Deep-Learning Atlas Registration for Melanoma Brain Metastases: Preserving Pathology While Enabling Cohort-Level Analyses

TL;DR

This paper introduces a deep-learning-based deformable registration framework that aligns pathological brain MRIs to a common atlas, preserving metastatic tissue and enabling multi-centre cohort analyses without requiring lesion masks.

Contribution

It presents a novel, fully differentiable registration method that handles anatomical variability and metastases without lesion masks, improving multi-centre brain tumor studies.

Findings

Achieved high registration accuracy (DSC 0.89-0.92) across datasets.

Enabled standardized mapping of metastases to various brain atlases.

Confirmed known spatial patterns of melanoma brain metastases.

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.