Learn2Reg: Comprehensive Multi-Task Medical Image Registration Challenge, Dataset and Evaluation in the Era of Deep Learning
Learn2Reg: Comprehensive Multi-Task Medical Image Registration Challenge, Dataset and Evaluation in the Era of Deep Learning
复制标题
DOI：
10.1109/tmi.2022.3213983
复制
发表时间：
2023-03-01
影响因子：
10.6
通讯作者：
Heinrich, Mattias P.
中科院分区：
文献类型：
--
作者：
Hering, Alessa;Hansen, Lasse;Heinrich, Mattias P.
图像配准是一项基本的医学图像分析任务，并且已经提出了多种方法。然而，只有少数研究在广泛的临床相关任务中全面比较了医学图像配准方法。这限制了注册方法的发展、研究进展应用于实践以及竞争方法的公平基准。 Learn2Reg 挑战赛通过提供多任务医学图像配准数据集来全面表征可变形配准算法，从而解决了这些限制。可以在 https://learn2reg.grand-challenge.org 上进行持续评估。 Learn2Reg 涵盖广泛的解剖结构（大脑、腹部和胸部）、模式（超声、CT、MR）、注释的可用性以及患者内和患者间的注册评估。我们建立了一个易于访问的框架，用于培训和验证 3D 配准方法，从而能够对来自 20 多个独特团队提交的超过 65 个单独方法的结果进行汇编。我们使用了一组互补的指标，包括鲁棒性、准确性、合理性和运行时间，从而能够对当前最先进的医学图像配准有独特的见解。本文描述了数据集、任务、评估方法和挑战结果，以及进一步分析新数据集可迁移性的结果、标签监督的重要性以及由此产生的偏差。虽然没有一种方法能够在所有任务中发挥最佳效果，但可以确定许多方法论方面，将医学图像配准的性能推向新的最先进性能。此外，我们揭开了传统注册方法必须比基于深度学习的方法慢得多的普遍看法。
Image registration is a fundamental medical image analysis task, and a wide variety of approaches have been proposed. However, only a few studies have comprehensively compared medical image registration approaches on a wide range of clinically relevant tasks. This limits the development of registration methods, the adoption of research advances into practice, and a fair benchmark across competing approaches. The Learn2Reg challenge addresses these limitations by providing a multi-task medical image registration data set for comprehensive characterisation of deformable registration algorithms. A continuous evaluation will be possible at https://learn2reg.grand-challenge.org. Learn2Reg covers a wide range of anatomies (brain, abdomen, and thorax), modalities (ultrasound, CT, MR), availability of annotations, as well as intra- and inter-patient registration evaluation. We established an easily accessible framework for training and validation of 3D registration methods, which enabled the compilation of results of over 65 individual method submissions from more than 20 unique teams. We used a complementary set of metrics, including robustness, accuracy, plausibility, and runtime, enabling unique insight into the current state-of-the-art of medical image registration. This paper describes datasets, tasks, evaluation methods and results of the challenge, as well as results of further analysis of transferability to new datasets, the importance of label supervision, and resulting bias. While no single approach worked best across all tasks, many methodological aspects could be identified that push the performance of medical image registration to new state-of-the-art performance. Furthermore, we demystified the common belief that conventional registration methods have to be much slower than deep-learning-based methods