Patient-Specific Autoregressive Models for Organ Motion Prediction in Radiotherapy

2025-05-17

AI Summary

Respiratory and other physiological motions during radiotherapy cause organ displacement, compromising treatment accuracy. Existing PCA-based pre-treatment motion prediction methods critically depend on image registration quality and struggle to capture periodic temporal dynamics. This paper proposes a patient-specific autoregressive motion prediction framework—the first to adapt the autoregressive paradigm from natural language processing to medical image motion modeling. It directly learns individualized spatiotemporal dynamics from preoperative 4D CT multi-phase sequences without requiring image registration. The model integrates 3D convolutional feature extraction with recurrent temporal modeling to explicitly encode motion periodicity and inter-patient variability. Evaluated on real clinical data comprising 70 patients and over 1,300 3D CT phases, the method achieves significantly higher prediction accuracy for lung and cardiac motion compared to state-of-the-art approaches, thereby enhancing the precision and adaptability of radiotherapy pre-planning.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Multimodal Learning
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Radiotherapy often involves a prolonged treatment period. During this time, patients may experience organ motion due to breathing and other physiological factors. Predicting and modeling this motion before treatment is crucial for ensuring precise radiation delivery. However, existing pre-treatment organ motion prediction methods primarily rely on deformation analysis using principal component analysis (PCA), which is highly dependent on registration quality and struggles to capture periodic temporal dynamics for motion modeling.In this paper, we observe that organ motion prediction closely resembles an autoregressive process, a technique widely used in natural language processing (NLP). Autoregressive models predict the next token based on previous inputs, naturally aligning with our objective of predicting future organ motion phases. Building on this insight, we reformulate organ motion prediction as an autoregressive process to better capture patient-specific motion patterns. Specifically, we acquire 4D CT scans for each patient before treatment, with each sequence comprising multiple 3D CT phases. These phases are fed into the autoregressive model to predict future phases based on prior phase motion patterns. We evaluate our method on a real-world test set of 4D CT scans from 50 patients who underwent radiotherapy at our institution and a public dataset containing 4D CT scans from 20 patients (some with multiple scans), totaling over 1,300 3D CT phases. The performance in predicting the motion of the lung and heart surpasses existing benchmarks, demonstrating its effectiveness in capturing motion dynamics from CT images. These results highlight the potential of our method to improve pre-treatment planning in radiotherapy, enabling more precise and adaptive radiation delivery.

Problem

• Predict patient-specific organ motion in radiotherapy
• Improve accuracy of pre-treatment motion modeling
• Capture periodic dynamics using autoregressive models

Innovation

• Autoregressive models predict organ motion phases
• Patient-specific 4D CT scans enhance motion prediction
• Method outperforms benchmarks in lung and heart