通过逐级优化能量得分，让医学图像分割模型自适应不同设备数据。
Progressive Test Time Energy Adaptation for Medical Image Segmentation
- 用预训练的形状能量模型为分割结果打分，低分代表正确结构。
- 在测试时逐步降低能量得分，使模型适应新数据分布。
- 在8个影像数据集上表现优于基线，适合临床实时应用。
我们提出一种模型无关的、渐进式的测试时能量自适应方法，用于医学图像分割。由于成像协议不一致和患者差异，模型在不同医学数据集上的性能难以保持。与需要多次遍历目标数据的领域自适应方法不同，我们的方法在处理测试数据时逐步调整预训练模型。该方法基于源数据训练的形状能量模型，在图像块级别为分割图分配能量分数：低能量表示分布内（准确）的形状，高能量则提示分布外（错误）的预测。通过在测试时最小化该能量分数，我们引导分割模型向目标分布对齐。为验证有效性与适应性，我们在八个公开的MRI（bSSFP、T1-和T2加权）和X-ray数据集上进行了评估，涵盖心脏、脊髓和肺部分割任务。结果表明，该框架在定量和定性上均持续优于基线方法。
原文摘要 · Abstract (English)
We propose a model-agnostic, progressive test-time energy adaptation approach for medical image segmentation. Maintaining model performance across diverse medical datasets is challenging, as distribution shifts arise from inconsistent imaging protocols and patient variations. Unlike domain adaptation methods that require multiple passes through target data - impractical in clinical settings - our approach adapts pretrained models progressively as they process test data. Our method leverages a shape energy model trained on source data, which assigns an energy score at the patch level to segmentation maps: low energy represents in-distribution (accurate) shapes, while high energy signals out-of-distribution (erroneous) predictions. By minimizing this energy score at test time, we refine the segmentation model to align with the target distribution. To validate the effectiveness and adaptability, we evaluated our framework on eight public MRI (bSSFP, T1- and T2-weighted) and X-ray datasets spanning cardiac, spinal cord, and lung segmentation. We consistently outperform baselines both quantitatively and qualitatively.
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。