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.

Mucinous neoplasms of the appendix are a heterogeneous group of neoplasms ranging from simple mucoceles to complex pseudomyxoma peritonei. Considerable controversy exists on their pathologic classification and nomenclature. Clear understanding of the histopathologic diversity of these neoplasms helps in establishing proper communication between the radiologist, the pathologist and the surgeon. In this article, we present a brief discussion of the current taxonomy and nomenclature of mucinous neoplasms of the appendix followed by a review of their imaging features. Important points including the significance of identifying extra-appendiceal mucin at imaging, the new classification of pseudomyxoma peritonei into low- and high-grade varieties and the significance of simultaneous ovarian and appendiceal neoplasms are highlighted.

This first systematic ultrasound evaluation of thyroid hemiagenesis in normal children established a prevalence of thyroid hemiagenesis of 0.2% and confirmed the female predominance and higher incidence of agenesis of the left lobe.

Purpose of review:Use of gadolinium-based contrast agents (GBCA) in renal impairment is controversial, with physician and patient apprehension in acute kidney injury (AKI), chronic kidney disease (CKD), and dialysis because of concerns regarding nephrogenic systemic fibrosis (NSF). The position that GBCA are absolutely contraindicated in AKI, category G4 and G5 CKD (estimated glomerular filtration rate [eGFR] < 30 mL/min/1.73 m2), and dialysis-dependent patients is outdated and may limit access to clinically necessary contrast-enhanced magnetic resonance imaging (MRI) examinations. This review and clinical practice guideline addresses the discrepancy between existing Canadian guidelines regarding use of GBCA in renal impairment and NSF.Sources of information:Published literature (including clinical trials, retrospective cohort series, review articles, and case reports), online registries, and direct manufacturer databases were searched for reported cases of NSF by class and specific GBCA and exposed patient population.Methods:A comprehensive review was conducted identifying cases of NSF and their association to class of GBCA, specific GBCA used, patient, and dose (when this information was available). Based on the available literature, consensus guidelines were developed by an expert panel of radiologists and nephrologists.Key findings:In patients with category G2 or G3 CKD (eGFR ≥ 30 and < 60 mL/min/1.73 m2), administration of standard doses of GBCA is safe and no additional precautions are necessary. In patients with AKI, with category G4 or G5 CKD (eGFR < 30 mL/min/1.73 m2) or on dialysis, administration of GBCA should be considered individually and alternative imaging modalities utilized whenever possible. If GBCA are necessary, newer GBCA may be administered with patient consent obtained by a physician (or their delegate) citing an exceedingly low risk (much less than 1%) of developing NSF. Standard GBCA dosing should be used; half or quarter dosing is not recommended and repeat injections should be avoided. Dialysis-dependent patients should receive dialysis; however, initiating dialysis or switching from peritoneal to hemodialysis to reduce the risk of NSF is unproven. Use of a macrocyclic ionic instead of macrocyclic nonionic GBCA or macrocyclic instead of newer linear GBCA to further prevent NSF is unproven. Gadopentetate dimeglumine, gadodiamide, and gadoversetamide remain absolutely contraindicated in patients with AKI, those with category G4 or G5 CKD, or those on dialysis. The panel agreed that screening for renal disease is important but less critical when using macrocyclic and newer linear GBCA. Monitoring for and reporting of potential cases of NSF in patients with AKI or CKD who have received GBCA is recommended.Limitations:Limited available literature (number of injections and use in renal impairment) regarding the use of gadoxetate disodium. Limited, but growing and generally high-quality, number of clinical trials evaluating GBCA administration in renal impairment. Limited data regarding the t...

Large tumor size, the presence of peritumoral neovascularity, and larger peritumoral vessels are features that are more commonly associated with sarcomatoid RCCs than with clear cell RCCs. Sarcomatoid RCCs are also more heterogeneous by texture analysis than clear cell RCCs.

We confirm the strong association between nephrogenic systemic fibrosis and gadolinium-based contrast administration. Although the use of high doses of gadolinium and the occurrence of chronic renal failure have been implicated in other reports, several of our patients received standard doses of gadolinium, and two had transient acute renal failure before diagnosis. Most patients had mild or moderate symptoms. Nephrogenic systemic fibrosis developed in 2.9% of patients undergoing long-term dialysis who received gadolinium-based contrast material but in none of the long-term dialysis patients who did not receive gadolinium-based contrast material.

Purpose: To assess the ability of magnetic resonance imaging (MRI) to diagnose extraprostatic extension (EPE) in prostate cancer. Materials and Methods: With Institutional Review Board (IRB) approval, 149 men with 170 0.5 mL tumors underwent preoperative 3T MRI followed by radical prostatectomy (RP) between 2012-2015. Two blinded radiologists (R1/R2) assessed tumors using Prostate Imaging Reporting and Data System (PI-RADS) v2, subjectively evaluated for the presence of EPE, measured tumor size, and length of capsular contact (LCC). A third blinded radiologist, using MRI-RP-maps, measured whole-lesion: apparent diffusion coefficient (ADC) mean/centile and histogram features. Comparisons were performed using chi-square, logistic regression, and receiver operator characteristic (ROC) analysis. Optimal SENS/SPEC for diagnosis of EPE were: size 15 mm 5 67.7/66.7% and LCC 11 mm 5 84.9/44.8%. 10 th -centile ADC and ADC entropy were both associated with EPE (P 5 0.02 and < 0.001), with AU-ROC 5 0.56 (0.47-0.65) and 0.76 (0.69-0.83), respectively. Optimal SENS/SPEC for diagnosis of EPE with entropy 6.99 was 63.3/75.0%. 25 th -centile ADC trended towards being significantly lower with EPE (P 5 0.06) with no difference in other ADC metrics (P 5 0.25-0.88). Size, LCC, and ADC entropy improved sensitivity but reduced specificity compared with subjective analysis with no difference in overall accuracy (P 5 0.38). Conclusion: Measurements of tumor size, capsular contact, and ADC entropy improve sensitivity but reduce specificity for diagnosis of EPE compared to subjective assessment. Level of Evidence: 3 Technical Efficacy: Stage 2

Use of gadolinium-based contrast agents (GBCAs) in renal impairment is controversial, with physician and patient apprehension in acute kidney injury (AKI), chronic kidney disease (CKD), and dialysis because of concerns regarding nephrogenic systemic fibrosis (NSF). The position that GBCAs are absolutely contraindicated in AKI, CKD stage 4 or 5 (estimated glomerular filtration rate [eGFR] <30 mL/min/1.73 m) and dialysis-dependent patients is outdated, and may limit access to clinically necessary contrast-enhanced MRI examinations. Following a comprehensive review of the literature and reported NSF cases to date, a committee of radiologists and nephrologists developed clinical practice guidelines to assist physicians in making decisions regarding GBCA administrations. In patients with mild-to-moderate CKD (eGFR ≥30 and <60 mL/min/1.73 m), administration of standard doses of GBCA is safe and no additional precautions are necessary. In patients with AKI, with severe CKD (eGFR <30 mL/min/1.73 m), or on dialysis, administration of GBCAs should be considered individually and alternative imaging modalities utilized whenever possible. If GBCAs are necessary, newer GBCAs may be administered with patient consent obtained by a physician (or their delegate), citing an exceedingly low risk (much less than 1%) of developing NSF. Standard GBCA dosing should be used; half or quarter dosing is not recommended and repeat injections should be avoided. Dialysis-dependent patients should receive dialysis; however, initiating dialysis or switching from peritoneal to hemodialysis to reduce the risk of NSF is unproven. Use of a macrocyclic ionic instead of macrocyclic nonionic GBCA or macrocyclic instead of newer linear GBCA to further prevent NSF is unproven. Gadopentetate dimeglumine, gadodiamide, and gadoversetamide remain absolutely contraindicated in patients with AKI, with stage 4 or 5 CKD, or on dialysis. The panel agreed that screening for renal disease is important but less critical when using macrocyclic and newer linear GBCAs. Monitoring for and reporting of potential cases of NSF in patients with AKI or CKD who have received GBCAs is recommended.