Canadian Association of Radiologists Statement on Environmental Sustainability in Medical Imaging.

Immediate and strategic action is needed to improve environmental sustainability and reduce the detrimental effects of climate change. Climate change is already adversely affecting the health of Canadians related to worsening air pollution and wildfire smoke, increasing frequency and intensity of extreme weather events, and expansion of vector-borne and infectious illnesses. On one hand, radiology contributes to the climate crisis by generating greenhouse gas emissions and waste during the production, manufacture, transportation, and use of medical imaging equipment and supplies. On the other hand, radiology departments are also susceptible to equipment and infrastructure damage from flooding, extreme temperatures, and power failures, as well as workforce shortages due to injury and illness, potentially disrupting radiology services and increasing costs. The Canadian Association of Radiologists' (CAR) advocacy for environmentally sustainable radiology in Canada encompasses both minimizing the detrimental effects that delivery of radiology services has on the environment and optimizing the resilience of radiology departments to increasing health needs and changing patterns of disease on imaging related to climate change. This statement provides specific recommendations and pathways to help guide radiologists, medical imaging leadership teams, industry partners, governments, and other key stakeholders to transition to environmentally sustainable, net-zero, and climate-resilient radiology organizations. Specific consideration is given to unique aspects of medical imaging in Canada. Finally, environmentally sustainable radiology programs, policies, and achievements in Canada are highlighted.

Economic Evaluation of Telerobotic Ultrasound Technology to Remotely Provide Ultrasound Services in Rural and Remote Communities.

INTRODUCTION: Telerobotic ultrasound technology allows radiologists and sonographers to remotely provide ultrasound services in underserved areas. This study aimed to compare costs associated with using telerobotic ultrasound to provide ultrasound services in rural and remote communities to costs associated with alternate models. METHODS: A cost-minimization approach was used to compare four ultrasound service delivery models: telerobotic ultrasound (Model 1), telerobotic ultrasound and an itinerant sonographer (Model 2), itinerant sonographer without telerobotic ultrasound (Model 3), and travel to another community for all exams (Model 4). In Models 1-3, travel was assumed when exams could not be successfully performed telerobotically or by an itinerant sonographer. A publicly funded healthcare payer perspective was used for the reference case and a societal perspective was used for a secondary non-reference case. Costs were based on the literature and experience using telerobotic ultrasound in Saskatchewan, Canada. Costs were expressed in 2020 Canadian dollars. RESULTS: Average cost per ultrasound exam was $342, $323, $368, and $478 for Models 1, 2, 3, and 4, respectively, from a publicly funded healthcare payer perspective, and $461, $355, $447, and $849, respectively, from a societal perspective. In one-way sensitivity analyses, Model 2 was the lowest cost from a payer perspective for communities with population >2075 people, distance >350 km from the nearest ultrasound facility, or >47% of the population eligible for publicly funded medical transportation. CONCLUSION: Health systems may wish to consider solutions such as telerobotic ultrasound and itinerant sonographers to reduce healthcare costs and improve access to ultrasound in rural and remote communities.

Bringing Radiology Education to a New Reality: A Pilot Study of Using Virtual Reality as a Remote Educational Tool.

Purpose: We investigated virtual reality (VR) during a 2-week, undergraduate, radiology elective to determine if it improved learning outcomes and user satisfaction. Methods: Eighteen students enrolled between August 2021 and February 2022. Each student had a collaborative Zoom teaching session with a preceptor using a Picture Archive and Communications System (PACS)-like viewing system Online DICOM Image Navigator (ODIN), followed by a teaching session using a VR, Digital Imaging and Communications in Medicine (DICOM) viewer (SieVRt). After each teaching session, the students independently reviewed 8 imaging cases and completed case related questions. The students completed a survey, rating their subjective experiences using ODIN and SieVRt. Results: There was no difference in total test scores between the two learning strategies. However, students did perform statistically better on two of five questions designed to test the detection/measurement capabilities of SieVRt vs ODIN. Students stated that they preferred using SieVRt over ODIN and agreed that they were able to view subtle imaging findings and abnormalities better using SieVRt. However, students found that some of the functions of SieVRt (measuring angles/lengths, and multitasking) were difficult. There were technical challenges with VR and minor undesirable physical effects (dizziness, nausea, etc.). Conclusions: Virtual reality has the potential to enhance radiology education by providing an immersive and engaging experience. Objectively, students were able to perform two tasks better with SieVRt. Subjectively, the VR platform received favourable reviews from students for a variety of features. There were reported technical and physical challenges related to using VR. Future developments in VR systems should focus on improving the user experience.

Complications Associated With Totally Implanted Venous Access Devices in the Arm Versus the Chest: A Short-Term Retrospective Study.

PURPOSE: To retrospectively compare complications for totally implanted venous access devices (TIVADs or ports) in the arm vs. the chest. One participating institution implanted all TIVADs in the arm, whereas the other institution implanted them in the chest. METHODS: Subjects were consecutive patients > 18 years with a device inserted between July 2017 and January 2019 at either Hospital A, where all devices were implanted in the arm, or at Hospital B, where all devices were implanted in the chest. Complications (rates/1,000 catheter-days and frequencies) were compared between the arm and chest locations. RESULTS: 201 arm devices (71% female, mean age 59.4 years) and 203 chest devices (66% female, mean age 61.5 years) were assessed. Overall complication rates did not differ between the arm and chest [arm: 30 complications per 56,938 catheter-days (0.530/1,000 catheter-days) vs. chest: 47 complications per 63,324 catheter-days (0.742/1,000 catheter-days), p-value 0.173]. Periprocedural complications and mechanical malfunction also did not differ. Although prophylactic antibiotic use was higher in the chest (79.3% vs. 1.50%, p-value < 0.0001), infection rates did not differ. Arm venous thrombosis was significantly higher in the arm cohort (0.205 vs. 0.017/1,000 catheter-days, p-value 0.003) and pulmonary thromboembolism in the chest cohort (0.269 vs 0.056/1,000 catheter-days, p-value 0.002). CONCLUSIONS: While arm venous thrombosis was higher in the arm and pulmonary thromboembolism in the chest cohort, other complications were similar. Antibiotic use was more frequent in the chest cohort, while infection rates remained similar in both cohorts.

The future of artificial intelligence in medicine: Medical-legal considerations for health leaders.

Artificial Intelligence (AI) is becoming increasingly common in healthcare and has potential to improve the efficiency and quality of healthcare services. As the utility of AI expands, medical-legal questions arise regarding the possible legal implications of incorporating AI into clinical practice. Particularly, the unique black box nature of AI brings distinct challenges. There is limited guidance addressing liability when AI is used in clinical practice, and traditional legal principles present limitations when applied to novel uses of AI. Comprehensive solutions to address the challenges of AI have not been well established in North America. As AI continues to evolve in healthcare, appropriate guidance from professional regulatory bodies may help the medical field realize AI's utility and encourage its safe use. As the options for AI in medicine evolve, physicians and health leaders would be prudent to consider the evolving medical-legal context regarding use of AI in clinical practices and facilities.

Telerobotic Sonography for Remote Diagnostic Imaging: Narrative Review of Current Developments and Clinical Applications.

Access to sonographers and sonologists is limited in many communities around the world. Telerobotic sonography (robotic ultrasound) is a new technology to increase access to sonography, providing sonographers and sonologists the ability to manipulate an ultrasound probe from a distant location and remotely perform ultrasound examinations. This narrative review discusses the development of telerobotic ultrasound systems, clinical studies evaluating the feasibility and diagnostic accuracy of telerobotic sonography, and emerging use of telerobotic sonography in clinical settings. Telerobotic sonography provides an opportunity to provide real-time ultrasound examinations to underserviced rural and remote communities to increase equity in the delivery of diagnostic imaging.

Flipping the Passive Radiology Elective by Including Active Learning.

OBJECTIVES: Exposure to radiology in undergraduate medical education is often restricted by other curriculum demands. Designing an effective radiology elective for medical students who choose to supplement their education can be challenging as it is often a passive observership-style elective. In this study, we examined the impact of incorporating an online learning platform and electronic book into radiology electives to stimulate active learning. MATERIALS AND METHODS: We enrolled 23 students who pursued a 2-week diagnostic radiology elective at our institution. Their radiology knowledge prior to the elective was assessed using 2 pretests. Students had opportunities to work with radiologists to review clinical imaging, attend academic rounds, and learn from the online learning resources. Their knowledge after the elective was assessed by readministering the 2 tests as "posttests." Students also ranked their perception of the elective experience and educational resources on a Likert scale from 1 to 5. RESULTS: There were statistically significant increases of 13.4% (P < .0001) in mean test 1 scores and 6.8% in mean test 2 scores (P = .001). Students also had favorable perceptions of the radiology elective experience and rated the electronic book (median score: 5 of 5) and online learning platform (4.5 of 5) as valuable educational resources. CONCLUSION: The implementation of an electronic book and online learning platform improved knowledge in radiology and resulted in positive student perceptions of the elective experience. This supports the use of online resources to facilitate independent self-learning for future radiology electives.

Comparing Two Resources Used to Teach Pulmonary Patterns for a Flipped Veterinary Radiology Course.

The flipped classroom has been gaining momentum within medical education circles. Pre-class assignments are an important component of this pedagogical approach. In this study, a section of the introductory course to veterinary medical imaging was taught using a flipped classroom, and the effectiveness of two different pre-classroom assignments was evaluated. The pre-classroom assignments consisted of either short videos or readings. Both had similar content, which included basic information about pulmonary patterns of disease on chest radiographs. Learning outcomes were assessed by in-classroom and final examination questions. Student learning self-assessments and student satisfaction were also evaluated via an online survey. Students in the video group answered more of the in-classroom questions correctly (71% video vs. 63% reading group; p = .01) and had higher scores on the final examination (83% video vs. 75% reading group; p = .02). There was also a higher student satisfaction with the videos versus the reading assignment. However, we found no significant difference in the student self-assessments of learning or participation in class. An additional finding of this study related to the ongoing difficulties students were having with the learning objectives, including differentiating a pathological process from a normal, or normal variant, recognizing the different pulmonary patterns, and developing a differential diagnoses list, despite the pre-classroom assignments and large group learning sessions. This speaks to the difficulty in developing confidence in pulmonary pattern recognition on chest radiographs, a skill that requires considerable training and time investment.

Randomized Clinical Trial Evaluating Complications and Complication-Related Removal of Arm-Situated Power-Injectable and Non-Power-Injectable Totally Implanted Venous Access Devices among Cancer Patients.

PURPOSE: To evaluate the hypothesis that power-injectable (PI) totally implanted venous access devices (TIVADs) situated in the arm are associated with more frequent complications and complication-related removal than non-power-injectable (NPI) arm TIVADs among adult cancer patients. MATERIALS AND METHODS: In this single-center trial, 211 adult chemotherapy patients were randomized to receive either a PI or a NPI arm TIVAD. Follow-up involved a standardized telephone interview 1 week after insertion, followed by a chest X-ray, arm X-ray, and Doppler ultrasound at 3 months and 12 months. Online complication reporting was also provided by patients and care providers for a minimum of 1 year. The primary end point was removal for port-related complications; the secondary end point was the occurrence of any port-related complication. RESULTS: Forty-two complications occurred (19.9% of patients), precipitating the removal of 6 PI ports and 7 standard ports. Time-to-removal did not differ between TIVAD types (hazard ratio 0.75, 95% confidence interval [CI] 0.25-2.24; P = .61). Complications were related to thrombosis, infection, or mechanical issues, with no statistical difference between groups for overall occurrence (23.1% vs 17.0%, odds ratio 1.47, 95% CI 0.74-2.92; P = .27); however, by type of complication, thrombosis occurred more frequently among PI TIVAD patients (15.2% vs 6.1%, odds ratio 2.79, 95% CI 1.04-7.44; P = .03). CONCLUSIONS: There was no difference in port-related complication occurrence or complication-related removal when using the arm PI port compared with the NPI port among cancer patients.

A Crossover Comparison of Standard and Telerobotic Approaches to Prenatal Sonography.

OBJECTIVES: To determine the feasibility of a telerobotic approach to remotely perform prenatal sonographic examinations. METHODS: Thirty participants were prospectively recruited. Participants underwent a limited examination (assessing biometry, placental location, and amniotic fluid; n = 20) or a detailed examination (biometry, placental location, amniotic fluid, and fetal anatomic survey; n = 10) performed with a conventional ultrasound system. This examination was followed by an equivalent examination performed with a telerobotic ultrasound system, which enabled sonographers to remotely control all ultrasound settings and fine movements of the ultrasound transducer from a distance. Telerobotic images were read independently from conventional images. RESULTS: The mean gestational age ± SD of the 30 participants was 22.9 ± 5.3 weeks. Paired-sample t tests showed no statistically significant difference between conventional and telerobotic measurements of fetal head circumference, biparietal diameter, or single deepest vertical pocket of amniotic fluid; however, a small but statistically significant difference was observed in measurements of abdominal circumference and femur length (P < .05). Intraclass correlations showed excellent agreement (>0.90) between telerobotic and conventional measurements of all 4 biometric parameters. Of 21 fetal structures included in the anatomic survey, 80% of the structures attempted across all patients were sufficiently visualized by the telerobotic system (range, 57%-100% per patient). Ninety-seven percent of patients strongly or somewhat agreed that they would be willing to have another telerobotic examination in the future. CONCLUSIONS: A telerobotic approach is feasible for remotely performing prenatal sonographic examinations. Telerobotic sonography (robotic telesonography) may allow for the development of satellite ultrasound clinics in rural, remote, or low-volume communities, thereby increasing access to prenatal imaging in underserved communities.

Initial Experience Using a Telerobotic Ultrasound System for Adult Abdominal Sonography.

PURPOSE: The study sought to assess the feasibility of performing adult abdominal examinations using a telerobotic ultrasound system in which radiologists or sonographers can control fine movements of a transducer and all ultrasound settings from a remote location. METHODS: Eighteen patients prospectively underwent a conventional sonography examination (using EPIQ 5 [Philips] or LOGIQ E9 [GE Healthcare]) followed by a telerobotic sonography examination (using the MELODY System [AdEchoTech] and SonixTablet [BK Ultrasound]) according to a standardized abdominal imaging protocol. For telerobotic examinations, patients were scanned remotely by a sonographer 2.75 km away. Conventional examinations were read independently from telerobotic examinations. Image quality and acceptability to patients and sonographers was assessed. RESULTS: Ninety-two percent of organs visualized on conventional examinations were sufficiently visualized on telerobotic examinations. Five pathological findings were identified on both telerobotic and conventional examinations, 3 findings were identified using only conventional sonography, and 2 findings were identified using only telerobotic sonography. A paired sample t test showed no significant difference between the 2 modalities in measurements of the liver, spleen, and diameter of the proximal aorta; however, telerobotic assessments overestimated distal aorta and common bile duct diameters and underestimated kidney lengths (P values < .05). All patients responded that they would be willing to have another telerobotic examination. CONCLUSIONS: A telerobotic ultrasound system is feasible for performing abdominal ultrasound examinations at a distant location with minimal training and setup requirements and a moderate learning curve. Telerobotic sonography (robotic telesonography) may open up the possibility of remote ultrasound clinics for communities that lack skilled sonographers and radiologists, thereby improving access to care.

Satisfaction and Quality of Life Related to Chemotherapy With an Arm Port: A Pilot Study.

PURPOSE: Placement of arm ports, or totally implanted venous access devices, is a common practice in our interventional radiology suite. We implant a miniaturized port in the upper arm for the provision of long-term chemotherapy. We hypothesized that there was general satisfaction with these arm ports and they have a minimal negative impact on quality of life. In this study we aimed to assess our hypotheses. METHODS: We surveyed subjects, who having previously received an arm port for chemotherapy to treat a malignancy, attended the interventional room for its removal. The survey assessed the port's effect on lifestyle, the degree of device-related pain, the acceptance of the port, and the willingness to have another port in the future. RESULTS: Survey responses from 77 subjects were reviewed. On a scale of 1 (most negative) to 10 (most positive), respondents indicated that the port system was a very positive enhancement to their treatment (satisfaction = 9.2 ± 2.0 and positivity = 8.8 ± 2.2). The port had little impact on daily activities. The mean score for the likelihood of choosing to have another port placed if additional treatment was required was 9.1 ± 2.1. DISCUSSION: The arm port in this study did not negatively impact subject satisfaction and quality of life for this cohort. Most subjects rated the device utility highly and felt that the port was a positive enhancement to their treatment, one that they would possibly utilise again in future, if need be.

University of Saskatchewan Radiology Courseware (USRC): an assessment of its utility for teaching diagnostic imaging in the medical school curriculum.

PROBLEM: We have found it very challenging to integrate images from our radiology digital imaging repository into the curriculum of our local medical school. Thus, it has been difficult to convey important knowledge related to viewing and interpreting diagnostic radiology images. We sought to determine if we could create a solution for this problem and evaluate whether students exposed to this solution were able to learn imaging concepts pertinent to medical practice. INTERVENTION: We developed University of Saskatchewan Radiology Courseware (USRC), a novel interactive web application that enables preclinical medical students to acquire image interpretation skills fundamental to clinical practice. This web application reformats content stored in Medical Imaging Resource Center teaching cases for BlackBoard Learn™, a popular learning management system. We have deployed this solution for 2 successive years in a 1st-year basic sciences medical school course at the College of Medicine, University of Saskatchewan. The "courseware" content covers both normal anatomy and common clinical pathologies in five distinct modules. We created two cohorts of learners consisting of an intervention cohort of students who had used USRC for their 1st academic year, whereas the nonintervention cohort was students who had not been exposed to this learning opportunity. CONTEXT: To assess the learning experience of the users we designed an online questionnaire and image review quiz delivered to both of the student groups. OUTCOME: Comparisons between the groups revealed statistically significant differences in both confidence with image interpretation and the ability to answer knowledge-based questions. Students were satisfied with the overall usability, functions, and capabilities of USRC. LESSONS LEARNED: USRC is an innovative technology that provides integration between Medical Imaging Resource Center, a teaching solution used in radiology, and a Learning Management System.

To CT or not to CT? The influence of computed tomography on the diagnosis of appendicitis in obese pediatric patients.

BACKGROUND: Appendicitis is a common pediatric query. However, obesity often results in nondiagnostic ultrasounds and increased likelihood of abdominal computed tomography (CT). Concern regarding radiation exposure led the Canadian Association of Radiologists to recommend foregoing CT when ultrasounds are nondiagnostic and clinical suspicion is high. We evaluated this recommendation by quantifying the influence of CT on the diagnosis of pediatric appendicitis. METHODS: We performed a 2-year retrospective case series of children presenting with suspected appendicitis. We stratified patients by weight (obese v. nonobese) and pediatric appendicitis score (PAS) and examined how often they received abdominal CT, why they received it, and its influence on diagnosis. RESULTS: Of 223 patients (84 obese, 139 nonobese), 54 received CT. Obese patients received CTs more frequently than nonobese patients (29% v. 22%). The most common reason for CT was a nondiagnostic ultrasound (75% in obese, 80% in nonobese patients). Sixty-five percent of CTs obtained after nondiagnostic ultrasounds confirmed the initial diagnosis, but the rates were 80% and 50%, respectively, when only obese and only nonobese patients were considered. Obese patients were 4 times more likely to have a CT confirming their initial appendicitis diagnosis. CONCLUSION: Because obese patients are more likely than nonobese patients to have a CT that confirms appendicitis, when treating an obese pediatric patient with suspected appendicitis and a nondiagnostic ultrasound, surgeons with a high clinical suspicion should strongly consider foregoing CT and proceeding with treatment.

CONTEXTE: L'appendicite est un tableau fréquent en pédiatrie. Toutefois, l'obésité produit souvent des résultats non diagnostiques à l'échographie et accroît la probabilité de recours à la tomographie abdominale. L'inquiétude soulevée par l'exposition aux radiations a poussé l'Association canadienne des radiologistes à déconseiller la tomographie lorsque l'échographie se révèle non diagnostique et que les soupçons cliniques sont élevés. Nous avons évalué cette recommandation en quantifiant l'influence de la tomographie sur le diagnostic de l'appendicite chez l'enfant. MÉTHODES: Nous avons procédé à la revue rétrospective d'une série de cas pédiatriques d'appendicite soupçonnée sur une période de 2 ans. Nous avons stratifié les patients selon le poids (obèses c. non obèses) et selon le score diagnostique d'appendicite pédiatrique, puis examiné la fréquence à laquelle on recourait à la tomographie abdominale, sa justification et son influence sur le diagnostic. RÉSULTANTS: Sur 223 patients (84 obèses, 139 non obèses), 54 ont subi une tomographie. Les patients obèses ont été soumis à la tomographie plus souvent que les patients non obèses (29 % c. 22 %). La raison la plus fréquemment invoquée pour recourir à la tomographie était l'échographie non diagnostique (75 % chez les patients obèses, 80 % chez les patients non obèses). Soixante-cinq pour cent des tomographies obtenues après une échographie non diagnostique ont confirmé le diagnostic initial, mais les taux étaient de 80 % et de 50 % respectivement lorsqu'on analysait les groupes obèses et non obèses séparément. Les patients obèses étaient 4 fois plus susceptibles de voir leur diagnostic initial d'appendicite confirmé par la tomographie. CONCLUSION: Étant donné que les patients obèses sont plus susceptibles que les patients non obèses de subir une tomographie qui confirmerait une appendicite, face à un patient pédiatrique obèse chez qui l'on soupçonne une appendicite et dont les résultats à l'échographie sont non diagnostiques, les chirurgiens qui entretiennent des soupçons cliniques élevés devraient envisager fortement d'éviter la tomographie et de procéder au traitement.

Establishing a Standard for Creating Angle-Corrected, Reformatted Brain CT Images.

PURPOSE: To establish a standardized method of reformatting axial images for computed tomography (CT) brain examinations. METHODS: An anatomic line between the superior orbital rim and the base of the occipital bone (SOR-BS line) was chosen as the standardized reference line. In June 2022, CT technologists at a tertiary care center received an educational presentation and a 1-page reference handout on making standardized CT reformats. This was the quality-of-care intervention. Subsequently, 100 CT brain examinations performed on July 1 to 10, 2020 (preintervention) were analyzed and compared with 100 CT brain examinations performed on July 1 to 10, 2022 (postintervention). RESULTS: There were no significant differences in the mean angle differences measured between the preintervention (6.2 ± 5.8°) and the postintervention (5.8 ± 4.7°) groups (P = .67). However, the number of CT brain studies with an angle difference of more than 20° decreased from 4 studies to 1 study. In addition, the number of CT brain studies without reformatted images decreased from 5 to 2 studies. DISCUSSION: The cause for the less-than-optimal adoption of the expected change in CT workflow might be complex and multifactorial. However, the institution in this study is a busy tertiary care center with a chronic shortage of CT technologists. The busy workflow might have contributed to lack of significance for the parameters assessed. CONCLUSION: There was a slight but not significant improvement between preintervention and postintervention data.

Adult fingers visualized on neonatal intensive care unit chest radiographs: what you don't see.

PURPOSE: In a previous publication, it was revealed that a disturbingly high incidence of adult fingers were seen on pediatric intensive care unit radiographs, an example of inappropriate occupational exposure to diagnostic radiation. The present study examined adult fingers seen on neonatal intensive care unit (NICU) radiographs to assess the frequency of this occupational radiation exposure. During this study, we encountered an unexpected issue. The inappropriately exposed fingers appeared on the raw images but were sometimes cropped during technologist image processing before being sent to the picture archiving and communication system (PACS) for interpretation. Our audit describes the frequency of cropping adult fingers from images before display on PACS, with the intent of unmasking this source of occupational radiation exposure, of which quality assurance personnel may not be aware. METHODS: At the x-ray workstation, the raw NICU source x-ray images were analysed for the visibility of adult fingers and then were compared with the final processed images sent to PACS by the x-ray technologist. RESULTS: Of 230 radiographs audited, 30 (13%) contained fingers directly in the x-ray beam that remained visible on PACS, 22 (10%) contained fingers in the direct beam that were cropped before being sent to PACS for analysis, and 44 (19%) contained fingers in the coned area. CONCLUSIONS: A significant number of adult fingers are being exposed to radiation during the acquisition of NICU radiographs. Cropping NICU radiographs before sending them to PACS can conceal a significant source of occupational radiation exposure.

Catheter fracture and embolization associated with arm implantation of the cook vital port.

PURPOSE: To determine the frequency of arm port catheter fracture and embolization related to the Cook Vital Port Mini Titanium. MATERIALS AND METHODS: A retrospective audit of our Cerner Radiology Information System was performed between June 1, 2006, and June 30, 2011, to determine the number of Cook arm venous ports implanted and the frequency of foreign body retrievals related to catheter fracture for these arm ports. RESULTS: A total of 691 arm implantations of the Cook Vital Port during the 5-year time frame were analysed. Eleven of these patients (1.6%) required intravenous foreign body retrieval in the interventional radiology suite related to catheter fracture and embolization. Three of these fractured catheters were retrieved from the peripheral venous system upstream of the pulmonary circulation, whereas 8 embolized to the pulmonary arteries. All were successfully extracted with an intravenous snare by interventional radiology. CONCLUSION: We discovered a 1.6% frequency of catheter fracture and embolization associated with arm implantation of the Cook Vital Port. All the catheters fractured at the vein entry site and did not detach from the port housing. The cause for catheter fracture and embolization is uncertain. Pulmonary embolization of the fractured catheters puts the patients at risk for possible further complications. No patients had ancillary complications related to catheter embolization or to catheter extraction procedures. Further investigation is required in an attempt to determine the circumstances that may result in catheter fracture and embolization related to this venous access device.

A multi-modal deep neural network for multi-class liver cancer diagnosis.

Liver disease is a potentially asymptomatic clinical entity that may progress to patient death. This study proposes a multi-modal deep neural network for multi-class malignant liver diagnosis. In parallel with the portal venous computed tomography (CT) scans, pathology data is utilized to prognosticate primary liver cancer variants and metastasis. The processed CT scans are fed to the deep dilated convolution neural network to explore salient features. The residual connections are further added to address vanishing gradient problems. Correspondingly, five pathological features are learned using a wide and deep network that gives a benefit of memorization with generalization. The down-scaled hierarchical features from CT scan and pathology data are concatenated to pass through fully connected layers for classification between liver cancer variants. In addition, the transfer learning of pre-trained deep dilated convolution layers assists in handling insufficient and imbalanced dataset issues. The fine-tuned network can predict three-class liver cancer variants with an average accuracy of 96.06% and an Area Under Curve (AUC) of 0.832. To the best of our knowledge, this is the first study to classify liver cancer variants by integrating pathology and image data, hence following the medical perspective of malignant liver diagnosis. The comparative analysis on the benchmark dataset shows that the proposed multi-modal neural network outperformed most of the liver diagnostic studies and is comparable to others.

Clinical Impact and Generalizability of a Computer-Assisted Diagnostic Tool to Risk-Stratify Lung Nodules With CT.

OBJECTIVE: To evaluate whether an imaging classifier for radiology practice can improve lung nodule classification and follow-up. METHODS: A machine learning classifier was developed and trained using imaging data from the National Lung Screening Trial (NSLT) to produce a malignancy risk score (malignancy Similarity Index [mSI]) for individual lung nodules. In addition to NLST cohorts, external cohorts were developed from a tertiary referral lung cancer screening program data set and an external nonscreening data set of all nodules detected on CT. Performance of the mSI combined with Lung-RADS was compared with Lung-RADS alone and the Mayo and Brock risk calculators. RESULTS: We analyzed 963 subjects and 1,331 nodules across these cohorts. The mSI was comparable in accuracy (area under the curve = 0.89) to existing clinical risk models (area under the curve = 0.86-0.88) and independently predictive in the NLST cohort of 704 nodules. When compared with Lung-RADS, the mSI significantly increased sensitivity across all cohorts (25%-117%), with significant increases in specificity in the screening cohorts (17%-33%). When used in conjunction with Lung-RADS, use of mSI would result in earlier diagnoses and reduced follow-up across cohorts, including the potential for early diagnosis in 42% of malignant NLST nodules from prior-year CT scans. CONCLUSION: A computer-assisted diagnosis software improved risk classification from chest CTs of screening and incidentally detected lung nodules compared with Lung-RADS. mSI added predictive value independent of existing radiological and clinical variables. These results suggest the generalizability and potential clinical impact of a tool that is straightforward to implement in practice.

USRC: a new strategy for adding digital images to the medical school curriculum.

Many medical schools use learning management systems (LMSs) to give students access to online lecture notes, assignments, quizzes, and other learning resources. LMSs can also be used to provide access to digital radiology images, potentially improving preclinical teaching in anatomy, physiology, and pathology while also allowing students to develop interpretation skills that are important in clinical practice. However, it is unclear how radiology images can best be stored, imported, and displayed in an LMS. We developed University of Saskatchewan Radiology Courseware (USRC), a new web application that allows course designers to import images into pages linked to BlackBoard Learn, a popular LMS. Page content, including images, annotations, captions, and supporting text, are stored as teaching cases on a MIRC (Medical Imaging Resource Center) server. Course designers create cases in MIRC, and then create a corresponding page in BlackBoard by modifying an HTML template so that it holds the URL of a MIRC case. When a user visits the page in BlackBoard, the page requests content from the MIRC case, reformats the text for display in BlackBoard, and loads an image viewer plug-in that allows students to view and interact with the images stored in the case. The USRC technology can be used to reformat MIRC cases for presentation in any website or in any learning management system that supports custom pages written in HTML with embedded JavaScript.