Journal of the American College of Radiology : JACR最新文献

{"title":"ACR Appropriateness Criteria® Postmenopausal Acute Pelvic Pain: 2026 Update.","authors":"Kira Melamud, Haatal B Dave, Adrian A Dawkins, Leann Kania, Bruce M Lo, Ekta Maheshwari, Krupa K Patel-Lippmann, Kimberly L Shampain, Luyao Shen, Angela Tong, Robbie Zimbroff, Myra K Feldman","doi":"10.1016/j.jacr.2026.08.033","DOIUrl":"https://doi.org/10.1016/j.jacr.2026.08.033","url":null,"abstract":"<p><p>Acute pelvic pain, defined as pain in the lower abdomen or pelvis lasting <3 months, is a common presenting symptom in women of all ages. This document will focus on gynecologic causes of acute pelvic pain in the postmenopausal age group, an age group that deserve special consideration, as these etiologies may be more challenging to diagnose, may present with atypical symptoms, and have higher potential for malignancy than causes of acute pain in premenopausal women. Etiologies considered include ovarian torsion, pelvic inflammatory disease, and acute complications of uterine fibroids. Ultrasound is the initial imaging modality of choice, with MRI and CT used in cases where sonographic findings are inconclusive. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.</p>","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Educational Impact of Hybrid and Remote Work: Attending and Trainee Perspectives on Preparing the Next Generation of Radiologists.","authors":"Tina Shiang, Edwin Thai, Stacy E Smith, Connie Y Chang","doi":"10.1016/j.jacr.2026.09.030","DOIUrl":"https://doi.org/10.1016/j.jacr.2026.09.030","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate attending and trainee perspectives of hybrid and work from home (HYB-WFH) practice models and their implications for radiology education and preparedness for contemporary practice.</p><p><strong>Methods: </strong>A voluntary, anonymous 38-question electronic survey was distributed to musculoskeletal (MSK) attending radiologists and fellows, and radiology residents, through the Society of Skeletal Radiology (SSR). Descriptive statistics summarized respondent characteristics. Chi-square test compared attending and trainee responses. Thematic analysis identified recurring educational perspectives from free-text responses.</p><p><strong>Results: </strong>Most trainees (93%) supported HYB-WFH practice models, citing improved work-life balance, and no trainee preferred a fully in-person practice model. Most readouts remained in-person, although nearly all trainees reported experience with virtual readouts, and perceptions of virtual readouts were mixed. Trainees were more likely than attendings to report receiving formal preparation regarding HYB-WFH practice during training (68% vs 37%, p=0.0005) yet were significantly less likely to report feeling prepared for HYB-WFH practice (61% vs 83%, p=0.002). Nearly one-quarter of trainees (23%) indicated they would benefit from additional education, specifically regarding remote workflows and practical aspects of HYB-WFH practice. Thematic analysis identified that successful remote teaching requires intentional educational design for virtual readout and active engagement from faculty and trainees, while preserving opportunities for in-person mentorship, professional relationship-building, and learning to function as consultant physicians.</p><p><strong>Conclusions: </strong>As HYB-WFH practice models become increasingly integrated into radiology practice, training programs should deliberately prepare trainees for contemporary practice by incorporating education on remote workflows, virtual readouts, and strategies for building professional relationships.</p>","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of a High-Priority Scheduling Guideline on Diagnostic Breast Imaging Timeliness Across a Multisite System.","authors":"Manisha Bahl, Fionnuala McPeake, Joanna J Conte, Dylan C Kwait, Gary X Wang, Oleg S Pianykh, Ramin Khorasani","doi":"10.1016/j.jacr.2026.09.031","DOIUrl":"https://doi.org/10.1016/j.jacr.2026.09.031","url":null,"abstract":"<p><strong>Objective: </strong>Delays in access to diagnostic imaging may postpone breast cancer diagnosis, particularly for patients with symptoms concerning for malignancy. Following a safety event analysis, our multisite health care system implemented a standardized scheduling guideline in August 2024 requiring completion of high-priority diagnostic breast imaging within 3 weeks of order placement. This study evaluated the impact of the guideline on diagnostic imaging timeliness.</p><p><strong>Methods: </strong>This quality improvement study included diagnostic breast imaging examinations performed during preimplementation (August 1, 2023-July 31, 2024) and postimplementation (October 1, 2024-September 30, 2025) periods. High-priority indications included new breast or axillary mass, new nipple changes or unilateral nipple discharge, new skin dimpling or indentation, and new symptoms during active breast cancer treatment. The primary outcome was completion within 3 weeks of order placement. Comparisons of completion rates and time to completion between groups were performed using two-proportion z tests and Mann-Whitney U tests, respectively.</p><p><strong>Results: </strong>A total of 70,823 examinations were included (34,101 preimplementation; 36,722 postimplementation), including 7,224 high-priority postimplementation examinations (19.7%). Completion within 3 weeks improved from 57.4% (19,559/34,101) preimplementation to 65.3% (23,987/36,722) postimplementation (p<0.001), with median time to completion decreasing from 18 to 14 days (p<0.001). Before implementation, symptomatic examinations had lower 3-week completion than asymptomatic examinations (49.5% vs 61.3%, p<0.001). After implementation, high-priority examinations demonstrated higher 3-week completion than preimplementation symptomatic examinations (61.1% vs 49.5%, p<0.001).</p><p><strong>Discussion: </strong>Implementation of a standardized high-priority scheduling guideline improved timeliness of diagnostic breast imaging across a multisite health care system, particularly for patients with concerning symptoms.</p>","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Method for Selecting Communities for Efficient Equity-Informed Radiology Quality Improvement Interventions Applied to Recommendation for Additional Imaging Adherence.","authors":"Simon Kidanemariam, Ronilda Lacson, Ramin Khorasani, Jeffrey P Guenette","doi":"10.1016/j.jacr.2026.09.029","DOIUrl":"https://doi.org/10.1016/j.jacr.2026.09.029","url":null,"abstract":"<p><strong>Objective: </strong>Determine if recommendation for additional imaging (RAI) adherence is heterogeneous within similar socioeconomic strata and develop a more resource- and impact-efficient method for targeting community-based radiology quality interventions than those based on socioeconomic strata alone.</p><p><strong>Methods: </strong>Secondary analysis of RAI from a closed-loop communication system at a large academic medical center from a study conducted 10/21/2019-6/30/2021. A potential adherence improvement index (PAII: non-adherence rate multiplied by total RAI without adherence) was developed to reflect potential intervention impact on a given community. PAII, RAI adherence, area deprivation index (ADI), and ADI variance were compared between the highest PAII and ADI quintiles. Geospatial mapping and multifactorial plots were generated to visualize community distributions including the intersections between various PAII and ADI thresholds.</p><p><strong>Results: </strong>545 communities with 2 or more RAI were included. The highest PAII quintile communities were spread across geographic regions and ADI quintiles with only 20% (22 of 109) of these communities in the highest ADI quintile. Maps and plots showed optimal target communities for a variety of resource thresholds. Median ADI (higher=more socioeconomic disadvantage) was 16 (IQR 9-21) in highest PAII quintile vs. 29.5 (26-33.8) in highest ADI quintile (p<.001). RAI adherence was 41%±13% vs. 74%±25% (p<.001), respectively. Mean PAII (higher=more potential impact) was 1.53±0.61 vs. 0.49±0.69 (p<0.001), respectively. ADI variance was higher in the highest PAII quintile vs. highest ADI quintile (F=2.12, p<0.001).</p><p><strong>Discussion: </strong>Equity-informed radiology quality interventions can likely be more resource- and impact-efficient if composite socioeconomic criteria are combined with additional community-level exposure information to focus interventions on high-risk communities.</p>","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reducing Clinician Annotation Fatigue in Open-Set Federated Learning: A Client-Adaptive Vision-Language Gatekeeper.","authors":"Adea Nesturi, David Dueñas Gaviria, Jiajun Zeng, Mohammed Bahaaeldin, Julian A Luetkens, Shadi Albarqouni","doi":"10.1016/j.jacr.2026.09.023","DOIUrl":"https://doi.org/10.1016/j.jacr.2026.09.023","url":null,"abstract":"<p><strong>Purpose: </strong>Federated learning enables breast-imaging sites to jointly train mammography artificial intelligence (AI) without sharing images, but radiologists at each site must still annotate selected images during active-learning rounds. We developed and evaluated a client-adaptive vision-language gatekeeper that withholds radiopaque artifact-containing images considered unsuitable for a breast-density annotation objective and quantified its effect on annotation time, queue quality, and label reliability.</p><p><strong>Methods: </strong>In this retrospective, scanner-partitioned study, we used FedEMBED, derived from the public Emory Breast Imaging Dataset (222,700 training and 65,891 test images; four scanners; artifact prevalence 4.8%-13.1% per scanner). PromptGate adapted a biomedical vision-language model with site-specific learnable prompts and classified each image as relevant in-distribution (ID) or irrelevant out-of-distribution (OOD) using the class with the highest softmax probability. A single radiologist who is a member of the study team and has 2 years of breast imaging experience independently read a patient-separated, artifact-enriched cohort of 500 single mammographic views (ID, n=346; OOD, n=154). Cases were randomized, ID and OOD images were intermixed, and the reader was blinded to reference labels, PromptGate decisions, enrichment status, and scanner metadata.</p><p><strong>Results: </strong>PromptGate withheld 101 of 154 artifact-containing images and 54 of 346 ID images, corresponding to 65.6% artifact sensitivity, 84.4% ID retention, and a 15.6% false-removal rate among ID images. Gross annotation time decreased by ∼30% (3.82 to 2.68 hours; 1.14 hours) in the enriched cohort; an analysis crediting only correctly removed artifacts yielded an estimated 20.0% reduction. A simple prevalence-based extrapolation suggests an approximate 20- to 65-min saving per 500 images at the observed scanner-specific prevalence, although the absolute benefit is expected to be smaller than in the enriched cohort. Artifact discrimination reached an area under the receiver operating characteristic curve of 0.85. Reader agreement with the manual artifact reference was 93.6% (κ=0.85), whereas agreement with the clinical-record density label was 60.9% exact (κ=0.48). Queue purity reached 92.5%, compared with 88.5% without filtering and 87.0% with a static vision-language model filter, while downstream density accuracy remained similar to the unfiltered condition.</p><p><strong>Conclusion: </strong>In this retrospective proof-of-concept study, a privacy-oriented, scanner-adaptive vision-language gate improved the concentration of task-relevant images in federated breast-density annotation queues and reduced gross reading time. Because some ID images were incorrectly withheld and the reader study used an artifact-enriched cohort, a prospective multireader and multi-institutional evaluation is needed before operational deployment.</p>","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reducing Disruptive and Unnecessary Calls With Education and Electronic Chat for Asynchronous Liaison With Radiology: The REDUCE-CALL Study.","authors":"Subhashaan Sreedharan, Lut Chan, Andrew Coote, Callum Umstad, Andy Le, Mark McCusker, Diane Pascoe, Stefan B Heinze","doi":"10.1016/j.jacr.2026.09.028","DOIUrl":"10.1016/j.jacr.2026.09.028","url":null,"abstract":"<p><strong>Objective: </strong>Frequent telephone calls to radiology departments are a major source of workflow interruption and inefficiency. Asynchronous messaging integrated within an electronic medical record may provide a more efficient communication pathway. This study evaluated the impact of implementing an electronic medical record-integrated chat function, supported by targeted education initiatives, on communication volumes and protocolling workflow in a tertiary academic radiology department.</p><p><strong>Methods: </strong>A retrospective pre- and post-intervention study compared workflow metrics across 20 matched weekdays before and after implementation. The primary outcome was in-hours telephone calls per weekday to the duty radiologist. Secondary outcomes included studies protocolled per day, time to protocol, total communication events (telephone calls plus messages), workload-adjusted communication events (communication events per 100 protocolled studies), and chat responsiveness. Comparisons were performed using the Mann-Whitney U test, with workload-adjusted contact rates analyzed using a Poisson model.</p><p><strong>Results: </strong>Median telephone calls to the duty radiologist decreased from 181 (interquartile range [IQR] 166-220) to 82 (IQR 60-103) per day P < .001). Total communication events decreased from 181 (IQR 166-220) to 104 (IQR 87-134) per weekday (P < .001). Number of studies protocolled was unchanged (92 [IQR 88-101] versus 97 [IQR 89-108] per day; P = .29). Workload-adjusted communication events decreased from 205 to 114 per 100 studies protocolled (rate ratio 0.56, 95% confidence interval 0.53-0.59; P < .001). Median time to read and time to reply for chat were 8 min (IQR 2-24) and 14 min (IQR 5-34), respectively.</p><p><strong>Discussion: </strong>Implementation of asynchronous messaging, supported by targeted education initiatives, was associated with a substantial reduction in both telephone calls and total communication volume (calls plus messages) without affecting protocolling productivity. Chat messages were reviewed and answered in a timely manner. These findings support a scalable strategy to reduce communication-related interruptions in high-volume radiology departments.</p>","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Expeditionary Radiology: Designing Human-AI Collaboration in Limited-Connectivity Military Medicine.","authors":"Nathan A Bumbarger, Brian A Telfer, Lars A Gjesteby, Florence X Doo","doi":"10.1016/j.jacr.2026.09.027","DOIUrl":"https://doi.org/10.1016/j.jacr.2026.09.027","url":null,"abstract":"","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Federated Learning - Towards Privacy-Preserving, Adaptable and Scalable Artificial Intelligence Integration in Clinical Breast Imaging Workflow.","authors":"Hyun Soo Ko","doi":"10.1016/j.jacr.2026.09.025","DOIUrl":"https://doi.org/10.1016/j.jacr.2026.09.025","url":null,"abstract":"","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149083122","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Association Between Technical Component Billing for Medical Imaging and the Likelihood of Radiology Practice Closure.","authors":"Eric W Christensen, Chi-Mei Liu, Eric M Rubin, Elizabeth Y Rula, Richard Duszak","doi":"10.1016/j.jacr.2026.08.026","DOIUrl":"https://doi.org/10.1016/j.jacr.2026.08.026","url":null,"abstract":"","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial Intelligence Latency, Report Turnaround Time, and Adoption in a Multivendor Artificial Intelligence Ecosystem: A Multisite Observational Study.","authors":"Sergey Morozov, Natalie Heracleous, Octave Novarina, Diana Korka, Benoît Dufour, Cyril Thouly, Benoît Rizk","doi":"10.1016/j.jacr.2026.09.026","DOIUrl":"10.1016/j.jacr.2026.09.026","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate infrastructure latency, workflow, and radiologist sentiment across a 4.5-year, multivendor artificial intelligence (AI) implementation program in a 20-center outpatient radiology network.</p><p><strong>Methods: </strong>Three retrospective cohorts: a technical cohort (96,874 examinations; Sep 2023-Sep 2025) for PACS-to-PACS latency of 9 AI tools and temporal alignment of 10 AI tools; a report turnaround time (TAT) analysis cohort (20,909 examinations; March to August 2025) comparing TAT between AI-available and concurrent non-AI workflows by Mann-Whitney U; and a survey cohort (58 radiologists; two waves 2025) for adoption, Likert-scale perceptions, and Net Promoter Score.</p><p><strong>Results: </strong>Active AI adoption was 91.4% (53 of 58), with 66% (35 of 53) reporting regular use. Median total latency was 2.06 min (IQR 1.74-3.05), 72% of which attributable to data routing. The \"Too Late\" rate (AI result arriving after report finalization) was 7.2% overall, ranging from 3.0% for knee MRI to 13.2% for chest CT. After adjustment for radiologist (linear mixed-effects models), AI availability was associated with lower median TAT for trauma radiography (-26%) and knee MRI (-18%; both P < .001); brain volumetry MRI showed no significant change (+9.2%; P = .33). In exploratory analysis, Net Promoter Score declined for chest CT (+38 to -3) and aorta CT (+22 to -25), nominally significant before multiple-comparison correction.</p><p><strong>Discussion: </strong>Multivendor AI at scale was associated with measurable TAT gains in high-volume modalities. Infrastructure latency, not algorithm speed, was the primary barrier to clinical utility. At ∼23% to 25% annualized cost of one radiologist full-time equivalent (FTE) salary, the program generated 0.69 FTE of capacity through trauma radiography alone (0.46 FTE after radiologist-adjusted sensitivity analysis).</p>","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149083124","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}