Real-World Performance of Large Vessel Occlusion Artificial Intelligence-Based Computer-Aided Triage and Notification Algorithms-What the Stroke Team Needs to Know.

PURPOSE: To evaluate the real-world performance of two FDA-approved artificial intelligence (AI)-based computer-aided triage and notification (CADt) detection devices and compare them with the manufacturer-reported performance testing in the instructions for use. MATERIALS AND METHODS: Clinical performance of two FDA-cleared CADt large-vessel occlusion (LVO) devices was retrospectively evaluated at two separate stroke centers. Consecutive "code stroke" CT angiography examinations were included and assessed for patient demographics, scanner manufacturer, presence or absence of CADt result, CADt result, and LVO in the internal carotid artery (ICA), horizontal middle cerebral artery (MCA) segment (M1), Sylvian MCA segments after the bifurcation (M2), precommunicating part of cerebral artery, postcommunicating part of the cerebral artery, vertebral artery, basilar artery vessel segments. The original radiology report served as the reference standard, and a study radiologist extracted the above data elements from the imaging examination and radiology report. RESULTS: At hospital A, the CADt algorithm manufacturer reports assessment of intracranial ICA and MCA with sensitivity of 97% and specificity of 95.6%. Real-world performance of 704 cases included 79 in which no CADt result was available. Sensitivity and specificity in ICA and M1 segments were 85.3% and 91.9%. Sensitivity decreased to 68.5% when M2 segments were included and to 59.9% when all proximal vessel segments were included. At hospital B the CADt algorithm manufacturer reports sensitivity of 87.8% and specificity of 89.6%, without specifying the vessel segments. Real-world performance of 642 cases included 20 cases in which no CADt result was available. Sensitivity and specificity in ICA and M1 segments were 90.7% and 97.9%. Sensitivity decreased to 76.4% when M2 segments were included and to 59.4% when all proximal vessel segments are included. DISCUSSION: Real-world testing of two CADt LVO detection algorithms identified gaps in the detection and communication of potentially treatable LVOs when considering vessels beyond the intracranial ICA and M1 segments and in cases with absent and uninterpretable data.

Current State of Peer Learning in Radiology: A Survey of ACR Members.

PURPOSE: Peer learning (PL) programs seek to improve upon the limitations of score-based peer review and incorporate modern approaches to improve patient care. The aim of this study was to further understand the landscape of PL among members of the ACR in the first quarter of 2022. METHODS: Members of the ACR were surveyed to evaluate the incidence, current practices, perceptions, and outcomes of PL in radiology practice. The survey was administered via e-mail to 20,850 ACR members. The demographic and practice characteristics of the 1,153 respondents (6%) were similar to those of the ACR radiologist membership and correspond to a normal distribution of the population of radiologists and can therefore be described as representative of that population. Therefore, the error range for the results from this survey is ±2.9% at a 95% confidence level. RESULTS: Among the total sample, 610 respondents (53%) currently use PL, and 334 (29%) do not. Users of PL are younger (mode age ranges, 45-54 years for users and 55-64 years for nonusers; P < .01), more likely to be female (29% vs 23%, P < .05), and more likely to practice in urban settings (52% vs 40%, P = .0002). Users of PL feel that it supports an improved culture of safety and wellness (543 of 610 [89%]) and fosters continuous improvement initiatives (523 of 610 [86%]). Users of PL are more likely than nonusers to identify learning opportunities from routine clinical practice (83% vs 50%, P < .00001), engage in programming inclusive of more team members, and implement more practice improvement projects (P < .00001). PL users' net promoter score of 65% strongly suggests that users of PL are highly likely to recommend the program to colleagues. CONCLUSIONS: Radiologists across a breadth of radiology practices are engaged in PL activities, which are perceived to align with emerging principles of improving health care and enhance culture, quality, and engagement.

Get With the Guidelines on MS Imaging by Leveraging Peer Learning.

OBJECTIVES: To achieve consensus on the performance, interpretation and reporting of MS imaging according to up-to-date guidelines using the Peer Learning Methodology. MATERIALS AND METHODS: We utilized the Peer Learning Methodology to engage our clinical and radiology colleagues, review the current guidelines, acheive consensus on imaging techniques and reporting standards. After implementing changes, we collected radiologist feedback on the impact of the optimized images on their interpretation. RESULTS: Survey responders indicated a strong preference for the new protocol in terms of overall image quality, individual lesions conspicuity and confidence in the ability to detect an MS lesion. The new protocol was preferred for both MS diagnosis and MS surveillance in 25 of 28 responses. CONCLUSION: The Peer Learning Methodology is an effective tool to standardize and improve MR imaging quality, interpretation and reporting for Multiple Sclerosis in accordance with current guidelines.

Multi-Energy CT Applications: Problem-Solving in Emergency Radiology.

Multi-energy computed tomography is a technology that is being increasingly used in the emergency room (ER) setting and has many applications that can impact patient care, including virtual monoenergetic imaging and material-specific imaging. It is important for radiologists to understand this technology, and how it can be optimally used in the ER setting.

Leveraging the Peer Learning Conference to Establish and Maintain a Peer Learning Program.

Peer learning is a model of continuous feedback, learning, and improvement that is now well-recognized as a method to address radiologist errors. The peer learning conference is the most public facing cornerstone of any peer learning program, and is critical in establishing and maintaining the "Just Culture" that allows the program to thrive. We describe here our 5-step approach to organizing and moderating peer learning conferences for continued growth and participation over the past 4 years, including: achieving group buy-in, setting expectations, preparing the conference, moderating the conference, and post-conference documentation.

Ischemic stroke.

The goal of stroke imaging is to appropriately select patients for different types of therapeutic management in order to optimize outcome and minimize potential complications. To accomplish this, the radiologist has to evaluate each case and tailor an imaging protocol to fit the patient's needs and best answer the clinical question. This review outlines the routinely used, current neuroimaging techniques and their role in the evaluation of the acute stroke patient. The ability of computed tomography and magnetic resonance imaging to adequately evaluate the infarcted brain parenchyma, the cerebral vasculature, and the ischemic, but potentially viable tissue, often referred to as the "ischemic penumbra," is compared The authors outline an imaging algorithm that has been employed at their institution, and briefly review endovascular therapies that can be used in specific patients for stroke treatment.