cs.CVNov 8, 2026

AgentCT: A Vision-Language Agent for Universal CT Imaging

Authors: Zhihao Chen, Qi Gao, Chuang Niu, Qiegen Liu, Yi Zhang, Hongming Shan

Organizations: Institute of Science and Technology for Brain-inspired Intelligence, Fudan University, Shanghai 200433, China · School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin 150001, China · School of Information Engineering, Nanchang University, Nanchang 330031, China · School of Cyber Science and Engineering, Sichuan University, Chengdu 610065, China

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.

Figures & tables

Explore similar work

CardsList
  1. TIR-Agent: Training an Explorative and Efficient Agent for Image Restoration

    Mar 29, 2026Guoli Jia, Yisheng Zhang, Haote Hu +11Tool-Using Vision-Language AgentsImage Restoration

  2. CT-DegradBench: A Physics-Informed Benchmark for CT Degradation Detection and Severity Estimation

    May 14, 2026Yousra Nabila Taifour, Marouane Tliba, Zuheng Ming +9Image Quality AssessmentComputed Tomography