[论文解读] The Brain Tumor Sequence Registration (BraTS-Reg) Challenge: Establishing Correspondence Between Pre-Operative and Follow-up MRI Scans of Diffuse Glioma Patients

Bhakti Baheti, Satrajit Chakrabarty+71 more|arXiv (Cornell University)|Dec 13, 2021

Medical Image Segmentation Techniques被引用 27

一句话总结

本论文介绍 BraTS-Reg，这是一个公开的基准测试和挑战，针对弥散性胶质瘤的术前与随访MRI之间的可变形配准，具备多机构数据集、标注地标及标准化评估指标。

ABSTRACT

Registration of longitudinal brain MRI scans containing pathologies is challenging due to dramatic changes in tissue appearance. Although there has been progress in developing general-purpose medical image registration techniques, they have not yet attained the requisite precision and reliability for this task, highlighting its inherent complexity. Here we describe the Brain Tumor Sequence Registration (BraTS-Reg) challenge, as the first public benchmark environment for deformable registration algorithms focusing on estimating correspondences between pre-operative and follow-up scans of the same patient diagnosed with a diffuse brain glioma. The BraTS-Reg data comprise de-identified multi-institutional multi-parametric MRI (mpMRI) scans, curated for size and resolution according to a canonical anatomical template, and divided into training, validation, and testing sets. Clinical experts annotated ground truth (GT) landmark points of anatomical locations distinct across the temporal domain. Quantitative evaluation and ranking were based on the Median Euclidean Error (MEE), Robustness, and the determinant of the Jacobian of the displacement field. The top-ranked methodologies yielded similar performance across all evaluation metrics and shared several methodological commonalities, including pre-alignment, deep neural networks, inverse consistency analysis, and test-time instance optimization per-case basis as a post-processing step. The top-ranked method attained the MEE at or below that of the inter-rater variability for approximately 60% of the evaluated landmarks, underscoring the scope for further accuracy and robustness improvements, especially relative to human experts. The aim of BraTS-Reg is to continue to serve as an active resource for research, with the data and online evaluation tools accessible at https://bratsreg.github.io/.

研究动机与目标

• 激励并解决由于肿块效应和组织变化导致的纵向脑MRI配准在弥漫性胶质瘤中的挑战。
• 提供一个公开的、多机构的数据集，具有标准化的可变形配准预处理，用于研究。
• 定义并实现真实地标点（ground-truth landmarks）以及用于评估配准算法的容器化评估框架。
• 通过使用固定的评估平台和清晰的提交协议，促进可重复性和公平比较。

提出的方法

• 汇集并对来自多家机构的250对术前和随访的多参数MRI扫描进行预处理，整合到通用模板（SRI24），分辨率为1mm3。
• 由专家在基线和随访扫描中标注对应的地标点（在肿瘤30mm范围内及超出30mm处），并由二次专家评估评注者之间的一致性。
• 提供包含真实地标坐标的训练数据和随访地标，验证/测试数据仅提供随访地标供评估。
• 通过专家放置的地标获得真实配准，并使用如 Median Absolute Error (MAE)、鲁棒性（Robustness）以及雅可比行列式正则性等指标对算法进行评估。
• 参赛者提交全自动、容器化（如 Docker/Singularity）的配准方法，以在隐藏测试数据上进行评估。

实验结果

研究问题

• RQ1 如何在跨机构的弥漫性胶质瘤病例中，可靠地建立术前与随访脑MRIs之间的可变形配准？
• RQ2 使用标准化预处理流程时，肿瘤引起的大变形和术后变化对配准精度有何影响？
• RQ3 基于地标的 MAE、鲁棒性以及基于雅可比的平滑度是否足以在多机构环境中对配准算法进行排名？
• RQ4 容器化、可重复的评估框架是否能确保公平比较和配准方法的泛化性？

主要发现

• BraTS-Reg 数据集包含250对患者，具备多参数MRI并标准化预处理至通用模板。
• 建立了基于地标的真实框架，每例6–50个地标，并评估评注者之间的一致性变异。
• 评估协议将 MAE、鲁棒性以及基于雅可比的平滑度定义为配准质量的核心定量指标。
• 训练数据提供基线和随访地标坐标；验证数据仅提供随访地标用于评估；测试数据对容器化提交评估保密。
• 以仿射配准提供基线性能，以对比变形方法。
• 挑战通过容器化提交和集中文评估平台（IPP）强调可重复性和公平比较。