AgentCT improves CT scan restoration by choosing specific fixes
AgentCT: A Vision-Language Agent for Universal CT Imaging
Computer Vision and Pattern Recognition
Summary
CT scans can have different kinds of problems like being too noisy, having missing views, or metal causing distortions. The paper presents AgentCT, a system that first figures out what kind of problem a CT image has and then sends it to a specialized fix designed for that problem. AgentCT’s controller can identify the problem type and severity accurately and its approach leads to clearer CT images compared to other methods. This helps doctors get better images without needing one general fixer that may not work well for all problems.
What this means in practice
- •For medical imaging engineers: Incorporate an AI controller that detects CT scan problems and routes images to best specialized repair models, improving restoration quality with fewer parameters.
- •For radiology it teams: Use AgentCT to automate CT image correction by automatically identifying degradation types and applying appropriate fixes, potentially streamlining clinical workflows.
Authors
Zhihao Chen, Qi Gao, Chuang Niu, Qiegen Liu, Yi Zhang, Hongming Shan
Abstract
Computed tomography (CT) restoration methods often use a single network for low-dose CT (LDCT), sparse-view CT (SVCT), and metal artifact reduction (MAR), despite the distinct physics of these degradations. We propose AgentCT, a vision-language agent that identifies the degradation and routes images to task-specific restoration models. A LoRA-adapted Qwen3-VL-4B controller predicts degradation type and severity, selects a specialist, and reassesses the restored image. The LDCT specialist uses an image-domain diffusion model, whereas the SVCT and MAR specialists combine projection-domain correction, data consistency, differentiable filtered back-projection, and image refinement. We evaluated the controller and specialists separately on patient-disjoint Mayo 2020 abdominal CT data across three severity levels for each degradation. The controller achieved 95.7% accuracy for degradation type and 93.9% for severity, with a 100% JSON parse rate. Using ground-truth degradation labels for routing, AgentCT achieved an overall PSNR/SSIM of 46.18 dB/0.984, compared with 44.93 dB/0.976 for AMIR and 44.29 dB/0.979 for TAMP, and attained the highest PSNR in all nine settings. For SVCT, its dual-domain specialist achieved 46.04 dB with 4.2 million parameters, compared with 44.43 dB for single-task AMIR and 43.57 dB for all-in-one AMIR with 23.5 million parameters. These results support degradation-specific CT restoration with controller-based model selection; evaluation under automatic routing and on independent clinical data remains necessary. Code is available at https://github.com/hao1635/AgentCT.