The U.S. Food and Drug Administration (FDA) plays an important role in ensuring safety and effectiveness of AI/ML-enabled devices through its regulatory processes. In recent years, there has been an increase in the number of these devices cleared by FDA. This study analyzes 104 FDA-approved ML-enabled medical devices from May 2021 to April 2023, extending previous research to provide a contemporary perspective on this evolving landscape. We examined clinical task, device task, device input and output, ML method and level of autonomy. Most approvals (n = 103) were via the 510(k) premarket notification pathway, indicating substantial equivalence to existing devices. Devices predominantly supported diagnostic tasks (n = 81). The majority of devices used imaging data (n = 99), with CT and MRI being the most common modalities. Device autonomy levels were distributed as follows: 52% assistive (requiring users to confirm or approve AI provided information or decision), 27% autonomous information, and 21% autonomous decision. The prevalence of assistive devices indicates a cautious approach to integrating ML into clinical decision-making, favoring support rather than replacement of human judgment.

The advent of anti-amyloid therapies (AATs) for Alzheimer's disease (AD) has elevated the importance of MRI surveillance for amyloidrelated imaging abnormalities (ARIA) such as microhemorrhages and siderosis (ARIA-H) and edema (ARIA-E). We report a literature review and early quality assurance experience with an FDA-cleared assistive AI tool intended for detection of ARIA in MRI clinical workflows. The AI system improved sensitivity for detection of subtle ARIA-E and ARIA-H lesions but at the cost of a reduction in specificity. We propose a tiered workflow combining protocol harmonization and expert interpretation with AI overlay review. AI-assisted ARIA detection is a paradigm shift that offers great promise to enhance patient safety as disease-modifying therapies for AD gain broader clinical use; however, some pitfalls need to be considered.ABBREVIATIONS: AAT＝ anti-amyloid therapy; ARIA＝ amyloid-related imaging abnormalities, ARIA-H = amyloid-related imaging abnormality-hemorrhage, ARIA-E = amyloid-related imaging abnormality-edema.

Optimal stent deployment assessed by intravascular ultrasound (IVUS) is associated with improved outcomes after percutaneous coronary intervention (PCI). However, IVUS remains underutilized due to its time-consuming analysis and reliance on operator expertise. AVVIGO™+, an FDA-approved artificial intelligence (AI) software, offers automated lesion assessment, but its performance for stent evaluation has not been thoroughly investigated. To assess whether an artificial intelligence-powered software (AVVIGO™+) provides a superior evaluation of IVUS-based stent expansion index (%Stent expansion = Minimum Stent Area (MSA) / Distal reference lumen area) and geographic miss (i.e. >50 % plaque burden - PB - at stent edges) compared to the current gold standard method performed by interventional cardiologists (IC), defined as frame-by-frame visual assessment by interventional cardiologists, selecting the MSA and the reference frame with the largest lumen area within 5 mm of the stent edge, following expert consensus. This retrospective study included 60 patients (47,997 IVUS frames) who underwent IVUS guided PCI, independently analyzed by IC and AVVIGO™+. Assessments included minimum stent area (MSA), stent expansion index, and PB at proximal and distal reference segments. For expansion, a threshold of 80 % was used to define suboptimal results. The time required for expansion analysis was recorded for both methods. Concordance, absolute and relative differences were evaluated. AVVIGO™ + consistently identified lower mean expansion (70.3 %) vs. IC (91.2 %), (p < 0.0001), primarily due to detecting frames with smaller MSA values (5.94 vs. 7.19 mm², p = 0.0053). This led to 25 discordant cases in which AVVIGO™ + reported suboptimal expansion while IC classified the result as adequate. The analysis time was significantly shorter with AVVIGO™ + (0.76 ± 0.39 min) vs IC (1.89 ± 0.62 min) (p < 0.0001), representing a 59.7 % reduction. For geographic miss, AVVIGO™ + reported higher PB than IC at both distal (51.8 % vs. 43.0 %, p < 0.0001) and proximal (50.0 % vs. 43.0 %, p = 0.0083) segments. When applying the 50 % PB threshold, AVVIGO™ + identified PB ≥50 % not seen by IC in 12 cases (6 distal, 6 proximal). AVVIGO™ + demonstrated improved detection of suboptimal stent expansion and geographic miss compared to interventional cardiologists, while also significantly reducing analysis time. These findings suggest that AI-based platforms may offer a more reliable and efficient approach to IVUS-guided stent optimization, with potential to enhance consistency in clinical practice.

The increasing incidence of thyroid nodules (TN) raises concerns about overdiagnosis and overtreatment. This study evaluates the clinical and economic impact of KOIOS, an FDA-approved artificial intelligence (AI) tool for the management of TN. A retrospective analysis was conducted on 176 patients who underwent thyroid surgery between May 2022 and November 2024. Ultrasound images were evaluated independently by an expert and novice operators using the American College of Radiology Thyroid Imaging Reporting and Data System (ACR-TIRADS), while KOIOS provided AI-adapted risk stratification. Sensitivity, specificity, and Receiver-Operating Curve (ROC) analysis were performed. The incremental cost-effectiveness ratio (ICER) was defined based on the number of optimal care interventions (FNAB and thyroid surgery). Both deterministic and probabilistic sensitivity analyses were conducted to evaluate model robustness. KOIOS AI demonstrated similar diagnostic performance to the expert operator (AUC: 0.794, 95% CI: 0.718-0.871 vs. 0.784, 95% CI: 0.706-0.861; p = 0.754) and significantly outperformed the novice operator (AUC: 0.619, 95% CI: 0.526-0.711; p < 0.001). ICER analysis estimated the cost per additional optimal care decision at -€8,085.56, indicating KOIOS as a dominant and cost-saving strategy when considering a third-party payer perspective over a one-year horizon. Deterministic sensitivity analysis identified surgical costs as the main drivers of variability, while probabilistic analysis consistently favored KOIOS as the optimal strategy. KOIOS AI is a cost-effective alternative, particularly in reducing overdiagnosis and overtreatment for benign TNs. Prospective, real-life studies are needed to validate these findings and explore long-term implications.

Artificial intelligence (AI) is increasingly integrated into clinical workflows. The performance of AI in production can diverge from initial evaluations. Post-deployment monitoring (PDM) remains a challenging ingredient of ongoing quality assurance once AI is deployed in clinical production. To develop and evaluate a PDM framework that uses large language models (LLMs) for free-text classification of radiology reports, and human oversight. We demonstrate its application to monitor a commercially vended pulmonary embolism (PE) detection AI (CVPED). We retrospectively analyzed 11,999 CT pulmonary angiography (CTPA) studies performed between 04/30/2023-06/17/2024. Ground truth was determined by combining LLM-based radiology-report classification and the CVPED outputs, with human review of discrepancies. We simulated a daily monitoring framework to track discrepancies between CVPED and the LLM. Drift was defined when discrepancy rate exceeded a fixed 95% confidence interval (CI) for seven consecutive days. The CI and the optimal retrospective assessment period were determined from a stable dataset with consistent performance. We simulated drift by systematically altering CVPED or LLM sensitivity and specificity, and we modeled an approach to detect data shifts. We incorporated a human-in-the-loop selective alerting framework for continuous prospective evaluation and to investigate potential for incremental detection. Of 11,999 CTPAs, 1,285 (10.7%) had PE. Overall, 373 (3.1%) had discrepant classifications between CVPED and LLM. Among 111 CVPED-positive and LLM-negative cases, 29 would have triggered an alert due to the radiologist not interacting with CVPED. Of those, 24 were CVPED false-positives, one was an LLM false-negative, and the framework ultimately identified four true-alerts for incremental PE cases. The optimal retrospective assessment period for drift detection was determined to be two months. A 2-3% decline in model specificity caused a 2-3-fold increase in discrepancies, while a 10% drop in sensitivity was required to produce a similar effect. For example, a 2.5% drop in LLM specificity led to a 1.7-fold increase in CVPED-negative-LLM-positive discrepancies, which would have taken 22 days to detect using the proposed framework. A PDM framework combining LLM-based free-text classification with a human-in-the-loop alerting system can continuously track an image-based AI's performance, alert for performance drift, and provide incremental clinical value.

Artificial intelligence (AI) algorithms and deep learning continue to change the landscape of radiology. New algorithms promise to enhance diagnostic accuracy, improve workflow efficiency, and automate repetitive tasks. This article provides a narrative review of the FDA-cleared AI algorithms which are commercially available in the United States as of late 2024 and targeted toward assessment of abdominopelvic organs and related diseases, evaluates potential advantages of using AI, and suggests future directions for the field.

The exponential rise in the artificial intelligence (AI) tools for medical imaging is profoundly impacting the practice of radiology. With over 1000 FDA-cleared AI algorithms now approved for clinical use-many of them designed for radiologic tasks-the responsibility lies with training institutions to ensure that radiology residents are equipped not only to use AI systems, but to critically evaluate, monitor, respond to their output in a safe, ethical manner. This review proposes a comprehensive framework to integrate AI into radiology residency curricula, targeting both essential competencies required of all residents, optional advanced skills for those interested in research or AI development. Core educational strategies include structured didactic instruction, hands-on lab exposure to commercial AI tools, case-based discussions, simulation-based clinical pathways, teaching residents how to interpret model cards, regulatory documentation. Clinical examples such as stroke triage, Urinary tract calculi detection, AI-CAD in mammography, false-positive detection are used to anchor theory in practice. The article also addresses critical domains of AI governance: model transparency, ethical dilemmas, algorithmic bias, the role of residents in human-in-the-loop oversight systems. It outlines mentorship, faculty development strategies to build institutional readiness, proposes a roadmap to future-proof radiology education. This includes exposure to foundation models, vision-language systems, multi-agent workflows, global best practices in post-deployment AI monitoring. This pragmatic framework aims to serve as a guide for residency programs adapting to the next era of radiology practice.

Artificial intelligence (AI) tools for large vessel occlusion (LVO) detection are increasingly used in acute stroke triage to expedite diagnosis and intervention. However, variability in access and workflow integration limits their potential impact. This study assessed current usage patterns, access disparities, and integration levels across U.S. stroke programs. Cross-sectional, web-based survey of 97 multidisciplinary stroke care providers from diverse institutions. Descriptive statistics summarized demographics, AI tool usage, access, and integration. Two-proportion Z-tests assessed differences across institutional types. Most respondents (97.9%) reported AI tool use, primarily Viz AI and Rapid AI, but only 62.1% consistently used them for triage prior to radiologist interpretation. Just 37.5% reported formal protocol integration, and 43.6% had designated personnel for AI alert response. Access varied significantly across departments, and in only 61.7% of programs did all relevant team members have access. Formal implementation of the AI detection tools did not differ based on the certification (z = -0.2; <i>p</i> = 0.4) or whether the program was academic or community-based (z =-0.3; <i>p</i> = 0.3). AI-enabled LVO detection tools have the potential to improve stroke care and patient outcomes by expediting workflows and reducing treatment delays. This survey effectively evaluated current utilization of these tools and revealed widespread adoption alongside significant variability in access, integration, and workflow standardization. Larger, more diverse samples are needed to validate these findings across different hospital types, and further prospective research is essential to determine how formal integration of AI tools can enhance stroke care delivery, reduce disparities, and improve clinical outcomes.

Scanner-related changes in data quality are common in medical imaging, yet monitoring their impact on diagnostic AI performance remains challenging. In this study, we performed standardized consistency testing of an FDA-cleared and CE-marked AI for triage and notification of intracranial aneurysms across changes in image data quality caused by dose and image reconstruction. Our assessment was based on repeated examinations of a head CT phantom designed for AI evaluation, replicating a patient with three intracranial aneurysms in the anterior, middle and posterior circulation. We show that the AI maintains stable performance within the medium dose range but produces inconsistent results at reduced dose and, unexpectedly, at higher dose when filtered back projection is used. Data quality standards required for AI are stricter than those for neuroradiologists, who report higher aneurysm visibility rates and experience performance degradation only at substantially lower doses, with no decline at higher doses.

PurposeWe aimed to investigate the external validation and performance of an FDA-approved deep learning model in labeling intracranial hemorrhage (ICH) cases on a real-world heterogeneous clinical dataset. Furthermore, we delved deeper into evaluating how patients' risk factors influenced the model's performance and gathered feedback on satisfaction from radiologists of varying ranks.MethodsThis prospective IRB approved study included 5600 non-contrast CT scans of the head in various clinical settings, that is, emergency, inpatient, and outpatient units. The patients' risk factors were collected and tested for impacting the performance of DL model utilizing univariate and multivariate regression analyses. The performance of DL model was contrasted to the radiologists' interpretation to determine the presence or absence of ICH with subsequent classification into subcategories of ICH. Key metrics, including accuracy, sensitivity, specificity, positive predictive value, and negative predictive value, were calculated. Receiver operating characteristics curve, along with the area under the curve, were determined. Additionally, a questionnaire was conducted with radiologists of varying ranks to assess their experience with the model.ResultsThe model exhibited outstanding performance, achieving a high sensitivity of 89% and specificity of 96%. Additional performance metrics, including positive predictive value (82%), negative predictive value (97%), and overall accuracy (94%), underscore its robust capabilities. The area under the ROC curve further demonstrated the model's efficacy, reaching 0.954. Multivariate logistic regression revealed statistical significance for age, sex, history of trauma, operative intervention, HTN, and smoking.ConclusionOur study highlights the satisfactory performance of the DL model on a diverse real-world dataset, garnering positive feedback from radiology trainees.