The Brain Resection Multimodal Image Registration (ReMIND2Reg) 2025 Challenge

2025-08-13

AI Summary

In brain tumor surgery, preoperative MRI-based navigation suffers from inaccuracies due to intraoperative brain shift, necessitating highly robust non-rigid multimodal registration between post-resection intraoperative ultrasound (iUS) and preoperative MRI. To address this, we introduce the first large-scale, publicly available benchmark specifically designed for real-world brain resection cases—comprising 99 training, 5 validation, and 10 private test cases—with paired 3D contrast-enhanced T1-weighted, T2-weighted MRI and post-resection 3D iUS volumes, all without manual annotations. We propose an anatomy-guided evaluation framework incorporating target registration error (TRE), TRE30 (TRE computed on the top-30 anatomically salient landmarks), and runtime, jointly optimizing registration accuracy and clinical practicality. This benchmark establishes a rigorous foundation for developing generalizable, robust, and clinically deployable non-rigid multimodal registration algorithms.

Technology Category

• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Large-scale security measurements

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.

Problem

• Align post-resection iUS with preoperative MRI for brain shift correction
• Address large anatomical changes and modality intensity gaps in registration
• Establish standardized evaluation for multimodal neurosurgery registration algorithms

Innovation

• Multimodal image registration for brain shift correction
• Largest public benchmark with 114 clinical cases
• Standardized evaluation using TRE and runtime metrics