Artificial intelligence (AI) is rapidly moving from an experimental phase to an implementation phase in many fields, including medicine. The combination of improved availability of large datasets, increasing computing power, and advances in learning algorithms has created major performance breakthroughs in the development of AI applications. In the last 5 years, AI techniques known as deep learning have delivered rapidly improving performance in image recognition, caption generation, and speech recognition. Radiology, in particular, is a prime candidate for early adoption of these techniques. It is anticipated that the implementation of AI in radiology over the next decade will significantly improve the quality, value, and depth of radiology's contribution to patient care and population health, and will revolutionize radiologists' workflows. The Canadian Association of Radiologists (CAR) is the national voice of radiology committed to promoting the highest standards in patient-centered imaging, lifelong learning, and research. The CAR has created an AI working group with the mandate to discuss and deliberate on practice, policy, and patient care issues related to the introduction and implementation of AI in imaging. This white paper provides recommendations for the CAR derived from deliberations between members of the AI working group. This white paper on AI in radiology will inform CAR members and policymakers on key terminology, educational needs of members, research and development, partnerships, potential clinical applications, implementation, structure and governance, role of radiologists, and potential impact of AI on radiology in Canada.

Objective: To determine whether there is an association between carotid artery web and ischemic stroke.Methods: This was a single-center, age-and sex-matched, case-control study. Cases were consecutive patients with anterior circulation ischemic stroke of undetermined etiology (Trial of Org 10172 in Acute Stroke Treatment [TOAST] classification). Controls were consecutive patients with cerebral aneurysms, arteriovenous malformations, or primary intracerebral hemorrhages. Additional inclusion criteria were age ,60 years and CT angiography of the neck. Two neuroradiologists diagnosed webs according to previously published criteria. One neuroradiologist also assessed for nonstenotic atherosclerotic plaque (carotid wall thickness $3 mm or intramural calcification). We used conditional logistic regression to estimate the odds ratio between carotid web and ischemic stroke and its 95% confidence interval.Results: Fifty-three of 62 cases (85%) were matched by age (within 1 year) and by sex to 102 controls. There was a carotid web in 4 of 53 cases (9.4%) vs 1 of 102 controls (1.0%, odds ratio 5 8.0, 95% confidence interval 5 1.2-67, p 5 0.032). There was no significant difference in the prevalence of nonstenotic carotid atherosclerotic plaque between the case and control groups. There was agreement on diagnosis of web for 163 of 164 patients (99%) and 7 of 8 webs (88%), and the Cohen k for interobserver agreement was 0.93. Conclusions:There is an association between carotid artery web and ischemic stroke in patients who lack an alternative cause of stroke. Carotid web may be an underappreciated risk factor for stroke. Therapeutic decision making for secondary stroke prevention relies on determining the cause of the initial transient ischemic attack or ischemic stroke. However, in one-third of cases, there is no apparent cause. 1A potentially underrecognized source of cerebral embolus is a carotid artery web. A carotid web is a thin, membrane-like shelf of tissue that extends from the wall of the carotid artery into the lumen, usually at the origin of the internal carotid artery. Carotid webs were first described 4 decades ago in a study of catheter angiograms at the Massachusetts General Hospital, 2 and subsequent case reports have added z50 cases to the literature. It is hypothesized that blood stasis along the downstream surface of a web may lead to thrombus formation and thromboembolic stroke.3 However, evidence of an association between carotid web and ischemic stroke has been only anecdotal.We conducted a case-control study to determine whether there is an association between carotid artery web and ischemic stroke.

Large but nonstenotic carotid artery plaque is considerably more common ipsilateral than contralateral to cryptogenic stroke, suggesting that nonstenotic plaque is an underrecognized cause of stroke. We measured plaque size using CT angiography, a method that could be easily implemented in clinical practice.