MedCL：学习一致性解剖分布用于涂鸦监督的医学图像分割
MedCL: Learning Consistent Anatomy Distribution for Scribble-supervised Medical Image Segmentation
AI总结：
针对医学图像分割中涂鸦标注不足且难以覆盖长尾疾病的问题，提出MedCL框架，通过特征混合与局部全局解剖分布聚类正则化，仅需少量弱监督即可分割常规器官与不规则病理，并在多个数据集上显著超越传统方法。
摘要：
构建大规模全标注数据集成本高昂、费时费力，尤其在医学图像领域。文献中已提出多种利用涂鸦形式弱标注的方法，但这些方法需要大量涂鸦标注，且仅适用于常规器官的分割，而这些标注对于长尾分布中的疾病类别往往不可获得。鉴于医学标签具有解剖分布先验，我们提出了一种基于聚类的涂鸦监督框架，称为MedCL，以学习医学标签固有的解剖分布。我们的方法包含两个步骤：i) 通过图像内和图像间的混合操作混合特征，ii) 执行特征聚类并在局部和全局层面正则化解剖分布。结合少量弱监督，所提出的MedCL能够分割常规器官和具有挑战性的不规则病理。我们基于SAM和UNet骨干实现了MedCL，并在三个开放数据集上评估性能：常规结构（MSCMRseg）、多器官（BTCV）和不规则病理（MyoPS）。结果表明，即使在更少的涂鸦监督下，MedCL也显著优于传统分割方法。我们的代码可在https://github.com/BWGZK/MedCL获取。
英文摘要：
Curating large-scale fully annotated datasets is expensive, laborious, and cumbersome, especially for medical images. Several methods have been proposed in the literature that make use of weak annotations in the form of scribbles. However, these approaches require large amounts of scribble annotations, and are only applied to the segmentation of regular organs, which are often unavailable for the disease species that fall in the long-tailed distribution. Motivated by the fact that the medical labels have anatomy distribution priors, we propose a scribble-supervised clustering-based framework, called MedCL, to learn the inherent anatomy distribution of medical labels. Our approach consists of two steps: i) Mix the features with intra- and inter-image mix operations, and ii) Perform feature clustering and regularize the anatomy distribution at both local and global levels. Combined with a small amount of weak supervision, the proposed MedCL is able to segment both regular organs and challenging irregular pathologies. We implement MedCL based on SAM and UNet backbones, and evaluate the performance on three open datasets of regular structure (MSCMRseg), multiple organs (BTCV) and irregular pathology (MyoPS). It is shown that even with less scribble supervision, MedCL substantially outperforms the conventional segmentation methods. Our code is available at https://github.com/BWGZK/MedCL.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
