Faculty Bibliography

RATIONALE AND OBJECTIVES/OBJECTIVE:To determine the impact of COVID-19 workflow changes on patient throughput at the outpatient imaging facilities of a large healthcare system in New York City. MATERIALS AND METHODS/METHODS:COVID-19 workflow changes to permit social distancing and patient and staff safety included screening at the time of scheduling, encouraging patients to use our digital platform to complete registration/safety forms prior to appointments, stationing screeners at all entrances, limiting waiting room capacity, implementing a texting system to notify patients of delays, limiting dressing room use by encouraging patients to wear exam-appropriate clothing, and accelerating MRI protocols without reducing image quality. We assessed patients' pre-exam wait times, MR exam times, overall time spent on site, and registration for and use of the digital portal before (February 2020) and after (June 2020) implementation of these measures. RESULTS:Across 17 outpatient imaging centers, workflow changes resulted in a 23.1% reduction (-6.8 minutes) in all patients' pre-exam wait times (p <0.00001). Pre-exam wait times for MRI, CT, ultrasound, x-ray, and mammography decreased 28.4% (-10.3 minutes), 16.5% (-6.7 minutes), 25.3% (-7.7 minutes), 22.8% (-3.7 minutes), and 23.9% (-5.0 minutes), respectively (p < 0.00001 for all). MR exam times decreased 9.7% (-3.5 minutes) and patients' overall time on site decreased 15.2% (-8.0 minutes). The proportions of patients actively using the digital patient portal (56.1%-70.1%) and completing forms electronically prior to arrival (24.9%-47.1%) increased (p < 0.0001 for both). CONCLUSION/CONCLUSIONS:Workflow changes necessitated by the COVID-19 pandemic to ensure safety of patients and staff have permitted higher outpatient throughput.

PURPOSE/OBJECTIVE:To advance research in the field of machine learning for MR image reconstruction with an open challenge. METHODS:We provided participants with a dataset of raw k-space data from 1,594 consecutive clinical exams of the knee. The goal of the challenge was to reconstruct images from these data. In order to strike a balance between realistic data and a shallow learning curve for those not already familiar with MR image reconstruction, we ran multiple tracks for multi-coil and single-coil data. We performed a two-stage evaluation based on quantitative image metrics followed by evaluation by a panel of radiologists. The challenge ran from June to December of 2019. RESULTS:We received a total of 33 challenge submissions. All participants chose to submit results from supervised machine learning approaches. CONCLUSIONS:The challenge led to new developments in machine learning for image reconstruction, provided insight into the current state of the art in the field, and highlighted remaining hurdles for clinical adoption.

OBJECTIVE:Deep Learning (DL) image reconstruction has the potential to disrupt the current state of MR imaging by significantly decreasing the time required for MR exams. Our goal was to use DL to accelerate MR imaging in order to allow a 5-minute comprehensive examination of the knee, without compromising image quality or diagnostic accuracy. METHODS:A DL model for image reconstruction using a variational network was optimized. The model was trained using dedicated multi-sequence training, in which a single reconstruction model was trained with data from multiple sequences with different contrast and orientations. Following training, data from 108 patients were retrospectively undersampled in a manner that would correspond with a net 3.49-fold acceleration of fully-sampled data acquisition and 1.88-fold acceleration compared to our standard two-fold accelerated parallel acquisition. An interchangeability study was performed, in which the ability of 6 readers to detect internal derangement of the knee was compared for the clinical and DL-accelerated images. RESULTS:The study demonstrated a high degree of interchangeability between standard and DL-accelerated images. In particular, results showed that interchanging the sequences would result in discordant clinical opinions no more than 4% of the time for any feature evaluated. Moreover, the accelerated sequence was judged by all six readers to have better quality than the clinical sequence. CONCLUSIONS:An optimized DL model allowed for acceleration of knee images which performed interchangeably with standard images for the detection of internal derangement of the knee. Importantly, readers preferred the quality of accelerated images to that of standard clinical images.

OBJECTIVE:To characterize national trends in oncologic imaging (OI) utilization. METHODS:This retrospective cross-sectional study used 2004 and 2016 CMS 5% Carrier Claims Research Identifiable Files. Radiologist-performed, primary noninvasive diagnostic imaging examinations were identified from billed Current Procedural Terminology codes; CT, MRI, and PET/CT examinations were categorized as "advanced" imaging. OI examinations were identified from imaging claims' primary International Classification of Diseases-9 and International Classification of Diseases-10 codes. Imaging services were stratified by academic practice status and place of service. State-level correlations of oncologic advanced imaging utilization (examinations per 1,000 beneficiaries) with cancer prevalence and radiologist supply were assessed by Spearman correlation coefficient. RESULTS:The national Medicare sample included 5,030,955 diagnostic imaging examinations (1,218,144 of them advanced) in 2004 and 5,017,287 diagnostic imaging examinations (1,503,490 of them advanced) in 2016. In 2004 and 2016, OI represented 3.9% and 4.3%, respectively, of all imaging versus 10.8% and 9.5%, respectively, of advanced imaging. The percentage of advanced OI done in academic practices rose from 18.8% in 2004 to 34.1% in 2016, leaving 65.9% outside academia. In 2016, 58.0% of advanced OI was performed in the hospital outpatient setting and 23.9% in the physician office setting. In 2016, state-level oncologic advanced imaging utilization correlated with state-level radiologist supply (r = +0.489, P < .001) but not with state-level cancer prevalence (r = -0.139, P = .329). DISCUSSION/CONCLUSIONS:Oncologic imaging usage varied between practice settings. Although the percentage of advanced OI done in academic settings nearly doubled from 2004 to 2016, the majority remained in nonacademic practices. State-level oncologic advanced imaging utilization correlated with radiologist supply but not cancer prevalence.

OBJECTIVE:The coronavirus disease 2019 (COVID-19) pandemic resulted in significant loss of radiologic volume as a result of shelter-at-home mandates and delay of non-time-sensitive imaging studies to preserve capacity for the pandemic. We analyze the volume-related impact of the COVID-19 pandemic on six academic medical systems (AMSs), three in high COVID-19 surge (high-surge) and three in low COVID-19 surge (low-surge) regions, and a large national private practice coalition. We sought to assess adaptations, risks of actions, and lessons learned. METHODS:Percent change of 2020 volume per week was compared with the corresponding 2019 volume calculated for each of the 14 imaging modalities and overall total, outpatient, emergency, and inpatient studies in high-surge AMSs and low-surge AMSs and the practice coalition. RESULTS:Steep examination volume drops occurred during week 11, with slow recovery starting week 17. The lowest total AMS volume drop was 40% compared with the same period the previous year, and the largest was 70%. The greatest decreases were seen with screening mammography and dual-energy x-ray absorptiometry scans, and the smallest decreases were seen with PET/CT, x-ray, and interventional radiology. Inpatient volume was least impacted compared with outpatient or emergency imaging. CONCLUSION/CONCLUSIONS:Large percentage drops in volume were seen from weeks 11 through 17, were seen with screening studies, and were larger for the high-surge AMSs than for the low-surge AMSs. The lowest drops in volume were seen with modalities in which delays in imaging had greater perceived adverse consequences.

RATIONALE AND OBJECTIVES/OBJECTIVE:The educational value of the daily resident readout, a vital component of resident training, has been markedly diminished due to a significant decrease in imaging volume and case mix diversity. The goal of this study was to create a "simulated" daily readout (SDR) to restore the educational value of the daily readout. MATERIALS AND METHODS/METHODS:To create the SDR the following tasks were performed; selection of cases for a daily worklist for each resident rotation, comprising a combination of normal and abnormal cases; determination of the correct number of cases and the appropriate mix of imaging modalities for each worklist; development of an "educational" environment consisting of separate "instances" of both our Picture Archive Communication System and reporting systems; and the anonymization of all of the cases on the worklists. Surveys of both residents and faculty involved in the SDR were performed to assess its effectiveness. RESULTS:Thirty-two residents participated in the SDR. The daily worklists for the first 20 days of the SDR included 3682 cases. An average of 480 cases per day was dictated by the residents. Surveys of the residents and the faculty involved in the SDR demonstrated that both agreed that the SDR effectively mimics a resident's daily work on rotations and preserves resident education during the Coronavirus Disease 2019 crisis. CONCLUSION/CONCLUSIONS:The development of the SDR provided an effective method of preserving the educational value of the daily readout experience of radiology residents, despite severe decreases in imaging exam volume and case mix diversity during the Coronavirus Disease 2019 pandemic.

The ACR recognizes that radiology practices are grappling with when and how to safely resume routine radiology care during the coronavirus disease 2019 (COVID-19) pandemic. Although it is unclear how long the pandemic will last, it may persist for many months. Throughout this time, it will be important to perform safe, comprehensive, and effective care for patients with and patients without COVID-19, recognizing that asymptomatic transmission is common with this disease. Local idiosyncrasies prevent a single prescriptive strategy. However, general considerations can be applied to most practice environments. A comprehensive strategy will include consideration of local COVID-19 statistics; availability of personal protective equipment (PPE); local, state, and federal government mandates; institutional regulatory guidance; local safety measures; health care worker availability; patient and health care worker risk factors; factors specific to the indication(s) for radiology care; and examination or procedure acuity. An accurate risk-benefit analysis of postponing versus performing a given routine radiology examination or procedure often is not possible due to many unknown and complex factors. However, this is the overriding principle: If the risk of illness or death to a health care worker or patient from health care-acquired COVID-19 is greater than the risk of illness or death from delaying radiology care, the care should be delayed; however, if the opposite is true, the radiology care should proceed in a timely fashion.

Artificial intelligence (AI) has the potential to significantly disrupt the way radiology will be practiced in the near future, but several issues need to be resolved before AI can be widely implemented in daily practice. These include the role of the different stakeholders in the development of AI for imaging, the ethical development and use of AI in healthcare, the appropriate validation of each developed AI algorithm, the development of effective data sharing mechanisms, regulatory hurdles for the clearance of AI algorithms, and the development of AI educational resources for both practicing radiologists and radiology trainees. This paper details these issues and presents possible solutions based on discussions held at the 2019 meeting of the International Society for Strategic Studies in Radiology. KEY POINTS: • Radiologists should be aware of the different types of bias commonly encountered in AI studies, and understand their possible effects. • Methods for effective data sharing to train, validate, and test AI algorithms need to be developed. • It is essential for all radiologists to gain an understanding of the basic principles, potentials, and limits of AI.