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

{"title":"Better Than Nothing Is Not a Standard: Lessons From Drug Development for Radiology AI Evaluation.","authors":"Julio Min Fei Zhang, Bruno Hochhegger","doi":"10.1016/j.jacr.2026.08.031","DOIUrl":"10.1016/j.jacr.2026.08.031","url":null,"abstract":"","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148992834","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":"Patient-Friendly Summary of the ACR Appropriateness Criteria®: Renovascular Hypertension.","authors":"Jayden Lee, David H Kim","doi":"10.1016/j.jacr.2026.09.009","DOIUrl":"10.1016/j.jacr.2026.09.009","url":null,"abstract":"","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148992859","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":"Patient-Friendly Summary of the ACR Appropriateness Criteria®: Rib Fractures.","authors":"Avani Shinde, Maria Daniela Martin Rother","doi":"10.1016/j.jacr.2026.09.008","DOIUrl":"10.1016/j.jacr.2026.09.008","url":null,"abstract":"","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148992819","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":"Patient-Friendly Summary of the ACR Appropriateness Criteria®: Breast Implant Evaluation: 2026 Update.","authors":"Yash Sachin Saboo, Sonya Bhole","doi":"10.1016/j.jacr.2026.09.012","DOIUrl":"10.1016/j.jacr.2026.09.012","url":null,"abstract":"","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148992814","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":"Structural Brain Imaging for Newly Diagnosed Cognitive Impairment by Medicare Coverage Type.","authors":"Soeren Mattke, Ying Liu, Wei Ye, Kimberly Altunkaynak","doi":"10.1016/j.jacr.2026.09.002","DOIUrl":"10.1016/j.jacr.2026.09.002","url":null,"abstract":"<p><strong>Purpose: </strong>Structural brain imaging is guideline-recommended for cases with newly diagnosed cognitive impairment. Adherence to this recommendation and differences by Medicare coverage type are not known. We determined the structural imaging rate overall and by Medicare coverage type: traditional Medicare, Medicare Advantage, and dual eligibility for Medicare and Medicaid (\"duals\") and diagnosis of mild cognitive impairment (MCI) and dementia.</p><p><strong>Methods: </strong>In this cross-sectional study, we used the 100% data for traditional Medicare and Medicare Advantage from 2020 through 2022. A total of 1,095,947 community-dwelling Medicare beneficiaries aged 65 to 84 were newly diagnosed with cognitive impairment in 2021, 373,561 (34.1%) with MCI and 722,386 (65.9%) with dementia. We determined receipt of structural imaging with MRI or CT scan within 365 days before or after the diagnosis.</p><p><strong>Results: </strong>Overall imaging rates within 365 days of diagnosis were 56.6% overall and 65.9% and 50.5% for an initial diagnosis of dementia and MCI, respectively. Rates were higher for nonduals than duals in traditional Medicare (60.5% versus 57.9%) and members of Medicare Advantage Plans (54.35 versus 52.7%). The initial scan was performed with an MRI in 29.3% of cases with lower rates in duals and Medicare Advantage.</p><p><strong>Conclusions: </strong>In the 2021 full Medicare population with a new diagnosis of cognitive impairment, structural brain imaging was substantially underused. This gap in appropriate care was accentuated in Medicare Advantage Plan members and the socioeconomically disadvantaged duals. Sustained efforts are needed to ensure equitable adherence to this guideline-recommended procedure.</p><p><strong>Summary: </strong>This observational study of the full Medicare population shows that structural brain imaging after diagnosis of cognitive impairment is underused, with lower rates in Medicare Advantage and for duals.</p>","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13714822/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148979154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prospective Shadow-Mode Evaluation of an Artificial Intelligence Tool for Intracranial Aneurysm Detection on CT Angiography: Incremental Yield and Operational Impact.","authors":"Shlomit Goldberg-Stein, Maria X Sanmartin, Rachel Saks, Jerrin Varghese, Yasser Mir, Amir Gandomi, Jonathan Scheiner, Ritesh D Patel, David Hirschorn, Elizabeth Y Rula, Jason J Naidich, Matthew A Barish, Pina C Sanelli","doi":"10.1016/j.jacr.2026.07.018","DOIUrl":"https://doi.org/10.1016/j.jacr.2026.07.018","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate the operational performance of an FDA-cleared artificial intelligence (AI) algorithm for brain CT angiography (CTA) aneurysm detection and the incremental value of combining AI with radiologists.</p><p><strong>Methods: </strong>Prospective shadow-mode study of consecutive brain CTAs (November 7, 2023, to December 19, 2023) was performed with radiologists blinded to AI. Aidoc's (Tel Aviv, Israel) AI algorithm processed CTAs, and natural language processing extracted radiology report results. Discordances underwent neuroradiologist adjudication with AI unblinding. Performance metrics included AI:radiologist incremental detection ratio, relative enhanced detection rate (rEDR), gain-to-pain ratio (GPR), and number-needed-to-examine (NNE). Performance metrics are estimated under a hybrid reference standard wherein only discordances are adjudicated.</p><p><strong>Results: </strong>Among 3,856 CTAs, examination positive rate was 5.1% (195 of 3,856). Radiologist-AI concordance was 96.3% (3,714 of 3,856). Sensitivity of AI alone (0.846, 0.787-0.894) exceeded radiologist alone (0.718, 0.649-0.779), with similar specificity (radiologist: 0.985, 0.981-0.989; AI: 0.987, 0.983-0.991). AI surfaced additional aneurysms not identified by radiologists, yielding an rEDR of 39% (55 AI-only true-positives per 140 radiologist true-positives) and projecting a higher combined sensitivity for radiologists with AI. AI:radiologist incremental detection ratio was 1.83 (55 of 30), favorable for AI. Operationally, GPR was favorable at 1.20 (55 of 46), and NNE was 70.1 (3,856 of 55). Operational metrics were most favorable in inpatients (rEDR 78.3%, GPR 2.57, NNE 28.9) and emergency (rEDR 37.1%, GPR 1.0, NNE 85.3) and were unfavorable in outpatients (rEDR 14.1%, GPR 0.67, NNE 130.3). Most AI-only aneurysms were <3 mm (31 of 55, 56.4%); radiologist-only were mostly 3 to 5 mm (18 of 33, 54.5%).</p><p><strong>Conclusions: </strong>The AI tool demonstrated favorable operational performance, supporting clinical deployment in real-world practice, although setting-specific metrics were variable.</p>","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148972768","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 Meaningful First Step Toward Large Language Model Quality Control of Breast Ultrasound Reports.","authors":"Ethen O Cohen, Jessica W T Leung","doi":"10.1016/j.jacr.2026.09.005","DOIUrl":"10.1016/j.jacr.2026.09.005","url":null,"abstract":"","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148946260","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":"Strategic Multidimensional Benchmark Deployment-Operationalizing National Standards on Prostate MRI and PI-RADS Adoption.","authors":"Ivo G Schoots, Masoom A Haider","doi":"10.1016/j.jacr.2026.09.004","DOIUrl":"10.1016/j.jacr.2026.09.004","url":null,"abstract":"","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148946304","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":"Breast Cancer Method of Detection: Screening Associated With Favorable Tumor Characteristics, Treatment, and Survival Across Age Groups.","authors":"Babita Panigrahi, Alexandra DiTommaso, Naveen Ghuman, Kelly S Myers, Lisa A Mullen, Emily B Ambinder, Eniola T Oluyemi","doi":"10.1016/j.jacr.2026.09.003","DOIUrl":"10.1016/j.jacr.2026.09.003","url":null,"abstract":"<p><strong>Objective: </strong>Breast cancer method of detection (MOD) describes how a cancer is first identified: through screening or nonscreening (symptomatic or incidental) presentation. We examined associations between MOD and patient demographics, tumor characteristics, treatment patterns, and survival.</p><p><strong>Methods: </strong>This retrospective cohort study included women ≥40 years diagnosed with breast cancer between January 2019 and December 2021, with follow-up through July 2026. MOD was classified as screen-detected or non-screen-detected cancer. Logistic regression and χ² tests evaluated associations with patient, tumor, and treatment variables. Kaplan-Meier and multivariable Cox regression assessed all-cause survival.</p><p><strong>Results: </strong>Among 1,023 women (mean age 63.5 ± 12.1 years), screen-detected cancers (n = 710, 69.4%) had more favorable characteristics: earlier T stage (T0: 26.3% versus 5.4%, P < .001), negative lymph nodes (N0: 85.5% versus 59.1%, P < .001), fewer metastases (M0: 98.6% versus 82.4%, P < .001), and lower grade (grade 1: 18.6% versus 7.4%, P < .001). More received lumpectomy (72.1% versus 50.2%, P < .001) and fewer received neoadjuvant chemotherapy (5.2% versus 22.5%, P < .001). Non-screen-detected cancers were more common among the unemployed (21.0% versus 14.0%, P = .001), uninsured (3.8% versus 1.7%, P = .026), and women ≥ 75 years (23.3% versus 16.1%, P = .019). Within non-screen-detected cancers, tumor stage worsened with time since last negative screen (P < .001). Screen-detected cancers showed superior all-cause survival (5-year survival: 92.9% versus 73.6%, P < .001). After adjustment, screen detection was independently associated with 43% lower mortality (hazard ratio = 0.57, P = .003). Significant survival benefit persisted in women ≥ 75 years (hazard ratio = 0.44, P = .014).</p><p><strong>Discussion: </strong>Screen-detected breast cancers were associated with favorable biology, less aggressive treatment, and improved survival. These findings can inform screening guidelines and underscore the importance of incorporating MOD into cancer registries.</p>","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148946277","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":"Human Judgment and the Limits of Artificial Intelligence for Automated Rank Order Lists in Diagnostic Radiology Residency Selection.","authors":"Cody H Savage, Rydhwana Hossain, James Mac Tonascia, Athanasios Pavlou, Charles S Resnik, Florence X Doo, Elana B Smith","doi":"10.1016/j.jacr.2026.09.006","DOIUrl":"10.1016/j.jacr.2026.09.006","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;To evaluate whether large language models (LLMs) can reliably reproduce a residency program's rank order list (ROL) from pre-interview application data alone versus with human interviews included and to determine whether automated ranking tools safely mirror human consensus or inadvertently introduce systematic displacements against specific applicant subgroups.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;In this single-institution pilot study of 148 applicants interviewed during the 2025-2026 cycle, seven LLM configurations (three proprietary models [each at \"medium\" and \"high\" reasoning levels] and one open-weight model) each generated 10 independent ROLs from de-identified application data under two conditions: pre-interview \"application-only\" data alone, and then with interview scores added (140 lists total). Nonmodel baselines (sorting solely by interview score or United States Medical Licensing Examination Step 2 Clinical Knowledge score) were also established. LLM lists were compared with the human committee's final ROL using a truth-anchored weighted Kendall's τ and precision@k (k = 10-40); rank displacement by applicant subgroup was also assessed.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The human committee's final ROL required approximately 390 faculty-hours to order 148 applicants for 7 positions. For LLMs in the application-only condition, all LLM configurations showed low agreement with the final ROL (median τ 0.15-0.36). In the positive control condition with human interviews included, agreement rose to excellent (median τ 0.84-0.93). Sorting applicants by summed interviewer score alone reproduced the final list at τ-b = 0.83, whereas sorting by United States Medical Licensing Examination Step 2 Clinical Knowledge score alone produced τ-b = 0.12. Increasing reasoning level from \"medium\" to \"high\" did not consistently improve agreement. In the application-only condition, LLM rankings systematically placed female, international, and non-MD applicants below the human committee's list (q &lt; .05), and program signalers were placed higher.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Discussion: &lt;/strong&gt;LLMs failed to replicate the human program's final ROL from pre-interview application-only data alone. The positive control including the human interview confirms this human-LLM lack of agreement may stem from the limited application-only data provided, rather than the models' inability to perform ranking tasks once provided the additional human judgment information. Importantly, these findings do not establish whether the LLM model or the human committee produced the \"better\" ROL; these data suggest that LLM rankings generated solely from pre-interview data systematically differed from the human committee's consensus, and may disproportionately penalize certain subgroups. Our findings suggest that artificial intelligence should not be used as a primary ROL generator or a replacement for human judgment but may serve supportive roles in tasks such as data retri","PeriodicalId":73968,"journal":{"name":"Journal of the American College of Radiology : JACR","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148946269","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}