A natural language processing-informed adrenal gland incidentaloma clinic improves guideline-based care.

INTRODUCTION: Adrenal gland incidentalomas (AGIs) are found in up to 5% of cross-sectional images. However, rates of guideline-based workup for AGIs are notoriously low. We sought to determine if a natural language processing (NLP)-informed AGI clinic could improve the rates of indicated biochemical evaluation and adrenal-specific imaging. METHODS: An NLP algorithm was created to detect clinically significant adrenal nodules from radiology reports of cross-sectional images at an academic institution. The NLP algorithm was applied to scans occurring between June 2020 and July 2021 to form a baseline cohort. The NLP algorithm was re-applied to scans from August 2021 to February 2023 and identified patients were invited to join an outpatient clinic dedicated to AGIs. Patients evaluated in the clinic from March 2022 to February 2023 were included in the intervention cohort. Statistical analysis utilized chi-square, t-test, and a multivariable logistic regression. RESULTS: The baseline and intervention cohorts included 1784 and 322 unique patients, respectively. Patients in the intervention cohort were more likely to be female (59% vs. 51%, p = 0.01), be younger (60 ± 13.1 vs. 64 ± 13.2 years, p < 0.001), have smaller nodules (1.7 cm, IQR 1.4-2.1 vs. 1.8 cm, IQR 1.4-2.5 cm, p = 0.017), have had biochemical workup (99% vs. 13%, p < 0.001), and have had adrenal-specific imaging (40% vs. 11%, p < 0.001). In a multivariable analysis, intervention cohort patients were significantly more likely to have had biochemical workup (odds ratio ,OR 1209, confidence interval ,CI 434-5117, p < 0.001) and adrenal-specific imaging (OR 8.89, CI 6.42-12.4, p < 0.001). CONCLUSION: The implementation of an NLP-informed AGI clinic was associated with a seven-fold increase in biochemical workup and a three-fold increase in adrenal-specific imaging in participating patients.

Prospective Evaluation of Artificial Intelligence Triage of Intracranial Hemorrhage on Noncontrast Head CT Examinations.

Background: Retrospective studies evaluating artificial intelligence (AI) algorithms for intracranial hemorrhage (ICH) detection on noncontrast CT (NCCT) have shown promising results but lack prospective validation. Objective: To evaluate the impact on radiologists' real-world aggregate performance for ICH detection and report turnaround times for ICH-positive examinations of a radiology department's implementation of an AI triage and notification system for ICH detection on head NCCT examinations. Methods: This prospective single-center study included adult patients who underwent head NCCT examinations from May 12, 2021 to June 30, 2021 (phase 1) or September 30, 2021 to December 4, 2021 (phase 2). Before phase 1, the radiology department implemented a commercial AI triage system for ICH detection that processed head NCCT examinations and notified radiologists of positive results through a widget with a floating pop-up display. Examinations were interpreted by neuroradiologists or emergency radiologists, who evaluated examinations without and with AI assistance in phase 1 and phase 2, respectively. A panel of radiologists conducted a review process for all examinations with discordance between the radiology report and AI and a subset of remaining examinations, to establish the reference standard. Diagnostic performance and report turnaround times were compared using Pearson chi-square test and Wilcoxon rank-sum test, respectively. Bonferroni correction was used to account for five diagnostic performance metrics (adjusted significance threshold, .01 [α=.05/5]). Results: A total of 9954 examinations from 7371 patients (mean age, 54.8±19.8 years; 3773 female, 3598 male) were included. In phases 1 and 2, 19.8% (735/3716) and 21.9% (1368/6238) of examinations, respectively, were positive for ICH (P=.01). Radiologists without versus with AI showed no significant difference in accuracy (99.5% vs 99.2%), sensitivity (98.6% vs 98.9%), PPV (99.0% vs 99.7%), or NPV (99.7% vs 99.7%) (all P>.01); specificity was higher for radiologists without than with AI (99.8% vs 99.3%, respectively, P=.004). Mean report turnaround time for ICH-positive examinations was 147.1 minutes without AI versus 149.9 minutes with AI (P=.11). Conclusion: An AI triage system for ICH detection did not improve radiologists' diagnostic performance or report turnaround times. Clinical Impact: This large prospective real-world study does not support use of AI assistance for ICH detection.

Clinical Consensus Statement on the Use of Indocyanine Green Fluorescence-guided Surgery in Pediatric Patients.

BACKGROUND AND AIMS: Indocyanine Green Fluorescence (ICG-F)- guided surgery is becoming an increasingly helpful tool in pediatric surgical care. This consensus statement investigates the utility of ICG-F in various pediatric surgical applications, primarily focusing on its evidence base, safety, indications, use across different surgical specialties and dosing strategies. The aim is to establish an international consensus for ICG-F use in pediatric surgery. METHODS: An international panel of 15 pediatric surgeons from 9 countries was assembled. The structured process consisted of a rapid scoping review, iterative discussion sessions, mixed-methods studies with key stakeholders, and voting rounds on individual statements to create draft consensus statements. RESULTS: 100 articles were identified during the review and summarized by application. Based on this condensed evidence, consensus statements were generated after 3 iterative rounds of anonymous voting. Key areas of agreement were quality of evidence, the safety of ICG, pediatric surgical indications, utilization per surgical specialty, and dosing of ICG. CONCLUSION: This consensus statement aims to guide healthcare professionals in managing ICG-F use in pediatric surgical cases based on the best available evidence, key stakeholder consultation, and expert opinions. Despite ICG-F's promising potential, the need for higher-quality evidence, prospective trials, and safety studies is underscored. The consensus also provides a framework for pediatric surgeons to utilize ICG-F effectively. LEVEL OF EVIDENCE: III.

Prospective Evaluation of Artificial Intelligence Triage of Incidental Pulmonary Emboli on Contrast-Enhanced CT Examinations of the Chest or Abdomen.

BACKGROUND. Artificial intelligence (AI) algorithms improved detection of incidental pulmonary embolism (IPE) on contrast-enhanced CT (CECT) examinations in retrospective studies; however, prospective validation studies are lacking. OBJECTIVE. The purpose of this study was to assess the effect on radiologists' real-world diagnostic performance and report turnaround times of a radiology department's clinical implementation of an AI triage system for detecting IPE on CECT examinations of the chest or abdomen. METHODS. This prospective single-center study included consecutive adult patients who underwent CECT of the chest or abdomen for reasons other than pulmonary embolism (PE) detection from May 12, 2021, to June 30, 2021 (phase 1), or from September 30, 2021, to December 4, 2021 (phase 2). Before phase 1, the radiology department installed a commercially available AI triage algorithm for IPE detection that automatically processed CT examinations and notified radiologists of positive results through an interactive floating widget. In phase 1, the widget was inactive, and radiologists interpreted examinations without AI assistance. In phase 2, the widget was activated, and radiologists interpreted examinations with AI assistance. A review process involving a panel of radiologists was implemented to establish the reference standard for the presence of IPE. Diagnostic performance and report turnaround times were compared using the Pearson chi-square test and Wilcoxon rank sum test, respectively. RESULTS. Phase 1 included 1467 examinations in 1434 patients (mean age, 53.8 ± 18.5 [SD] years; 753 men, 681 women); phase 2 included 3182 examinations in 2886 patients (mean age, 55.4 ± 18.2 years; 1520 men, 1366 women). The frequency of IPE was 1.4% (20/1467) in phase 1 and 1.6% (52/3182) in phase 2. Radiologists without AI, in comparison to radiologists with AI, showed significantly lower sensitivity (80.0% vs 96.2%, respectively; p = .03), without a significant difference in specificity (99.9% vs 99.9%, p = .58), for the detection of IPE. The mean report turnaround time for IPE-positive examinations was not significantly different between radiologists without AI and radiologists with AI (78.3 vs 74.6 minutes, p = .26). CONCLUSION. An AI triage system improved radiologists' sensitivity for IPE detection on CECT examinations of the chest or abdomen without significant change in report turnaround times. CLINICAL IMPACT. This prospective real-world study supports the use of AI assistance for maximizing IPE detection.

Thoracoscopic Excision of Mediastinal Bronchogenic Cysts in Children: A Case Series.

Background: Bronchogenic cysts result from a congenital anomalous budding of the tracheobronchial tree. Resection is usually recommended to avoid complications. Mediastinal bronchogenic cysts present a unique challenge due to their proximity to vital structures. The purpose of this study is to review our experience with mediastinal bronchogenic cysts. Methods: A single-institution retrospective review evaluated all mediastinal bronchogenic cyst excisions between January 2012 and November 2022. Patient demographics were assessed, including age at diagnosis, presenting symptoms, imaging workup, and cyst characteristics. Operative approach, complications, and surgical pathology were reported. Results: Five patients were identified. Age at diagnosis ranged from 18 to 27 months. No patient was diagnosed prenatally. All patients had symptoms at the time of diagnosis, including cough, wheezing, and respiratory distress. Three cysts were paratracheal, and two were paraesophageal. Age at surgery ranged from 26 to 30 months. All bronchogenic cysts were successfully resected thoracoscopically. Individual technical challenges included narrowing of the mainstem bronchus preventing lung isolation, significant mediastinal inflammation, the necessity for cyst evacuation to delineate the extent of the cyst, adherence of cyst wall to bronchus or trachea requiring cold dissection, and a stalk of tissue with an intimate connection to the carina that was amputated. No intraoperative or postoperative complication occurred. Surgical pathology was consistent with a bronchogenic cyst in all cases. Median length of hospital stay was two days. Conclusion: Thoracoscopy is a safe and effective procedure for mediastinal bronchogenic cyst excision in children. Certain technical maneuvers are highlighted, which may facilitate resection.

General-Purpose Large Language Models Versus a Domain-Specific Natural Language Processing Tool for Label Extraction From Chest Radiograph Reports.

GPT-4 outperformed a radiology domain-specific natural language processing model in classifying imaging findings from chest radiograph reports, both with and without predefined labels. Prompt engineering for context further improved performance. The findings indicate a role for large language models to accelerate artificial intelligence model development in radiology by automating data annotation.

Defining digital surgery: a SAGES white paper.

BACKGROUND: Digital surgery is a new paradigm within the surgical innovation space that is rapidly advancing and encompasses multiple areas. METHODS: This white paper from the SAGES Digital Surgery Working Group outlines the scope of digital surgery, defines key terms, and analyzes the challenges and opportunities surrounding this disruptive technology. RESULTS: In its simplest form, digital surgery inserts a computer interface between surgeon and patient. We divide the digital surgery space into the following elements: advanced visualization, enhanced instrumentation, data capture, data analytics with artificial intelligence/machine learning, connectivity via telepresence, and robotic surgical platforms. We will define each area, describe specific terminology, review current advances as well as discuss limitations and opportunities for future growth. CONCLUSION: Digital Surgery will continue to evolve and has great potential to bring value to all levels of the healthcare system. The surgical community has an essential role in understanding, developing, and guiding this emerging field.

Evaluation of Thoracoscopic Lobectomy in Infants for Congenital Lung Lesions: Earlier Is Better!

OBJECTIVES: This study evaluates the safety and efficacy of thoracoscopic lobectomy for congenital lung lesions in infants less then 4 months of age. MATERIALS AND METHODS: From January 1997 to October 2022, 194 patients under 4 months of age and weight less then 5.6 Kg underwent video-assisted thoracoscopic lobe resection for CPAM, Sequestration, and CLE. All procedures were performed by or under the direct guidance of a single surgeon. RESULTS: 195 of 196 procedures were completed thoracoscopically. Operative times ranged from 25 min to 195 min (average, 82 min). There were 50 upper, 8 middle, and 136 lower lobe resections. There were 4 intraoperative complications (2.1 %), of which 1 (0.5 %) required conversion to an open thoracotomy. The postoperative complication rate was 3.1 % Hospital length of stay ranged from 1 to 8 days (Avg 1.8) for those admitted for surgery. There were no conversions to open or blood transfusions in the last 15 years. CONCLUSIONS: Thoracoscopic lung resection congenital lung lesions in infants is a safe and efficacious technique and avoids the morbidity of a thoracotomy. Early intervention allows surgery before clinical infections or symptoms occur. Newer instrumentation and techniques allow the operation to be safely performed in the first few months of life with shorter operative times, fewer complications, and decreased hospital stays. The minimal morbidity of this procedure should be considered when considering non-operative management of these patients.

Congenital lung malformations.

Congenital lung malformations (CLMs) are rare developmental anomalies of the lung, including congenital pulmonary airway malformations (CPAM), bronchopulmonary sequestration, congenital lobar overinflation, bronchogenic cyst and isolated congenital bronchial atresia. CLMs occur in 4 out of 10,000 live births. Postnatal presentation ranges from an asymptomatic infant to respiratory failure. CLMs are typically diagnosed with antenatal ultrasonography and confirmed by chest CT angiography in the first few months of life. Although surgical treatment is the gold standard for symptomatic CLMs, a consensus on asymptomatic cases has not been reached. Resection, either thoracoscopically or through thoracotomy, minimizes the risk of local morbidity, including recurrent infections and pneumothorax, and avoids the risk of malignancies that have been associated with CPAM, bronchopulmonary sequestration and bronchogenic cyst. However, some surgeons suggest expectant management as the incidence of adverse outcomes, including malignancy, remains unknown. In either case, a planned follow-up and a proper transition to adult care are needed. The biological mechanisms through which some CLMs may trigger malignant transformation are under investigation. KRAS has already been confirmed to be somatically mutated in CPAM and other genetic susceptibilities linked to tumour development have been explored. By summarizing current progress in CLM diagnosis, management and molecular understanding we hope to highlight open questions that require urgent attention.

Prospective Evaluation of AI Triage of Pulmonary Emboli on CT Pulmonary Angiograms.

Background Artificial intelligence (AI) algorithms have shown high accuracy for detection of pulmonary embolism (PE) on CT pulmonary angiography (CTPA) studies in academic studies. Purpose To determine whether use of an AI triage system to detect PE on CTPA studies improves radiologist performance or examination and report turnaround times in a clinical setting. Materials and Methods This prospective single-center study included adult participants who underwent CTPA for suspected PE in a clinical practice setting. Consecutive CTPA studies were evaluated in two phases, first by radiologists alone (n = 31) (May 2021 to June 2021) and then by radiologists aided by a commercially available AI triage system (n = 37) (September 2021 to December 2021). Sixty-two percent of radiologists (26 of 42 radiologists) interpreted studies in both phases. The reference standard was determined by an independent re-review of studies by thoracic radiologists and was used to calculate performance metrics. Diagnostic accuracy and turnaround times were compared using Pearson χ2 and Wilcoxon rank sum tests. Results Phases 1 and 2 included 503 studies (participant mean age, 54.0 years ± 17.8 [SD]; 275 female, 228 male) and 1023 studies (participant mean age, 55.1 years ± 17.5; 583 female, 440 male), respectively. In phases 1 and 2, 14.5% (73 of 503) and 15.9% (163 of 1023) of CTPA studies were positive for PE (P = .47). Mean wait time for positive PE studies decreased from 21.5 minutes without AI to 11.3 minutes with AI (P < .001). The accuracy and miss rate, respectively, for radiologist detection of any PE on CTPA studies was 97.6% and 12.3% without AI and 98.6% and 6.1% with AI, which was not significantly different (P = .15 and P = .11, respectively). Conclusion The use of an AI triage system to detect any PE on CTPA studies improved wait times but did not improve radiologist accuracy, miss rate, or examination and report turnaround times. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Murphy and Tee in this issue.

Pulmonary Surface Irregularity Score as a New Quantitative CT Marker for Idiopathic Pulmonary Fibrosis-a Pilot Study.

The purpose of this study is to evaluate the accuracy and inter-observer agreement of a quantitative pulmonary surface irregularity (PSI) score on high-resolution chest CT (HRCT) for predicting transplant-free survival in patients with IPF. For this IRB-approved HIPAA-compliant retrospective single-center study, adult patients with IPF and HRCT imaging (N = 50) and an age- and gender-matched negative control group with normal HRCT imaging (N = 50) were identified. Four independent readers measured the PSI score in the midlungs on HRCT images using dedicated software while blinded to clinical data. A t-test was used to compare the PSI scores between negative control and IPF cohorts. In the IPF cohort, multivariate cox regression analysis was used to associate PSI score and clinical parameters with transplant-free survival. Inter-observer agreement for the PSI score was assessed by intraclass correlation coefficient (ICC). The technical failure rate of the midlung PSI score was 0% (0/100). The mean PSI score of 5.38 in the IPF cohort was significantly higher than 3.14 in the negative control cohort (p < .001). In the IPF cohort, patients with a high PSI score (≥ median) were 8 times more likely to die than patients with a low PSI score (HR: 8.36; 95%CI: 2.91-24.03; p < .001). In a multivariate model including age, gender, FVC, DLCO, and PSI score, only the PSI score was associated with transplant-free survival (HR:2.11 per unit increase; 95%CI: 0.26-3.51; p = .004). Inter-observer agreement for the PSI score among 4 readers was good (ICC: 0.88; 95%CI: 0.84-0.91). The PSI score had high accuracy and good inter-observer agreement on HRCT for predicting transplant-free survival in patients with IPF.

Prenatal ultrasound-and MRI-based imaging predictors of respiratory symptoms at birth for congenital lung malformations.

BACKGROUND: Congenital lung malformations (CLM) are rare developmental anomalies of the fetal lung with a minority of patients exhibiting symptoms around the time of birth. Although ultrasound remains the gold standard, fetal MRI has recently been incorporated as an adjunct imaging modality in the workup and prenatal counseling of patients with CLM as it is thought to more accurately delineate lesion boundaries and diagnose lesion type. We evaluate what prenatal variables correlate with postnatal respiratory symptoms. METHODS: We performed a retrospective review of patients with prenatal diagnosis of CLM treated at our institution between 2006-2020. Fetal ultrasound and magnetic resonance imaging (MRI) parameters including maximal congenital pulmonary airway malformation volume ratio (CVR), absolute cyst volume, and observed to expected normal fetal lung volume (O/E NFLV) were correlated with outcomes including postnatal respiratory symptoms, need for supplementary oxygen or mechanical ventilation, delay in tolerating full feeds, resection in the neonatal period. RESULTS: Our study included 111 patients, all of whom underwent fetal ultrasound with 64 patients additionally undergoing fetal MRI. Postnatal respiratory symptoms were noted in 22.5% of patients, 19.8% required supplemental oxygen, 2.7% mechanical ventilation and two patients requiring urgent resection. Ultrasound parameters including absolute cyst volume and maximal CVR correlated with need for mechanical ventilation (p=0.034 and p=0.024, respectively) and for urgent resection (p=0.018 and p=0.023, respectively) and had a marginal association with postnatal respiratory symptoms (p=0.050 and p=0.052). Absolute cyst volume became associated with postnatal respiratory symptoms (p=0.017) after multivariable analysis controlling for maternal steroid administration and gestational age. O/E NFLV did not correlate with perinatal outcomes. CONCLUSION: We have found that ultrasound-based measurements correlate with postnatal respiratory symptoms, while MRI derived O/E NFLV does not. Further studies are needed to elucidate the role of MRI in the prenatal workup of congenital lung malformations. TYPE OF STUDY: Study of Diagnostic Test. LEVEL OF EVIDENCE: Level I.

Inter-Rater Reliability and Correlation of L1 Hounsfield Unit Measurements with DXA Scores.

INTRODUCTION: While prior studies have generally reported rigorous protocols using prespecified CT scanner settings for HU measurements, the present study sought to report on the correlation between DXA and HUs recorded using several CT scanners with varying sequences, simulating measurements performed in "real-world" hospital and Emergency Department (ED) settings. METHODOLOGY: Six raters performed HU measurements of trabecular bone at the L1 vertebral body for forty consecutive patients on Phillips and General Electric (GE) abdominal CT scans obtained between 2017 and 2021. Inter-rater reliability of the HU measurements and their correlations with recorded DXA-based bone assessments were determined. Correlation coefficients were calculated for the HU measurements between scanner vendors as well as for the CT HUs with each DXA measurement. RESULTS: The ICC for L1 HUs read on the Phillips and GE scanners were 0.85 and 0.82, respectively, indicating excellent agreement. The correlation coefficient for the mean HUs on the Phillips and GE scanners was 0.92, also indicating excellent correlation. For both scanner vendors, the HU values most closely correlated with the total femur and femoral neck T-scores. CONCLUSIONS: HU values recorded on a Phillips and GE scanner both demonstrated excellent inter-rater reliability. Correlations were strongest between L1 HU values and total femur DXA T-scores. Readily available abdominal CT image data across multiple hospital settings can be utilized by providers of varying level of imaging interpretation expertise to determine vertebral body Hounsfield units that may help identify osteoporosis risk without additional radiation exposure or cost.

Prospective Evaluation of a Machine-Learning Prediction Model for Missed Radiology Appointments.

The term "no-show" refers to scheduled appointments that a patient misses, or for which she arrives too late to utilize medical resources. Accurately predicting no-shows creates opportunities to intervene, ensuring that patients receive needed medical resources. A machine-learning (ML) model can accurately identify individuals at high no-show risk, to facilitate strategic and targeted interventions. We used 4,546,104 non-same-day scheduled appointments in our medical system from 1/1/2017 through 1/1/2020 for training data, including 631,386 no-shows. We applied eight ML techniques, which yielded cross-validation AUCs of 0.77-0.93. We then prospectively tested the best performing model, Gradient Boosted Regression Trees, over a 6-week period at a single outpatient location. We observed 123 no-shows. The model accurately identified likely no-show patients retrospectively (AUC 0.93) and prospectively (AUC 0.73, p < 0.0005). Individuals in the highest-risk category were three times more likely to no-show than the average of all other patients. No-show prediction modeling based on machine learning has the potential to identify patients for targeted interventions to improve their access to medical resources, reduce waste in the medical system and improve overall operational efficiency. Caution is advised, due to the potential for bias to decrease the quality of service for patients based on race, zip code, and gender.

Thoracoscopic Lobectomy in Infants and Children.

Indications for pulmonary lobectomy in infants and children include cystic pulmonary adenomatoid malformation, congenital lobar emphysema, chronic infection, and malignancy. These procedures can now all be done thoracoscopically avoiding the short- and long-term morbidity of an open thoracotomy. In this article we describe the technique of thoracoscopic lobectomy as well as the preoperative and postoperative care.

Mentoring in Pediatric Thoracoscopy: From Theory to Practice.

Introduction: Thoracoscopy represents the most challenging area of pediatric minimally invasive surgery due to its technical difficulty. A standardized training program would be advisable. The aim of this study is to evaluate the results of our surgical training. Materials and Methods: A retrospective, single-center, cohort study was performed. The following four-step program was tested: (1) theoretical part; (2) experimental training; (3) training in centers of reference; (4) personal operative experience. Particular attention was focused on the choice of mentor. Times and modality of adherence to the program were evaluated. The effectiveness and safety of the training were evaluated according to the surgical results of esophageal atresia (EA/TEF) repair and resection of congenital lung malformations (CLM). The study was conducted from January 2014 to May 2020. Attending surgeons with previous experience in neonatal and pediatric laparoscopy were selected for the training program after being evaluated by the head of Department. Results: The training program was fully completed in 2 years. Twenty-four lobectomies, 9 sequestrectomies, 2 bronchogenic cyst resections and 20 EA/TEF repair were performed. Thoracoscopy was always feasible and effective, with no conversion. The operative times progressively decreased. Only three minor complications were recorded, all treated conservatively. Conclusions: A standardized training program is highly desirable to learn how to safely perform advanced pediatric thoracoscopy. The 4-steps design seems a valid educational option. The choice of the mentor is crucial. An experience-based profile for pediatric surgeons who may teach thoracoscopy is advisable.

Radiology Education in the Time of COVID-19: A Novel Distance Learning Workstation Experience for Residents.

RATIONALE AND OBJECTIVES: The coronavirus disease of 2019 (COVID-19) pandemic has challenged the educational missions of academic radiology departments nationwide. We describe a novel cloud-based HIPAA compliant and accessible education platform which simulates a live radiology workstation for continued education of first year radiology (R1) residents, with an emphasis on call preparation and peer to peer resident learning. MATERIALS AND METHODS: Three tools were used in our education model: Pacsbin (Orion Medical Technologies, Baltimore, MD, pacsbin.com), Zoom (Zoom Video Communications, San Jose, CA, zoom.us), and Google Classroom (Google, Mountain View, CA, classroom.google.com). A senior radiology resident (R2-R4) (n = 7) driven workflow was established to provide scrollable Digital Imaging and Communications in Medicine (DICOM) based case collections to the R1 residents (n = 9) via Pacsbin. A centralized classroom was created using Google Classroom for assignments, reports, and discussion where attending radiologists could review content for accuracy. Daily case collections over an 8-week period from March to May were reviewed via Zoom video conference readout in small groups consisting of a R2-R4 teacher and R1 residents. Surveys were administered to R1 residents, R2-4 residents, and attending radiologist participants. RESULTS: Hundred percent of R1 residents felt this model improved their confidence and knowledge to take independent call. Seventy-eight percent of the R1 residents (n = 7/9) demonstrated strong interest in continuing the project after pandemic related restrictions are lifted. Based on a Likert "helpfulness" scale of 1-5 with 5 being most helpful, the project earned an overall average rating of 4.9. Two R2-R4 teachers demonstrated increased interest in pursuing academic radiology. CONCLUSION: In response to unique pandemic circumstances, our institution implemented a novel cloud-based distance learning solution to simulate the radiology workstation. This platform helped continue the program's educational mission, offered first year residents increased call preparation, and promoted peer to peer learning. This approach to case-based learning could be used at other institutions to educate residents.