LV分割应能改善预测。我们引入一个定量标准——分割天花板，使其可检验：从EF作为舒张末期与收缩末期容积的归一化差值出发，我们以闭式推导了每帧分割面积误差如何传播为EF误差，从而得出掩膜在能优于直接回归前必须达到的精度。使用EchoNet-Dynamic、UniFormer-S骨干网络以及经验测量的患者内误差相关性，该标准将盈亏平衡点置于约10%的每帧面积误差，而代表性分割器运行在约14%，高于天花板。与此一致，四种注入分割或面积信息的策略（预测掩膜通道、舒张末期/收缩末期片段采样、逐箱和幅度面积一致性目标）均未能超越原始视频基线；真实掩膜仅通过标签泄漏起作用。输入表示并非限制因素，我们将泛化识别为实际杠杆：强增强下的权重平均在匹配的密集片段协议下达到测试R^2为0.806（MAE 4.08），与R(2+1)D基线（0.811）相当，同时缩小了验证到测试的差距。最后，异方差beta-NLL公式产生信息丰富、校准良好的逐预测不确定性，在临床更难的低EF病例中更大，而蒙特卡洛dropout则不然。分割天花板为掩膜引导的EF估计何时值得提供了具体设计标准，以及一个简单、不确定性感知的EF回归方案。
英文摘要
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.
Comments15 pages, 4 figures
