Reinforcement Learning-Based Optimization of CT Acquisition and Reconstruction Parameters Through Virtual Imaging Trials

2025-10-09

AI Summary

CT protocol optimization faces challenges due to strong coupling among acquisition parameters (e.g., tube voltage, tube current, reconstruction kernel), rendering exhaustive search inefficient and incapable of simultaneously optimizing image quality and radiation dose. To address this, we propose an end-to-end CT protocol optimization framework integrating virtual imaging with proximal policy optimization (PPO)—the first application of PPO to joint CT parameter optimization. Our method incorporates a validated CT simulator, a custom-built reconstruction toolkit, and anthropomorphic virtual phantoms, enabling multi-objective image quality assessment. Evaluated on liver lesion detection, the framework achieves the globally optimal detection index (d′), reducing optimization iterations by 79.7% compared to exhaustive search while significantly improving computational efficiency. Moreover, it demonstrates strong scalability and clinical adaptability potential.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Computer Vision: Learning & Optimization for CV
• Constraint Satisfaction and Optimization: Constraint Optimization

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Protocol optimization is critical in Computed Tomography (CT) to achieve high diagnostic image quality while minimizing radiation dose. However, due to the complex interdependencies among CT acquisition and reconstruction parameters, traditional optimization methods rely on exhaustive testing of combinations of these parameters, which is often impractical. This study introduces a novel methodology that combines virtual imaging tools with reinforcement learning to optimize CT protocols more efficiently. Human models with liver lesions were imaged using a validated CT simulator and reconstructed with a novel CT reconstruction toolkit. The optimization parameter space included tube voltage, tube current, reconstruction kernel, slice thickness, and pixel size. The optimization process was performed using a Proximal Policy Optimization (PPO) agent, which was trained to maximize an image quality objective, specifically the detectability index (d') of liver lesions in the reconstructed images. Optimization performance was compared against an exhaustive search performed on a supercomputer. The proposed reinforcement learning approach achieved the global maximum d' across test cases while requiring 79.7% fewer steps than the exhaustive search, demonstrating both accuracy and computational efficiency. The proposed framework is flexible and can accommodate various image quality objectives. The findings highlight the potential of integrating virtual imaging tools with reinforcement learning for CT protocol management.

Problem

• Optimizing CT acquisition and reconstruction parameters to balance radiation dose and image quality
• Addressing complex parameter interdependencies impractical for traditional exhaustive testing methods
• Developing reinforcement learning framework for efficient CT protocol optimization using virtual trials

Innovation

• Reinforcement learning optimizes CT acquisition parameters
• Virtual imaging trials simulate human models with lesions
• PPO agent maximizes lesion detectability with fewer steps