Deep Learning to Detect Intracranial Hemorrhage in a National Teleradiology Program and the Impact on Interpretation Time.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. The diagnostic performance of an artificial intelligence (AI) clinical decision support (CDS) solution for acute intracranial hemorrhage (ICH) detection was assessed in a large teleradiology practice. The impact on radiologist read times and system efficiency was also quantified. A total of 61,704 consecutive noncontrast head CTs (NCHCT) were retrospectively evaluated. System performance was calculated along with mean and median read time values for NCHCT pre-AI (baseline; August 2021-May 2022) and post-AI (January 2023-February 2024). The AI solution had a sensitivity of 75.6%, specificity of 92.1%, accuracy of 91.7%, prevalence of 2.70%, and positive predictive value of 21.1%. Of the 56,745 post-AI NCHCT with no bleed identified by a radiologist, examinations falsely flagged as suspected ICH by the AI solution (n = 4,464) took 9min40sec on average/8min7sec median to interpret as compared with 8min25sec average/6min48ec median for unremarkable NCHCT pre-AI (n = 49,007) (P < .001) and 8min38sec average/6min53sec median post-AI when ICH was not suspected by the AI solution (n = 52,281) (P < .001). NCHCT with no bleed identified by the AI but reported as positive for ICH by the radiologist (n = 384) took 14min23sec on average/13min35sec median to interpret as compared with a read time of 13min34sec mean/12min30sec median for NCHCT correctly reported as a bleed by the AI (n = 1192) (P = .04). With lengthened read times for falsely flagged examinations, system inefficiencies may outweigh the potential benefits of using the tool in a high volume, low prevalence environment. ©RSNA, 2024.

The Association of Health Care System Resources With Lung Cancer Screening Implementation: A Cohort Study.

BACKGROUND: The Veterans Health Administration issued policy for lung cancer screening resources at eight Veterans Affairs Medical Centers (VAMCs) in a demonstration project (DP) from 2013 through 2015. RESEARCH QUESTION: Do policies that provide resources increase lung cancer screening rates? STUDY DESIGN AND METHODS: Data from eight DP VAMCs (DP group) and 20 comparable VAMCs (comparison group) were divided into before DP (January 2011-June 2013), DP (July 2013-June 2015), and after DP (July 2015-December 2018) periods. Coprimary outcomes were unique veterans screened per 1,000 eligible per month and those with 1-year (9-15 months) follow-up screening. Eligible veterans were estimated using yearly counts and the percentage of those with eligible smoking histories. Controlled interrupted time series and difference-in-differences analyses were performed. RESULTS: Of 27,746 veterans screened, the median age was 66.5 years and most were White (77.7%), male (95.6%), and urban dwelling (67.3%). During the DP, the average rate of unique veterans screened at DP VAMCs was 17.7 per 1,000 eligible per month, compared with 0.3 at comparison VAMCs. Adjusted analyses found a higher rate increase at DP VAMCs by 0.93 screening per 1,000 eligible per month (95% CI, 0.25-1.61) during this time, with an average facility-level difference of 17.4 screenings per 1,000 eligible per month (95% CI, 12.6-22.3). Veterans with 1-year follow-up screening also increased more rapidly at DP VAMCs during the DP, by 0.39 screening per 1,000 eligible per month (95% CI, 0.18-0.60), for an average facility-level difference of 7.2 more screenings per 1,000 eligible per month (95% CI, 5.2-9.2). Gains were not maintained after the DP. INTERPRETATION: In this cohort, provision of resources for lung cancer screening implementation was associated with an increase in veterans screened and those with 1-year follow-up screening. Screening gains associated with the DP were not maintained.

Patient Exposure from Radiologic and Nuclear Medicine Procedures in the United States: Procedure Volume and Effective Dose for the Period 2006-2016.

Background Comprehensive assessments of the frequency and associated doses from radiologic and nuclear medicine procedures are rarely conducted. The use of these procedures and the population-based radiation dose increased remarkably from 1980 to 2006. Purpose To determine the change in per capita radiation exposure in the United States from 2006 to 2016. Materials and Methods The U.S. National Council on Radiation Protection and Measurements conducted a retrospective assessment for 2016 and compared the results to previously published data for the year 2006. Effective dose values for procedures were obtained from the literature, and frequency data were obtained from commercial, governmental, and professional society data. Results In the United States in 2006, an estimated 377 million diagnostic and interventional radiologic examinations were performed. This value remained essentially the same for 2016 even though the U.S. population had increased by about 24 million people. The number of CT scans performed increased from 67 million to 84 million, but the number of other procedures (eg, diagnostic fluoroscopy) and nuclear medicine procedures decreased from 17 million to 13.5 million. The number of dental radiographic and dental CT examinations performed was estimated to be about 320 million in 2016. Using the tissue-weighting factors from Publication 60 of the International Commission on Radiological Protection, the U.S. annual individual (per capita) effective dose from diagnostic and interventional medical procedures was estimated to have been 2.9 mSv in 2006 and 2.3 mSv in 2016, with the collective doses being 885 000 and 755 000 person-sievert, respectively. Conclusion The trend from 1980 to 2006 of increasing dose from medical radiation has reversed. Estimated 2016 total collective effective dose and radiation dose per capita dose are lower than in 2006. © RSNA, 2020 See also the editorial by Einstein in this issue.

National Lung Cancer Screening Utilization Trends in the Veterans Health Administration.

BACKGROUND: Many Veterans are high risk for lung cancer. Low-dose computed tomography (LDCT) is an effective strategy for lung cancer early detection in a high-risk population. Our objective was to describe and compare annual and geographic utilization trends for LDCT screening in the Veteran's Health Administration (VHA). METHODS: A national retrospective cohort of screened Veterans from January 1, 2011 to May 31, 2018 was used to calculate annual and regional rates of initial LDCT utilization per 1000 eligible Veterans. We identified Veterans with a first LDCT exam using common procedure terminology codes G0297 or 71250 and described as "lung cancer screening," "screening," or "LCS." The number of screen-eligible Veterans per year was calculated as unique Veterans aged 55 to 80 years seen at a Veterans Affairs medical center (VAMC) in that year, multiplied by 32% (estimated proportion with eligible smoking history). We present 95% confidence intervals (CI) for rates. RESULTS: Screened Veterans had a mean age of 66.1 years (standard deviation [SD] = 5.6); 95.5% male; 77.4% Caucasian. There were 119 300 LDCT exams, of which 80 819 (67.7%) were initial. Nationally, initial screens increased from 0 (95% CI = 0.00 to 0.00) in 2011 to 29.6 (95% CI = 29.26 to 29.88) scans per 1000 eligible Veterans in 2018 (Ptrend < .001). Initial screens increased over time within all geographic regions, most prominently in northeastern and Florida VAMCs. CONCLUSION: VHA LDCT utilization increased from 2011 to 2018. However, overall utilization remained low. Future interventions are needed to increase lung cancer screening utilization among eligible Veterans.

The role of the VA in academic radiology: a report of the ACR's Committee on Governmental and Regulatory Affairs in Academic Radiology.

Academic radiology departments have benefited from their relationships with US Department of Veterans Affairs hospitals. Review of the history of the care of veterans shows a unique relationship with academic medical centers. Opportunities for future collaborations include clinical care, teaching, and research.