[论文解读] Deep-Learning Atlas Registration for Melanoma Brain Metastases: Preserving Pathology While Enabling Cohort-Level Analyses

Nanna Wielenberg, Ilinca Popp+7 more|arXiv (Cornell University)|Feb 13, 2026

Cutaneous Melanoma Detection and Management被引用 0

一句话总结

引入一个完全可微分、无需预处理的深度学习大脑归一图谱对齐框架，在保持转移性病灶的同时将 MBM 对齐到一个通用的图谱，实现跨多中心数据的稳健队列分析。

ABSTRACT

Melanoma brain metastases (MBM) are common and spatially heterogeneous lesions, complicating cohort-level analyses due to anatomical variability and differing MRI protocols. We propose a fully differentiable, deep-learning-based deformable registration framework that aligns individual pathological brains to a common atlas while preserving metastatic tissue without requiring lesion masks or preprocessing. Missing anatomical correspondences caused by metastases are handled through a forward-model similarity metric based on distance-transformed anatomical labels, combined with a volume-preserving regularization term to ensure deformation plausibility. Registration performance was evaluated using Dice coefficient (DSC), Hausdorff distance (HD), average symmetric surface distance (ASSD), and Jacobian-based measures. The method was applied to 209 MBM patients from three centres, enabling standardized mapping of metastases to anatomical, arterial, and perfusion atlases. The framework achieved high registration accuracy across datasets (DSC 0.89-0.92, HD 6.79-7.60 mm, ASSD 0.63-0.77 mm) while preserving metastatic volumes. Spatial analysis demonstrated significant over-representation of MBM in the cerebral cortex and putamen, under-representation in white matter, and consistent localization near the gray-white matter junction. No arterial territory showed increased metastasis frequency after volume correction. This approach enables robust atlas registration of pathological brain MRI without lesion masks and supports reproducible multi-centre analyses. Applied to MBM, it confirms and refines known spatial predilections, particularly preferential seeding near the gray-white matter junction and cortical regions. The publicly available implementation facilitates reproducible research and extension to other brain tumours and neurological pathologies.

研究动机与目标

• 降低个体之间的解剖变异性，以实现黑色素瘤脑转移（MBM）队列级可重复分析的目标。
• 在无需预处理或病灶遮罩的情况下，将病理性大脑影像注册到一个通用图谱。
• 在注册过程中保持转移性组织，并对缺失对应关系进行鲁棒处理。
• 在多中心 MBM 队列上验证框架，并分析空间分布模式。

提出的方法

• 使用一个完全可微分的可变形配准框架，通过一个输出 stationary velocity field 的 U-net 计算形变场，将每个受试者映射到一个图谱。
• 采用一个采样模块，通过可学习的采样网格应用变换，以避免重采样带来的图像退化。
• 在 Learn2Reg 的健康数据集上训练一个通用模型，然后对个体病例进行一次性过拟合（Learn2Reg-OF 和 Clin1-Clin3-OF），以获得更高的准确性。
• 使用两项损失：基于标签图的相似性损失（通过距离变换标签和 NCC）以及正则化/体积保持项，外加一个可选的体积损失，用于处理过拟合过程中的缺失对应。
• 用 Dice、Hausdorff 距离、ASSD 进行配准评估，并结合基于雅可比的合理性和肿瘤体积变化进行综合评估。
• 框架的公开实现，结合基于图谱的 MBM 分析，覆盖三个中心。

Figure 1 : The overall architecture used in this work. The sampling modules act like a wrapper around images ( $I_{i}$ and $I_{j}$ ) and the atlas ( $I_{A}$ ) and are responsible for preparing them as input for the neural network and for applying the calculated transformations ( $T_{i}$ , $T_{j}$ )

实验结果

研究问题

• RQ1 在无需预处理或病灶掩膜的前提下，深度学习的可变形配准框架是否能将 MBM 对齐到一个通用图谱，同时保持肿瘤组织？
• RQ2 该方法是否能够在跨多中心 MBM 数据集上实现稳健、可重复的队列级空间分析？
• RQ3 对齐到图谱后 MBM 的空间分布模式是什么，与已知的神经解剖和灌注标志相关吗？
• RQ4 一次性对个体病例的过拟合与通用模型在准确性和病理组织保持方面有何比较？

主要发现

• 在不同数据集上，配准准确性保持较高（DSC 0.89–0.92，HD 6.79–7.60 mm，ASSD 0.63–0.77 mm），且转移性体积得到保持。
• 对齐到图谱后，MBM 在大脑皮层和壳核呈现过度代表，在白质中呈现不足，转移性病灶更偏向灰质–白质界面附近。
• 在区域体积校正后，动脉区没有显著增加的 MBM 频率。
• 体积保持损失在过拟合过程中提升了肿瘤保持（例如 Clin1-OF DSC 0.89，HD 7.27 mm，ASSD 0.77 mm；肿瘤体积因子约为 0.82，雅可比比约为 0.91）。
• 该框架在不进行预处理和病灶掩膜的情况下实现了强大配准，支持跨中心的可重复队列分析。

Figure 2 : This figure illustrates the difference in contour-based loss between a collapsing tumour region and a volume-preserved tumour evaluated in image space and atlas space for a simplified (left) and a real world (right) example. The upper part of the figure shows the images with tumour contou