Horst, Kelly

The field of radiology is experiencing rapid adoption of large language models (LLMs), yet their tendency to generate hallucinations (plausible but incorrect information) remains a significant barrier to trust. This comprehensive review evaluates emerging agentic artificial intelligence (AI) approaches, including multi-agent role-based systems, retrieval-augmented generation (RAG), and uncertainty quantification, to assess their potential for reducing hallucinations in radiology workflows. Evidence from 2024 to 2025 demonstrates that agentic AI can improve diagnostic accuracy and reduce error rates, though these methods remain computationally demanding and lack comprehensive clinical validation. Multi-agent frameworks enable cross-validation through role-based specialization and systematic workflow orchestration, while RAG strategies enhance accuracy by grounding responses in verified medical literature. Within multi-agent systems, uncertainty quantification enables agents to communicate confidence levels to one another, allowing them to appropriately weigh each other’s contributions during collaborative analysis. While multi-agent frameworks and RAG strategies show significant promise, practical deployment will require careful integration with human oversight, robust evaluation metrics tailored to medical imaging tasks, and regulatory adaptation to ensure safe clinical use in diverse patient populations and imaging modalities.

The NCCN Clinical Practice Guidelines (NCCN Guidelines) for Wilms Tumor (WT; nephroblastoma) cover strategies for the screening, diagnosis, and treatment of WT, which is the most frequent primary kidney tumor in children. WT can generally be separated into 2 histology types: favorable histology WT and anaplastic WT. Five-year survival is high for children with favorable histology WT who receive appropriate treatment; however, survival rates are much lower for patients who present with higher stage diffuse anaplastic WT. Treatment of WT can range from surgery alone to surgery plus intensive chemotherapy and radiation depending on whether the tumor is unilateral or bilateral, histology, and local stage. The goal of therapy is to maximize cure while minimizing long-term toxicities. The content featured in this issue covers the NCCN panel’s recommendations for overall management of both favorable histology WT and anaplastic WT.

Abstract The benefits of photon-counting detector (PCD) CT include improved spatial resolution, increased radiation dose efficiency, and the elimination of electronic noise. Unlike traditional energy-integrating-detector (EID) CT systems, PCDs have inherent spectral capabilities, which support “always-on” dual energy and multi-energy imaging acquisition. PCD-CT directly converts X-ray photons into electrical signals and captures their individual energy levels. Current commercially available PCD-CT scanners, all from one manufacturer, include 2 models that incorporate dual-source geometry. This innovation is particularly advantageous for paediatric imaging by enabling rapid scans that reduce motion artifact and therefore the need for sedation and can now be combined in the current model with multi-energy imaging or ultra-high-resolution acquisition. This review article explores how the technical benefits of PCD CT improve the diagnostic quality of images and opens the field of paediatric radiology up to future opportunities for research and new applications.

This article addresses clinical challenges of photon-counting detector (PCD) CT in pediatric patients by outlining fundamental terminology, explaining technical aspects, and providing protocol guidance for the first commercially available PCD CT scanner.