Continuous sPatial-Temporal Deformable Image Registration (CPT-DIR) for motion modelling in radiotherapy: beyond classic voxel-based methods

2024-05-01

arXiv.org

AI Summary

Existing deformable image registration (DIR) methods rely on discrete parameterizations (e.g., B-splines), limiting accurate modeling of large deformations and sliding boundaries—such as the lung–chest wall interface—thereby compromising contour propagation and dose accumulation reliability in radiotherapy. To address this, we propose the first continuous spatiotemporal DIR framework tailored for radiotherapy: it employs implicit neural representations (INRs) to directly map spatial coordinates to a velocity field, followed by temporal integration to generate a displacement field—enabling joint continuous modeling in both space and time. The method requires no pretraining and achieves rapid, single-case adaptation, significantly improving robustness and generalizability. Evaluated on the DIR-Lab 4DCT dataset, it reduces target registration error from 2.79 mm to 0.99 mm, achieves whole-body voxel-wise mean absolute error of 28.99 HU, attains a rib Dice score of 90.56%, and completes single-case registration in under 15 seconds.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Intelligent Robots: Localization, Mapping, and Navigation

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Background and purpose: Deformable image registration (DIR) is a crucial tool in radiotherapy for extracting and modelling organ motion. However, when significant changes and sliding boundaries are present, it faces compromised accuracy and uncertainty, determining the subsequential contour propagation and dose accumulation procedures. Materials and methods: We propose an implicit neural representation (INR)-based approach modelling motion continuously in both space and time, named Continues-sPatial-Temporal DIR (CPT-DIR). This method uses a multilayer perception (MLP) network to map 3D coordinate (x,y,z) to its corresponding velocity vector (vx,vy,vz). The displacement vectors (dx,dy,dz) are then calculated by integrating velocity vectors over time. The MLP's parameters can rapidly adapt to new cases without pre-training, enhancing optimisation. The DIR's performance was tested on the DIR-Lab dataset of 10 lung 4DCT cases, using metrics of landmark accuracy (TRE), contour conformity (Dice) and image similarity (MAE). Results: The proposed CPT-DIR can reduce landmark TRE from 2.79mm to 0.99mm, outperforming B-splines' results for all cases. The MAE of the whole-body region improves from 35.46HU to 28.99HU. Furthermore, CPT-DIR surpasses B-splines for accuracy in the sliding boundary region, lowering MAE and increasing Dice coefficients for the ribcage from 65.65HU and 90.41% to 42.04HU and 90.56%, versus 75.40HU and 89.30% without registration. Meanwhile, CPT-DIR offers significant speed advantages, completing in under 15 seconds compared to a few minutes with the conventional B-splines method. Conclusion: Leveraging the continuous representations, the CPT-DIR method significantly enhances registration accuracy, automation and speed, outperforming traditional B-splines in landmark and contour precision, particularly in the challenging areas.

Problem

• Enhances accuracy in deformable image registration for radiotherapy
• Addresses limitations of discrete motion representation in DIR
• Improves handling of complex anatomical interfaces like lung-chest wall

Innovation

• Uses implicit neural representation for motion modeling
• Ensures spatial and temporal continuity in registration
• Unifies Eulerian and Lagrangian specifications effectively