The Brain Resection Multimodal Image Registration (ReMIND2Reg) 2025 Challenge

TL;DR

This paper presents ReMIND2Reg 2025, the largest public benchmark for registering preoperative MRI to post-resection intraoperative ultrasound to compensate brain shift during brain tumor surgery. It details a multimodal dataset derived from ReMIND, including 99 training, 5 validation, and 10 private test cases with ceT1 and T2 MRI alongside post-resection iUS, all pre-processed to a common resolution and space. Evaluation uses TRE, TRE30, and runtime, employing bootstrap-based Wilcoxon ranking to compare methods under varying landmark counts. The framework aims to accelerate robust, generalizable multimodal registration approaches that can enhance intraoperative navigation and patient outcomes.

Abstract

Accurate intraoperative image guidance is critical for achieving maximal safe resection in brain tumor surgery, yet neuronavigation systems based on preoperative MRI lose accuracy during the procedure due to brain shift. Aligning post-resection intraoperative ultrasound (iUS) with preoperative MRI can restore spatial accuracy by estimating brain shift deformations, but it remains a challenging problem given the large anatomical and topological changes and substantial modality intensity gap. The ReMIND2Reg 2025 Challenge provides the largest public benchmark for this task, built upon the ReMIND dataset. It offers 99 training cases, 5 validation cases, and 10 private test cases comprising paired 3D ceT1 MRI, T2 MRI, and post-resection 3D iUS volumes. Data are provided without annotations for training, while validation and test performance are evaluated on manually annotated anatomical landmarks. Metrics include target registration error (TRE), robustness to worst-case landmark misalignment (TRE30), and runtime. By establishing a standardized evaluation framework for this clinically critical and technically complex problem, ReMIND2Reg aims to accelerate the development of robust, generalizable, and clinically deployable multimodal registration algorithms for image-guided neurosurgery.

Figures (1)

• Figure 1: Illustrative example of unregistered preoperative MRI and overlaid post-resection iUS. Misalignment is observed between (a) contrast-enhanced T1 MRI and post-resection iUS, and (b) T2 MRI and post-resection iUS. A prominent resection cavity is clearly visible in the iUS images.