研究心脏超声分割中依赖理想条件导致部署失败的问题
When Oracle Conditioning Misleads Deployment: Conditioning-Availability Bias in Echocardiographic Segmentation
- 用可部署的估计相位替代理想真值，检测模型对条件变化的敏感性
- 在CAMUS数据上，理想训练的模型在真实部署时性能严重下降
- 提出部署感知检查点选择，能有效缓解条件偏差问题
条件分割模型在训练和评估时使用比实际部署时更干净的辅助信号，这种协议层面的捷径学习现象在相位条件化的心脏超声分割中尤为明显。通过互补差距对（complementary gap pair）衡量在可部署的基于估算相位路径上的损失，并探测在随机相位路径上的敏感性。在独立测试集CAMUS上，一个强循环、基于真值选择的模型在使用估算相位时表现严重退化，且对错误相位的敏感性在三个运行中持续存在；在EchoNet-Dynamic上，当前估计器仍可用，但随机相位测试揭示了强烈的潜在敏感性。部署感知检查点选择与相位扰动能显著减小两种差距，同时几乎不影响平均Dice分数。探索性子组分析量化了不同测量分层间的差异，下游射血分数（EF）审计显示，分割恢复并不一定意味着EF误差或符号偏差的恢复。这些差距用于检验基于真值条件的性能是否能在实际部署路径中保持。
原文摘要 · Abstract (English)
Conditional segmentation models may be trained and evaluated with auxiliary signals cleaner than those available at deployment. We study this protocol-level manifestation of shortcut learning and auxiliary-variable shift in phase-conditioned echocardiographic segmentation. The complementary gap pair measures loss on the deployable oracle-estimated pathway and probes sensitivity on the oracle-random pathway. On held-out CAMUS data, one strong-cyclic, oracle-selected run fails severely with estimated phase, while sensitivity to incorrect phase persists across three runs. On EchoNet-Dynamic, the current estimator remains usable, but random-phase testing reveals strong latent sensitivity. Deployment-aware checkpoint selection and phase perturbation reduce both gaps with little change in mean Dice. Exploratory subgroup analyses quantify variation across measured strata, and a downstream ejection fraction (EF) audit shows that recovering segmentation does not necessarily recover EF error or signed bias. Together, the gaps test whether oracle-conditioned performance survives the inference pathway actually available at deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。