Test Time Optimized Generalized AI-based Medical Image Registration Method

TL;DR

This paper presents a novel AI-based 3D non-rigid medical image registration framework that is highly generalizable across different imaging modalities and anatomical regions, aiming to improve real-time clinical application.

Contribution

The proposed method introduces a generalizable, modality-agnostic AI framework for 3D non-rigid registration, reducing the need for task-specific retraining and customization.

Findings

Demonstrates effective registration across multiple modalities and regions

Reduces parameter tuning and computational costs

Enables real-time clinical workflow integration

Abstract

Medical image registration is critical for aligning anatomical structures across imaging modalities such as computed tomography (CT), magnetic resonance imaging (MRI), and ultrasound. Among existing techniques, non-rigid registration (NRR) is particularly challenging due to the need to capture complex anatomical deformations caused by physiological processes like respiration or contrast-induced signal variations. Traditional NRR methods, while theoretically robust, often require extensive parameter tuning and incur high computational costs, limiting their use in real-time clinical workflows. Recent deep learning (DL)-based approaches have shown promise; however, their dependence on task-specific retraining restricts scalability and adaptability in practice. These limitations underscore the need for efficient, generalizable registration frameworks capable of handling heterogeneous imaging contexts. In this work, we introduce a novel AI-driven framework for 3D non-rigid registration that generalizes across multiple imaging modalities and anatomical regions. Unlike conventional methods that rely on application-specific models, our approach eliminates anatomy- or modality-specific customization, enabling streamlined integration into diverse clinical environments.