DINOMotion: advanced robust tissue motion tracking with DINOv2 in 2D-Cine MRI-guided radiotherapy

2025-08-13

AI Summary

To address the poor robustness, limited interpretability, and difficulty in handling large displacements in tissue motion tracking for 2D-cine MRI-guided radiotherapy, this paper proposes a lightweight, keypoint-driven registration framework synergistically optimized using DINOv2 and LoRA. Methodologically, self-supervised DINOv2 features enhance robustness to large deformations; LoRA enables efficient fine-tuning and parameter compression; and end-to-end keypoint detection establishes explicit anatomical correspondences, enabling real-time (≈30 ms/frame), non-iterative direct inference. Evaluated on volunteer and patient data, the method achieves Dice scores of 92.07%, 90.90%, and 95.23% for kidney, liver, and lung parenchyma segmentation, respectively, with corresponding Hausdorff distances of 5.47 mm, 8.31 mm, and 6.72 mm—significantly outperforming state-of-the-art approaches. The framework delivers high accuracy, strong robustness to motion and deformation, and clinically meaningful interpretability through anatomically grounded keypoints.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: Motion and Path Planning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Accurate tissue motion tracking is critical to ensure treatment outcome and safety in 2D-Cine MRI-guided radiotherapy. This is typically achieved by registration of sequential images, but existing methods often face challenges with large misalignments and lack of interpretability. In this paper, we introduce DINOMotion, a novel deep learning framework based on DINOv2 with Low-Rank Adaptation (LoRA) layers for robust, efficient, and interpretable motion tracking. DINOMotion automatically detects corresponding landmarks to derive optimal image registration, enhancing interpretability by providing explicit visual correspondences between sequential images. The integration of LoRA layers reduces trainable parameters, improving training efficiency, while DINOv2's powerful feature representations offer robustness against large misalignments. Unlike iterative optimization-based methods, DINOMotion directly computes image registration at test time. Our experiments on volunteer and patient datasets demonstrate its effectiveness in estimating both linear and nonlinear transformations, achieving Dice scores of 92.07% for the kidney, 90.90% for the liver, and 95.23% for the lung, with corresponding Hausdorff distances of 5.47 mm, 8.31 mm, and 6.72 mm, respectively. DINOMotion processes each scan in approximately 30ms and consistently outperforms state-of-the-art methods, particularly in handling large misalignments. These results highlight its potential as a robust and interpretable solution for real-time motion tracking in 2D-Cine MRI-guided radiotherapy.

Problem

• Accurate tissue motion tracking in MRI-guided radiotherapy
• Challenges with large misalignments in image registration
• Need for interpretable and efficient motion tracking methods

Innovation

• Uses DINOv2 with LoRA for robust motion tracking
• Automatically detects landmarks for image registration
• Directly computes registration for real-time processing