OncoReg: Medical Image Registration for Oncological Challenges

2025-03-29

AI Summary

In medical image registration, patient privacy constraints hinder multi-center data sharing, resulting in poor model generalizability. Method: OncoReg introduces the first two-stage privacy-preserving registration paradigm that synergistically integrates public pretraining with hospital-specific private data. It proposes an end-to-end interpretable registration framework that innovatively hybridizes deep learning with classical algorithms, with particular emphasis on optimizing the feature extraction module. Technically, it enables accurate cross-modal registration between cone-beam CT (CBCT) and planning CT, supporting dynamic tumor tracking in image-guided radiotherapy. Contribution/Results: Experiments identify feature extraction as the primary performance bottleneck. The proposed hybrid strategy significantly outperforms single-method baselines in registration accuracy, robustness, and stability—thereby enhancing clinical deployability of registration models.

Technology Category

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

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Data transparency and provenance
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

In modern cancer research, the vast volume of medical data generated is often underutilised due to challenges related to patient privacy. The OncoReg Challenge addresses this issue by enabling researchers to develop and validate image registration methods through a two-phase framework that ensures patient privacy while fostering the development of more generalisable AI models. Phase one involves working with a publicly available dataset, while phase two focuses on training models on a private dataset within secure hospital networks. OncoReg builds upon the foundation established by the Learn2Reg Challenge by incorporating the registration of interventional cone-beam computed tomography (CBCT) with standard planning fan-beam CT (FBCT) images in radiotherapy. Accurate image registration is crucial in oncology, particularly for dynamic treatment adjustments in image-guided radiotherapy, where precise alignment is necessary to minimise radiation exposure to healthy tissues while effectively targeting tumours. This work details the methodology and data behind the OncoReg Challenge and provides a comprehensive analysis of the competition entries and results. Findings reveal that feature extraction plays a pivotal role in this registration task. A new method emerging from this challenge demonstrated its versatility, while established approaches continue to perform comparably to newer techniques. Both deep learning and classical approaches still play significant roles in image registration, with the combination of methods - particularly in feature extraction - proving most effective.

Problem

• Develops privacy-preserving medical image registration for oncology
• Addresses alignment of CBCT and FBCT in radiotherapy
• Evaluates deep learning and classical registration methods

Innovation

• Two-phase framework ensures privacy and generalizability
• Interventional CBCT and FBCT image registration
• Combines deep learning and classical feature extraction