The Environmental, Social, Governance Movement and Radiology: Opportunities and Strategy.

The environmental, social, governance (ESG) movement has come to health care organizations, in part through the Biden administration's challenge to them to reduce greenhouse gas emissions by 50% by 2030 and achieve net zero emissions by 2050, in support of more robust environmental sustainability. Radiology practices should become knowledgeable about ESG concepts and look for opportunities that are meaningful and achievable to support their host organizations' ESG efforts. Examples of initiatives to support improved environmental sustainability include selecting the least energy intensive imaging method for a given diagnosis, shutting down equipment in standby mode, sourcing energy from renewable sources, and reducing waste through recycling. Optimizing imaging protocols can reduce radiation exposure to patients, energy used per examination, and the use of other resources such as iodinated contrast media, an environmental pollutant. Achieving socially equitable access to services for ethnic and racial minorities remains a challenge in the US health care system. Extending hours of operation for screening services to include nights and weekends can provide options for patients who otherwise must take time away from work with loss of income. With respect to governance, more transparency in leadership selection and greater opportunities for participation by women and racial/ethnic minorities in the leadership of professional organizations should be supported in radiology. To succeed in ESG initiatives, radiology practice leaders should consider appointing a lead person and a multifunctional team that includes broad representation from the radiology workplace. The team should work to identify opportunities that are realistic and achievable within their institutional contexts.

Rethinking the Approach to Artificial Intelligence for Medical Image Analysis: The Case for Precision Diagnosis.

To date, widely generalizable artificial intelligence (AI) programs for medical image analysis have not been demonstrated, including for mammography. Rather than pursuing a strategy of collecting ever-larger databases in the attempt to build generalizable programs, we suggest three possible avenues for exploring a precision medicine or precision imaging approach. First, it is now technologically feasible to collect hundreds of thousands of multi-institutional cases along with other patient data, allowing stratification of patients into subpopulations that have similar characteristics in the manner discussed by the National Research Council in its white paper on precision medicine. A family of AI programs could be developed across different examination types that are matched to specific patient subpopulations. Such stratification can help address bias, including racial or ethnic bias, by allowing unbiased data aggregation for creation of subpopulations. Second, for common examinations, larger institutions may be able to collect enough of their own data to train AI programs that reflect disease prevalence and variety in their respective unique patient subpopulations. Third, high- and low-probability subpopulations can be identified by application of AI programs, thereby allowing their triage off the radiology work list. This would reduce radiologists' workloads, providing more time for interpretation of the remaining examinations. For high-volume procedures, investigators should come together to define reference standards, collect data, and compare the merits of pursuing generalizability versus a precision medicine subpopulation-based strategy.

Radiology Mentoring Program for Early Career Faculty-Implementation and Outcomes.

OBJECTIVE: To implement a mentoring program for early career faculty in an academic radiology department and to assess its impact on career development. METHODS: A formal departmental mentoring program for early career faculty (instructors) who were paired with senior radiologists outside of their division was implemented. The program provided structured one-on-one mentoring, creation of a mentoring network, and opportunities for peer mentoring. A survey was conducted before and 1 year after initiation of the program. Historical data on promotion over 5 years before the implementation of the program was used to determine the impact on the rate of promotion. The study was exempt from institutional review board approval. RESULTS: Before and 1 year after implementation of the mentoring program, 57% versus 86% of instructors were satisfied with their mentor (P = .04); 43% versus 90% felt that by encouraging mentorship, the department valued their professional development (P = .001); 38% versus 86% felt that the department created an environment that promoted feedback and sharing of information (P = .002); and 43% versus 76% felt that faculty strove to support each other (P = .03). Since implementation of the program, 43% of instructors received grant funding, 50% received other awards, and 10 instructors were promoted to assistant professor, compared with an average of 4.2/y over the past 5 years. Of those, three were underrepresented minorities in medicine versus none in the previous 5 years. CONCLUSIONS: A mentoring program helped to advance the careers of early career and minority radiology faculty and helped create an atmosphere of more openness and support in the department.

Mentorship in academic radiology: why it matters.

Mentorship plays a critical role in the success of academic radiologists. Faculty members with mentors have better career opportunities, publish more papers, receive more research grants, and have greater overall career satisfaction. However, with the increasing focus on clinical productivity, pressure on turn-around times, and the difficult funding climate, effective mentoring in academic radiology can be challenging. The high prevalence of "burnout" among radiologists makes mentorship even more important. This article reviews benefits and challenges of mentorship in academic radiology, discusses how to institute a faculty mentoring program, examines different types of mentoring, and reviews challenges related to diversity and inclusion.

Deep learning-enabled system for rapid pneumothorax screening on chest CT.

PURPOSE: Prompt diagnosis and quantitation of pneumothorax impact decisions pertaining to patient management. The purpose of our study was to develop and evaluate the accuracy of a deep learning (DL)-based image classification program for detection of pneumothorax on chest CT. METHOD: In an IRB approved study, an eight-layer convolutional neural network (CNN) using constant-size (36*36 pixels) 2D image patches was trained on a set of 80 chest CTs, with (n = 50) and without (n = 30) pneumothorax. Image patches were classified based on their probability of representing pneumothorax with subsequent generation of 3D heat-maps. The heat maps were further defined to include 1) pneumothorax area size, 2) relative location of the region to the lung boundary, and 3) a shape descriptor based on regional anisotropy. A support vector machine (SVM) was trained for classification. RESULT: We assessed performance of our program in a separate test dataset of 200 chest CT examinations, with (160/200, 75%) and without (40/200, 25%) pneumothorax. Data were analyzed to determine the accuracy, sensitivity, specificity. The subject-wise sensitivity was 100% (all 160/160 pneumothoraces detected) and specificity was 82.5% (33 true negative/40). False positive classifications were primarily related to emphysema and/or artifacts in the test images. CONCLUSION: This deep learning-based program demonstrated high accuracy for automatic detection of pneumothorax on chest CTs. By implementing it on a high-performance computing platform and integrating the domain knowledge of radiologists into the analytics framework, our method can be used to rapidly pre-screen large numbers of cases for presence of pneumothorax, a critical finding.

Artificial Intelligence and Machine Learning in Radiology: Opportunities, Challenges, Pitfalls, and Criteria for Success.

Worldwide interest in artificial intelligence (AI) applications, including imaging, is high and growing rapidly, fueled by availability of large datasets ("big data"), substantial advances in computing power, and new deep-learning algorithms. Apart from developing new AI methods per se, there are many opportunities and challenges for the imaging community, including the development of a common nomenclature, better ways to share image data, and standards for validating AI program use across different imaging platforms and patient populations. AI surveillance programs may help radiologists prioritize work lists by identifying suspicious or positive cases for early review. AI programs can be used to extract "radiomic" information from images not discernible by visual inspection, potentially increasing the diagnostic and prognostic value derived from image datasets. Predictions have been made that suggest AI will put radiologists out of business. This issue has been overstated, and it is much more likely that radiologists will beneficially incorporate AI methods into their practices. Current limitations in availability of technical expertise and even computing power will be resolved over time and can also be addressed by remote access solutions. Success for AI in imaging will be measured by value created: increased diagnostic certainty, faster turnaround, better outcomes for patients, and better quality of work life for radiologists. AI offers a new and promising set of methods for analyzing image data. Radiologists will explore these new pathways and are likely to play a leading role in medical applications of AI.

Utilization Management of High-Cost Imaging in an Outpatient Setting in a Large Stable Patient and Provider Cohort over 7 Years.

Purpose To quantify the effect of a comprehensive, long-term, provider-led utilization management (UM) program on high-cost imaging (computed tomography, magnetic resonance imaging, nuclear imaging, and positron emission tomography) performed on an outpatient basis. Materials and Methods This retrospective, 7-year cohort study included all patients regularly seen by primary care physicians (PCPs) at an urban academic medical center. The main outcome was the number of outpatient high-cost imaging examinations per patient per year ordered by the patient's PCP or by any specialist. The authors determined the probability of a patient undergoing any high-cost imaging procedure during a study year and the number of examinations per patient per year (intensity) in patients who underwent high-cost imaging. Risk-adjusted hierarchical models were used to directly quantify the physician component of variation in probability and intensity of high-cost imaging use, and clinicians were provided with regular comparative feedback on the basis of the results. Observed trends in high-cost imaging use and provider variation were compared with the same measures for outpatient laboratory studies because laboratory use was not subject to UM during this period. Finally, per-member per-year high-cost imaging use data were compared with statewide high-cost imaging use data from a major private payer on the basis of the same claim set. Results The patient cohort steadily increased in size from 88 959 in 2007 to 109 823 in 2013. Overall high-cost imaging utilization went from 0.43 examinations per year in 2007 to 0.34 examinations per year in 2013, a decrease of 21.33% (P < .0001). At the same time, similarly adjusted routine laboratory study utilization decreased by less than half that rate (9.4%, P < .0001). On the basis of unadjusted data, outpatient high-cost imaging utilization in this cohort decreased 28%, compared with a 20% decrease in statewide utilization (P = .0023). Conclusion Analysis of high-cost imaging utilization in a stable cohort of patients cared for by PCPs during a 7-year period showed that comprehensive UM can produce a significant and sustained reduction in risk-adjusted per-patient year outpatient high-cost imaging volume. © RSNA, 2017.

Saul Hertz, MD, and the birth of radionuclide therapy.

The year, 2016, marked the 75th anniversary of Dr. Saul Hertz first using radioiodine to treat a patient with thyroid disease. In November of 1936, a luncheon was held of the faculty of Harvard Medical School where Karl Compton, PhD, president of the Massachusetts Institute of Technology was invited to give a presentation entitled "What Physics Can Do for Biology and Medicine." Saul Hertz who attended the luncheon spontaneously asked the very pertinent question that perhaps changed the course of treatment of thyroid disease, "Could iodine be made radioactive artificially?" We review the events leading up to the asking of this question, the preclinical investigations by Dr. Hertz and his colleague Arthur Roberts prior to the treatment of the first patient and what occurred in the years following this landmark event. This commentary seeks to set the record straight to the sequence of events leading to the first radioiodine therapy, so that those involved can be recognized with due credit.

External Factors That Influence the Practice of Radiology: Proceedings of the International Society for Strategic Studies in Radiology Meeting.

In both the United States and Europe, efforts to reduce soaring health care costs have led to intense scrutiny of both standard and innovative uses of imaging. Given that the United States spends a larger share of its gross domestic product on health care than any other nation and also has the most varied health care financing and delivery systems in the world, it has become an especially fertile environment for developing and testing approaches to controlling health care costs and value. This report focuses on recent reforms that have had a dampening effect on imaging use in the United States and provides a glimpse of obstacles that imaging practices may soon face or are already facing in other countries. On the basis of material presented at the 2015 meeting of the International Society for Strategic Studies in Radiology, this report outlines the effects of reforms aimed at (a) controlling imaging use, (b) controlling payer expense through changes in benefit design, and (c) controlling both costs and quality through "value-based" payment schemes. Reasons are considered for radiology practices on both sides of the Atlantic about why the emphasis needs to shift from providing a large volume of imaging services to increasing the value of imaging as manifested in clinical outcomes, patient satisfaction, and overall system savings. Options for facilitating the shift from volume to value are discussed, from the use of advanced management strategies that improve workflow to the creation of programs for patient engagement, the development of new clinical decision-making support tools, and the validation of clinically relevant imaging biomarkers. Radiologists in collaboration with industry must enhance their efforts to expand the performance of comparative effectiveness research to establish the value of these initiatives, while being mindful of the importance of minimizing conflicts of interest. © RSNA, 2017.

Analysis of Low Appropriateness Score Exam Trends in Decision Support-based Radiology Order Entry System.

PURPOSE: Awareness of imaging utilization increased after implementation of Radiology Order Entry with decision support systems (ROE-DS). Our hypothesis is few exams with low Clinical Appropriateness Score (CAS) on ROE-DS are performed. Clinical indications of exams with CAS less than 3 (9-point scale) were re-reviewed and reports analyzed. MATERIALS AND METHODS: Structured Query Language-based query retrieved exams with CAS less than 3 in ROE-DS from January 2007 to December 2011. Reasons provided by physicians for ordering these exams and reports of exams performed were analyzed. For each indication, number of exams ordered and performed was calculated. Statistical significance was assessed using Student's t test and χ2 analysis (P < .05). RESULTS: From 445,984 exams, 12,615 exams (2.8%) had CAS less than 3, and 7,956 exams (63%) were performed. Reasons for ordering of 12,615 low CAS exams were as follows: Requests by physician specialists without further explanation (4,516 = 35.8%), notation of special clinical circumstances (2,877 = 22.8%), requests by nonphysician staff without further explanation (1,383 = 10.9%), absence of suspected finding on previous modality (1,099 = 8.7%), patient preference (737 = 5.8%), and requests based on radiologists' recommendations (706 = 5.6%). Difference between male and female (male < female) preferences for low CAS exams was statistically significant (P < .01). Imaging outcome was highest for extremity MRI cases (66.7%; P < .01). CONCLUSION: Less than 3% of exams ordered had low CAS and about two-thirds of these were performed. Most common indication for ordering these exams was physician specialist request based on opinion of medical necessity without specification. Extremity MRI constituted the highest positive findings for low CAS exams performed.

The Empirical Foundations of Teleradiology and Related Applications: A Review of the Evidence.

INTRODUCTION: Radiology was founded on a technological discovery by Wilhelm Roentgen in 1895. Teleradiology also had its roots in technology dating back to 1947 with the successful transmission of radiographic images through telephone lines. Diagnostic radiology has become the eye of medicine in terms of diagnosing and treating injury and disease. This article documents the empirical foundations of teleradiology. METHODS: A selective review of the credible literature during the past decade (2005-2015) was conducted, using robust research design and adequate sample size as criteria for inclusion. FINDINGS: The evidence regarding feasibility of teleradiology and related information technology applications has been well documented for several decades. The majority of studies focused on intermediate outcomes, as indicated by comparability between teleradiology and conventional radiology. A consistent trend of concordance between the two modalities was observed in terms of diagnostic accuracy and reliability. Additional benefits include reductions in patient transfer, rehospitalization, and length of stay.

Key Performance Indicators in Radiology: You Can't Manage What You Can't Measure.

Quality assurance (QA) is a fundamental component of every successful radiology operation. A radiology QA program must be able to efficiently and effectively monitor and respond to quality problems. However, as radiology QA has expanded into the depths of radiology operations, the task of defining and measuring quality has become more difficult. Key performance indicators (KPIs) are highly valuable data points and measurement tools that can be used to monitor and evaluate the quality of services provided by a radiology operation. As such, KPIs empower a radiology QA program to bridge normative understandings of health care quality with on-the-ground quality management. This review introduces the importance of KPIs in health care QA, a framework for structuring KPIs, a method to identify and tailor KPIs, and strategies to analyze and communicate KPI data that would drive process improvement. Adopting a KPI-driven QA program is both good for patient care and allows a radiology operation to demonstrate measurable value to other health care stakeholders.