发表机构
School of Engineering and Applied Science, University of Virginia; School of Medicine, University of Virginia（弗吉尼亚大学工程与应用科学学院; 弗吉尼亚大学医学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出CalcSeg框架，通过置信感知动态半监督课程学习与潜在切片级自注意力机制，在多中心LGE-CMR数据集上实现优于现有方法的心肌瘢痕分割性能，代码已开源。
AI 中文摘要
从单堆叠钆延迟增强心脏磁共振（LGE-CMR）图像中分割心肌瘢痕是一项长期存在且具有重要临床意义的挑战，尤其在组织对比度低、瘢痕呈弥漫性或体积较小时更为突出。3D空间上下文的有限可用性进一步加剧了这些挑战。本文提出CalcSeg，这是一个置信感知潜在上下文课程学习框架，利用单堆叠2D LGE-CMR图像的融合3D特征表示实现鲁棒的瘢痕分割。具体而言，我们引入动态半监督课程学习策略，通过学习到的置信感知评分函数，从较简单的瘢痕病例到更具挑战性的病例逐步扩展训练过程。该函数将预测瘢痕图的误差、量化的认知不确定性以及瘢痕负荷估计相结合，无需人工标签即可自动评估样本难度。为弥补单堆叠采集的空间上下文有限的问题，我们开发了潜在切片级自注意力机制，以捕捉切片间依赖关系并从稀疏2D输入中推断3D空间表示。我们在多中心临床LGE-CMR数据集上对CalcSeg进行评估，并与现有瘢痕分割网络进行基准测试。实验结果表明，CalcSeg始终优于所有对比方法，尤其在临床具有挑战性的病例中实现了显著改进。我们的代码已在Github上发布。
英文摘要
Myocardial scar segmentation from single-stack late gadolinium-enhanced cardiac magnetic resonance (LGE-CMR) imaging has been a longstanding and clinically important challenge, particularly in the presence of low tissue contrast, diffuse, and small scar regions. These challenges are further intensified by the limited availability of 3D spatial context. This paper presents CalcSeg, a Confidence-aware latent context curriculum learning framework that leverages fused 3D feature representations from single-stack 2D LGE-CMR images for robust scar segmentation. Specifically, we introduce a dynamic semi-supervised curriculum learning strategy that progressively expands training from easier to more challenging scar cases using a learned confidence-aware scoring function. Such a function integrates errors in the predicted scar maps with quantified epistemic uncertainty and scar burden estimation to automatically assess sample difficulty without requiring manual labels. To compensate for the limited spatial context in single-stack acquisitions, we then develop a latent slice-wise self-attention to capture inter-slice dependencies and infer 3D spatial representations from sparse 2D inputs. We evaluate CalcSeg on multi-center clinical LGE-CMR datasets and benchmark against existing scar segmentation networks. Experimental results show that CalcSeg consistently outperforms all competing methods, particularly with substantial improvements on clinically challenging cases. Our code is released on Github.
