An Explainable Agentic AI Framework for Uncertainty-Aware and Abstention-Enabled Acute Ischemic Stroke Imaging Decisions

TL;DR

This paper introduces an explainable AI framework for stroke imaging that explicitly models uncertainty and allows abstention, enhancing safety and transparency in high-stakes clinical decisions.

Contribution

It presents a modular agentic AI system that incorporates uncertainty estimation and abstention mechanisms, emphasizing safety and interpretability over mere accuracy improvements.

Findings

Uncertainty-driven abstention occurs in ambiguous regions.

Visual explanations support decision and abstention processes.

Framework prioritizes safety and transparency in clinical AI applications.

Abstract

Artificial intelligence models have shown strong potential in acute ischemic stroke imaging, particularly for lesion detection and segmentation using computed tomography and magnetic resonance imaging. However, most existing approaches operate as black box predictors, producing deterministic outputs without explicit uncertainty awareness or structured mechanisms to abstain under ambiguous conditions. This limitation raises serious safety and trust concerns in high risk emergency radiology settings. In this paper, we propose an explainable agentic AI framework for uncertainty aware and abstention enabled decision support in acute ischemic stroke imaging. The framework follows a modular agentic pipeline in which a perception agent performs lesion aware image analysis, an uncertainty estimation agent computes slice level predictive reliability, and a decision agent determines whether to issue a prediction or abstain based on predefined uncertainty thresholds. Unlike prior stroke imaging systems that primarily focus on improving segmentation or classification accuracy, the proposed framework explicitly prioritizes clinical safety, transparency, and clinician aligned decision behavior. Qualitative and case based analyses across representative stroke imaging scenarios demonstrate that uncertainty driven abstention naturally emerges in diagnostically ambiguous regions and low information slices. The framework further integrates visual explanation mechanisms to support both predictive and abstention decisions, addressing a key limitation of existing uncertainty aware medical imaging systems. Rather than introducing a new performance benchmark, this work presents agentic control, uncertainty awareness, and selective abstention as essential design principles for developing safe and trustworthy medical imaging AI systems.