轻量U-Net实现超快心超左室分割，精度媲美大模型。
Lightweight image segmentation for echocardiography
- 仅保留关键组件：仿射增强+深度监督，舍弃复杂设计
- 参数量仅200万（原3300万），速度提升4倍（1.35ms/帧）
- 适合临床实时应用，尤其资源受限的便携设备
准确分割心超图像中的左心室可实现全自动临床指标提取，如容积和射血分数。尽管nnU-Net表现良好，但其模型庞大、推理缓慢，限制了实时应用。通过消融实验系统评估数据增强、结构修改、损失函数和后处理技术，发现仿射增强与深度监督是性能关键，而复杂增强和大模型容量收益递减。基于此，我们构建了一个轻量级U-Net（2M参数对比原版33M），在CAMUS数据集（N=500）上达到与nnU-Net相当的分割效果（左心室/心肌/左房Dice分数分别为0.93/0.85/0.89 vs 0.93/0.86/0.89，p>0.05），体积缩小16倍，推理速度提升4倍（1.35ms vs 5.40ms每帧）。跨数据集验证显示在内部数据集（N=311）上仍具良好泛化能力。
原文摘要 · Abstract (English)
Accurate segmentation of the left ventricle in echocardiography can enable fully automatic extraction of clinical measurements such as volumes and ejection fraction. While models configured by nnU-Net perform well, they are large and slow, thus limiting real-time use. We identified the most effective components of nnU-Net for cardiac segmentation through an ablation study, incrementally evaluating data augmentation schemes, architectural modifications, loss functions, and post-processing techniques. Our analysis revealed that simple affine augmentations and deep supervision drive performance, while complex augmentations and large model capacity offer diminishing returns. Based on these insights, we developed a lightweight U-Net (2M vs 33M parameters) that achieves statistically equivalent performance to nnU-Net on CAMUS (N=500) with Dice scores of 0.93/0.85/0.89 vs 0.93/0.86/0.89 for LV/MYO/LA ($p>0.05$), while being 16 times smaller and 4 times faster (1.35ms vs 5.40ms per frame) than the default nnU-Net configuration. Cross-dataset evaluation on an internal dataset (N=311) confirms comparable generalization.
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。