AI should be viewed not as a replacement for ultrasound professionals but as a decision-support technology that may improve consistency, efficiency, and diagnostic confidence when carefully validated in real-world clinical settings.
Abstract
Ultrasound imaging is widely used across cardiology, hepatology, obstetrics, breast and thyroid imaging, and emergency care because it is real-time, noninvasive, and relatively accessible. However, its diagnostic performance remains influenced by operator experience, image quality, scanner settings, and interpretation variability. Artificial intelligence (AI) has emerged as a promising support tool for ultrasound, assisting with image acquisition, quality assessment, view classification, segmentation, measurement, lesion characterization, and structured reporting. This narrative review summarizes recent developments in AI-assisted ultrasound imaging, emphasizing its technical foundations, clinical applications, validation challenges, and relevance to Gulf health care systems. Current evidence suggests that AI may improve workflow efficiency, reduce interobserver variability, and support diagnostic decision-making in selected ultrasound tasks, particularly when models are trained and tested on large, diverse data sets. Nevertheless, the clinical readiness of many AI tools remains constrained by retrospective study designs, single-center data sets, limited external validation, vendor-dependent image variability, and insufficient prospective evaluation. These limitations are particularly salient in Gulf health care, where ultrasound services are delivered across heterogeneous public, private, military, and academic institutions that use different equipment, workflows, and operator training backgrounds. Gulf countries are well-positioned to adopt AI-enabled ultrasound because of the ongoing digital health transformation and emerging regulatory frameworks, including the Saudi SFDA guidance and the UAE AI governance initiatives. However, responsible implementation will require region-specific, multicenter, multivendor validation, transparent reporting of model performance and failure cases, clinician training, and privacy-preserving data governance. AI should therefore be viewed not as a replacement for ultrasound professionals but as a decision-support technology that may improve consistency, efficiency, and diagnostic confidence when carefully validated in real-world clinical settings.
The continued integration of AI has the potential to improve diagnostic accuracy, streamline radiological workflows, and support more personalized patient care in the next generation of diagnostic imaging.
Mr. Vishal Walia, Mr. Honey Thakur, Ms. Ashwarya Sharma et al.· PAIN, JOINTS, SPINE· 0 citations
Context and objectives Lung ultrasound (LUS) is a safe low-cost tool that enables diagnosis, monitoring and guidance for interventional procedures at the patient's bedside. However, its expansion is hindered by a lack of training programs and the inherent difficulty of interpreting ultrasound images. In this context, Artificial Intelligence (AI) is emerging as a supportive tool for LUS interpretation, ensuring diagnostic efficacy and mitigating the shortage of experts. This systematic review aims to summarize and analyze recent advances in AI-based tools to support LUS interpretation. Methods A systematic literature search was conducted across Web of Science, IEEE Xplore, and PubMed databases to identify peer-reviewed original journal articles published between 2015 and November 2025 that employed AI for the identification and localization of lung artifacts, anatomical structures, and pathological findings. Risk of bias was assessed using PROBAST + AI. Results Twenty-four studies were included, identifying three main strategies: segmentation (10 studies), object detection (4 studies), and the generation of visual explanations through saliency maps (10 studies). All employed CNN-based architectures. The evaluation metrics used were heterogeneous. The PROBAST + AI assessment showed relevant risk-of-bias concerns, mainly concentrated in the participants and analysis domains. Conclusions The development of AI systems to support LUS interpretation shows high potential; however, current studies exhibit significant heterogeneity in their objectives, methodologies, and evaluation metrics. It is necessary to move towards solutions designed for specific clinical environments and to adopt standardized protocols and evaluations that facilitate their implementation in clinical practice. Systematic Review Registration https://www.crd.york.ac.uk/PROSPERO/view/CRD420261322517, PROSPERO CRD420261322517.
Julia López-Canay, Alberto Fernández-Villar, Cristina Ramos-Hernández et al.· Frontiers in Radiology· 1 citation
This review summarizes AI applications in thyroid ultrasound, including image preprocessing, nodule segmentation, quantitative feature analysis, benign-malignant differentiation, TIRADS optimization and automated reporting, and highlights AI’s potential in enhancing diagnostic consistency and accuracy.
Ye Guo, Tong Zhao, Li-li Zhang et al.· Frontiers in Endocrinology· 0 citations
Emergency radiology operates in a high-acuity, time-sensitive environment where imaging is tightly integrated into real-time clinical decision-making. Growing imaging demand, increasing case complexity, and workforce constraints have intensified pressure on emergency radiologists. Artificial intelligence (AI) has emerged as a potential tool to support imaging prioritization, interpretation, and operational efficiency. However, to meaningfully advance care delivery, the role of AI must be considered beyond algorithm performance, including its implementation, reliability, and real-world clinical impact. In this narrative review, we examine the role of AI across the emergency radiology workflow through three lenses: current capabilities, limitations of the supporting evidence, and practical considerations for clinical implementation. We review applications spanning pre-image acquisition, image acquisition and reconstruction, computer-aided triage and detection, reporting, and follow-up, integrating published evidence with practical insights. Discrepancies between reported and real-world performance, the influence of human-AI interaction on clinical decision-making, and the potential for subtle errors and bias are also discussed. As national regulatory and local governance frameworks continue to evolve, including emerging challenges posed by large language models, gaps remain between reported and real-world AI performance. In emergency radiology, the true impact of AI will depend on how seamlessly and effectively these tools are integrated into existing clinical workflows. Local validation, ongoing performance monitoring, and multidisciplinary institutional oversight are essential to identify performance variability, mitigate biases, and support reliable use in a high-stakes clinical environment.
Zachary D. Miller, William E. King, N. Cross et al.· Seminars in roentgenology· 0 citations
A comprehensive narrative review of current AI/DL applications in ultrasound diagnosis, synthesising evidence across four major clinical domains and identifying recurring limitations across the literature - dataset heterogeneity, limited external/multicentre validation, and interpretability gaps - and outlines directions for future research toward clinically deployable, trustworthy AI-assisted ultrasound diagnosis.
R. Sivakumar, Arati Shahapurkar, J. G et al.· Adolescência e Saúde· 0 citations