在3D分割中融合深度度量学习与Coreset的主动学习方法
Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation
AI总结：
本文提出一种融合深度度量学习与Coreset的基于切片的主动学习方法，用于3D医学分割，在弱标注和完整标注下均优于现有方法，显著降低标注成本。
摘要：
深度学习在机器学习领域取得了显著进展，但通常需要大量标注数据。3D语义分割等任务带来了沉重的标注负担，尤其是在医学等领域，专家标注进一步推高了成本。主动学习（AL）在减轻3D医学分割的标注负担方面具有巨大潜力。然而，现有的大多数主动学习方法并未针对医学领域进行定制。尽管弱监督方法已被探索用于降低标注负担，但主动学习与弱监督的融合仍未得到研究，尽管这种融合有潜力显著降低标注成本。此外，针对3D分割的基于切片的主动学习关注较少，与传统的基于体素的主动学习相比，这种方式也能显著降低成本。本文提出了一种新颖的度量学习方法，用于Coreset在3D医学分割中执行基于切片的主动学习。通过将对比学习与医学影像中固有的数据分组相结合，我们学习了一种度量，该度量强调样本中与训练3D医学分割模型相关的差异。我们在四个数据集（医学和非医学）上使用弱标注和完整标注进行了全面评估。实验结果表明，我们的方法在弱标注和完整标注上均超越了现有的主动学习技术，并在低标注预算下取得了优越性能，这在医学影像中至关重要。本项目的源代码可在补充材料中获取，并已发布在GitHub上：https://github.com/arvindmvepa/al-seg。
英文摘要：
Deep learning has seen remarkable advancements in machine learning, yet it often demands extensive annotated data. Tasks like 3D semantic segmentation impose a substantial annotation burden, especially in domains like medicine, where expert annotations drive up the cost. Active learning (AL) holds great potential to alleviate this annotation burden in 3D medical segmentation. The majority of existing AL methods, however, are not tailored to the medical domain. While weakly-supervised methods have been explored to reduce annotation burden, the fusion of AL with weak supervision remains unexplored, despite its potential to significantly reduce annotation costs. Additionally, there is little focus on slice-based AL for 3D segmentation, which can also significantly reduce costs in comparison to conventional volume-based AL. This paper introduces a novel metric learning method for Coreset to perform slice-based active learning in 3D medical segmentation. By merging contrastive learning with inherent data groupings in medical imaging, we learn a metric that emphasizes the relevant differences in samples for training 3D medical segmentation models. We perform comprehensive evaluations using both weak and full annotations across four datasets (medical and non-medical). Our findings demonstrate that our approach surpasses existing active learning techniques on both weak and full annotations and obtains superior performance with low-annotation budgets which is crucial in medical imaging. Source code for this project is available in the supplementary materials and on GitHub: https://github.com/arvindmvepa/al-seg.
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。
