Policy-Driven CT-Agent: Modeling Phase-Aware Diagnostic Control for Clinically Consistent CT Reasoning

2026-07-12

AI Summary

This work addresses a critical limitation in current AI systems for CT-based diagnosis, which typically assume the availability of all contrast-enhancement phases and thus fail to reflect real-world clinical workflows where non-contrast, arterial, or venous phases are dynamically selected based on preliminary findings to minimize radiation exposure and align with diverse diagnostic protocols. To bridge this gap, the authors propose a strategy-driven CT agent that integrates a Clinical Structure Abstraction Module (CSAM) to unify multi-phase image representations and a Knowledge-Guided Diagnostic Control Model (KDCM) to evaluate phase sufficiency and request additional phases only when necessary. Experimental results on LIDC, MCT-LTDiag, and a private dataset demonstrate that the proposed approach significantly outperforms existing methods relying on static phase assumptions, achieving both strong clinical consistency and adaptability across varying guidelines.

Abstract

Computed Tomography (CT) diagnosis often relies on dynamic selection of imaging phases, such as non-contrast, arterial, or venous phases, based on preliminary findings, clinical suspicion, and diagnostic guidelines. This phase-wise decision process is critical for reducing unnecessary radiation exposure while supporting timely staging and treatment planning. However, phase-selection protocols can vary across hospitals, regions, and guidelines, while most existing CT-based AI methods assume that all phases are available and focus on static tasks under a fixed imaging phase, failing to model whether additional phases are required. This limitation stems from heterogeneous multi-phase representations, the need for knowledge-guided phase control beyond visual cues, and the lack of supervision for phase-sufficiency decisions in existing datasets. To address these challenges, we propose Policy-Driven CT-Agent (PD-CTAgent) for clinically consistent CT phase selection and diagnostic reasoning. PD-CTAgent introduces a Clinical Structure Abstraction Module (CSAM) to harmonize heterogeneous CT phases into a unified, phase-aware evidence representation. Based on this representation, a Knowledge-Guided Diagnostic Control Model (KDCM) evaluates phase sufficiency and iteratively requests additional phases when necessary. The policy-driven agent design further allows PD-CTAgent to flexibly follow different institutional, regional, or guideline-specific diagnostic protocols. Together, PD-CTAgent bridges static CT analysis and real-world clinical workflows. Experiments on two public datasets, LIDC and MCT-LTDiag, and one private dataset demonstrate its effectiveness and clinical consistency. Code will be made public upon acceptance.

Problem

• CT phase selection
• diagnostic reasoning
• clinical consistency
• multi-phase CT
• phase sufficiency

Innovation

• phase-aware reasoning
• policy-driven agent
• clinical structure abstraction
• knowledge-guided control
• multi-phase CT diagnosis