Radiology最新文献

{"title":"Uncovering Demographic Bias in Natural Language Processing Tools for Radiology.","authors":"Wenli Cai","doi":"10.1148/radiol.242723","DOIUrl":"https://doi.org/10.1148/radiol.242723","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"313 1","pages":"e242723"},"PeriodicalIF":12.1,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142473376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI-derived Tumor Volume from Multiparametric MRI and Outcomes in Localized Prostate Cancer.","authors":"David D Yang, Leslie K Lee, James M G Tsui, Jonathan E Leeman, Heather M McClure, Atchar Sudhyadhom, Christian V Guthier, Mary-Ellen Taplin, Quoc-Dien Trinh, Kent W Mouw, Neil E Martin, Peter F Orio, Paul L Nguyen, Anthony V D'Amico, Kee-Young Shin, Katie N Lee, Martin T King","doi":"10.1148/radiol.240041","DOIUrl":"10.1148/radiol.240041","url":null,"abstract":"<p><p>Background An artificial intelligence (AI)-based method for measuring intraprostatic tumor volume based on data from MRI may provide prognostic information. Purpose To evaluate whether the total volume of intraprostatic tumor from AI-generated segmentations (V_AI) provides independent prognostic information in patients with localized prostate cancer treated with radiation therapy (RT) or radical prostatectomy (RP). Materials and Methods For this retrospective, single-center study (January 2021 to August 2023), patients with cT1-3N0M0 prostate cancer who underwent MRI and were treated with RT or RP were identified. Patients who underwent RT were randomly divided into cross-validation and test RT groups. An AI segmentation algorithm was trained to delineate Prostate Imaging Reporting and Data System (PI-RADS) 3-5 lesions in the cross-validation RT group before providing segmentations for the test RT and RP groups. Cox regression models were used to evaluate the association between V_AI and time to metastasis and adjusted for clinical and radiologic factors for combined RT (ie, cross-validation RT and test RT) and RP groups. Areas under the receiver operating characteristic curve (AUCs) were calculated for V_AI and National Comprehensive Cancer Network (NCCN) risk categorization for prediction of 5-year metastasis (RP group) and 7-year metastasis (combined RT group). Results Overall, 732 patients were included (combined RT group, 438 patients; RP group, 294 patients). Median ages were 68 years (IQR, 62-73 years) and 61 years (IQR, 56-66 years) for the combined RT group and the RP group, respectively. V_AI was associated with metastasis in the combined RT group (median follow-up, 6.9 years; adjusted hazard ratio [AHR], 1.09 per milliliter increase; 95% CI: 1.04, 1.15; <i>P</i> = .001) and the RP group (median follow-up, 5.5 years; AHR, 1.22; 95% CI: 1.08, 1.39; <i>P</i> = .001). AUCs for 7-year metastasis for the combined RT group for V_AI and NCCN risk category were 0.84 (95% CI: 0.74, 0.94) and 0.74 (95% CI: 0.80, 0.98), respectively (<i>P</i> = .02). Five-year AUCs for the RP group for V_AI and NCCN risk category were 0.89 (95% CI: 0.80, 0.98) and 0.79 (95% CI: 0.64, 0.94), respectively (<i>P</i> = .25). Conclusion The volume of AI-segmented lesions was an independent, prognostic factor for localized prostate cancer. © RSNA, 2024 <i>Supplemental material is available for this article.</i></p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"313 1","pages":"e240041"},"PeriodicalIF":12.1,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142522810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Case 330: Ovarian Torsion in the Setting of Ovarian Hyperstimulation Syndrome.","authors":"Maria Zulfiqar, Fatima Al Khafaji, Megan Wasson","doi":"10.1148/radiol.231864","DOIUrl":"10.1148/radiol.231864","url":null,"abstract":"<p><strong>History: </strong>A 30-year-old female patient with a history of infertility and no pregnancy presented to the gynecologic endometriosis clinic for follow-up 1 month after oocyte retrieval, to be evaluated for pelvic optimization before potential embryo transfer, with worsening dysmenorrhea, dyspareunia, and overall pelvic pain. Eleven years prior, the patient had undergone left ovarian cystectomy for treatment of endometrioma, as well as excision of deep infiltrating endometriosis. The oocyte retrieval procedure, where more than 30 eggs were retrieved, was complicated by ovarian hyperstimulation syndrome and intraperitoneal bleeding, which necessitated admission to the intensive care unit (ICU) for 3 days. Following discharge from the ICU, the patient experienced occasional on-and-off pressure of the urinary bladder and persistent aching pelvic pain.</p><p><p>At the 1-month follow-up appointment, the patient's vital signs were assessed (blood pressure, 142/94 mm Hg; pulse rate, 95 per minute; temperature, 96.8 °F [36 °C]). Routine blood investigations, including white blood cell count, were within normal limits. Physical examination showed the abdomen was soft but there was mild pelvic tenderness. The serum β-human chorionic gonadotropin test result was negative for pregnancy, and urinalysis testing showed no leukocyte esterase or nitrites. MRI of the pelvis was performed to evaluate the worsening pain.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"313 1","pages":"e231864"},"PeriodicalIF":12.1,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142522820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Step Closer to ADC as a Biomarker in Clinical Practice.","authors":"Masoom A Haider","doi":"10.1148/radiol.241036","DOIUrl":"https://doi.org/10.1148/radiol.241036","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"79 1","pages":"e241036"},"PeriodicalIF":19.7,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142385530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multifocal Fibromuscular Dysplasia Involving the Coronary Arteries.","authors":"Xingshun Zhou,Cong Huang","doi":"10.1148/radiol.241283","DOIUrl":"https://doi.org/10.1148/radiol.241283","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"16 1","pages":"e241283"},"PeriodicalIF":19.7,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142385484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnostic Accuracy of Screening Contrast-enhanced Mammography for Women with Extremely Dense Breasts at Increased Risk of Breast Cancer.","authors":"Noam Nissan, Christopher E Comstock, Varadan Sevilimedu, Jill Gluskin, Victoria L Mango, Mary Hughes, R Elena Ochoa-Albiztegui, Janice S Sung, Maxine S Jochelson","doi":"10.1148/radiol.232580","DOIUrl":"10.1148/radiol.232580","url":null,"abstract":"<p><p>Background Mammogram interpretation is challenging in female patients with extremely dense breasts (Breast Imaging Reporting and Data System [BI-RADS] category D), who have a higher breast cancer risk. Contrast-enhanced mammography (CEM) has recently emerged as a potential alternative; however, data regarding CEM utility in this subpopulation are limited. Purpose To evaluate the diagnostic performance of CEM for breast cancer screening in female patients with extremely dense breasts. Materials and Methods This retrospective single-institution study included consecutive CEM examinations in asymptomatic female patients with extremely dense breasts performed from December 2012 to March 2022. From CEM examinations, low-energy (LE) images were the equivalent of a two-dimensional full-field digital mammogram. Recombined images highlighting areas of contrast enhancement were constructed using a postprocessing algorithm. The sensitivity and specificity of LE images and CEM images (ie, including both LE and recombined images) were calculated and compared using the McNemar test. Results This study included 1299 screening CEM examinations (609 female patients; mean age, 50 years ± 9 [SD]). Sixteen screen-detected cancers were diagnosed, and two interval cancers occured. Five cancers were depicted at LE imaging and an additional 11 cancers were depicted at CEM (incremental cancer detection rate, 8.7 cancers per 1000 examinations). CEM sensitivity was 88.9% (16 of 18; 95% CI: 65.3, 98.6), which was higher than the LE examination sensitivity of 27.8% (five of 18; 95% CI: 9.7, 53.5) (<i>P</i> = .003). However, there was decreased CEM specificity (88.9%; 1108 of 1246; 95% CI: 87.0, 90.6) compared with LE imaging (specificity, 96.2%; 1199 of 1246; 95% CI: 95.0, 97.2) (<i>P</i> < .001). Compared with specificity at baseline, CEM specificity at follow-up improved to 90.7% (705 of 777; 95% CI: 88.5, 92.7; <i>P</i> = .01). Conclusion Compared with LE imaging, CEM showed higher sensitivity but lower specificity in female patients with extremely dense breasts, although specificity improved at follow-up. © RSNA, 2024 See also the editorial by Lobbes in this issue.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"313 1","pages":"e232580"},"PeriodicalIF":12.1,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11535862/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142352725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Retrieval-Augmented Generation for Large Language Models in Radiology: Another Leap Forward in Board Examination Performance.","authors":"Rajesh Bhayana, Aly Fawzy, Yangqing Deng, Robert R Bleakney, Satheesh Krishna","doi":"10.1148/radiol.241489","DOIUrl":"https://doi.org/10.1148/radiol.241489","url":null,"abstract":"<p><p><i>Supplemental material is available for this article.</i> See also the editorial by Forghani in this issue.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"313 1","pages":"e241489"},"PeriodicalIF":12.1,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142392797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of Patient-reported Symptom Information on the Interpretation of MRI of the Lumbar Spine.","authors":"Rene Balza, Sarah F Mercaldo, Ambrose J Huang, Jad S Husseini, Mohamed Jarraya, F Joseph Simeone, Joao R T Vicentini, William E Palmer","doi":"10.1148/radiol.233487","DOIUrl":"10.1148/radiol.233487","url":null,"abstract":"<p><p>Background Distinguishing lumbar pain generators from incidental findings at MRI can be difficult. Dictated reports may become lists of findings that cannot be ranked in order of diagnostic importance. Purpose To determine whether patient-reported symptom information can improve the interpretation of lumbar spine MRI by using the spine specialist as the reference standard. Materials and Methods This prospective, single-center, multireader study analyzed 240 participants who completed pre-MRI symptom questionnaires between May 2022 and February 2023. At the time of clinical MRI reporting, radiologists recorded pain generators in consecutive participants, creating two study groups by alternating interpretations with versus without symptom questionnaire results (SQR). Diagnostic certainty was recorded using a numeric scale of 0 to 100. Types, levels, and sides of pain generators were compared with reference diagnoses by calculating Cohen κ values with 95% CIs. Participant characteristics and diagnostic certainties were compared using the Wilcoxon rank sum, Pearson χ², or Kruskal-Wallis test. Interrater agreement was analyzed. Results There was no difference in age (<i>P</i> = .69) or sex (<i>P</i> = .60) between participants using SQR (<i>n</i> = 120; mean age, 61.0 years; 62 female) and not using SQR (<i>n</i> = 120; mean age, 62.5 years; 67 female). When radiologists were compared with specialists, agreements on pain generators were almost perfect for interpretations using SQR (type: κ = 0.82 [95% CI: 0.74,0.89]; level: κ = 0.88 [95% CI: 0.80, 0.95]; side: κ = 0.84 [95% CI: 0.75, 0.92]), but only fair to moderate for interpretations not using SQR (type: κ = 0.26 [95% CI: 0.15, 0.36]; level: κ = 0.51 [95% CI: 0.39, 0.63]; side: κ = 0.30 [95% CI: 0.18, 0.42]) (all <i>P</i> < .001). Diagnostic certainty was higher for MRI interpretations using SQR (mean, 80.4 ± 14.9 [SD]) than MRI interpretations not using SQR (60.5 ± 17.7) (<i>P</i> < .001). Interrater agreements were substantial (κ = 0.65-0.78) for MRI interpretations using SQR but only fair to moderate (κ = 0.24-0.49) for MRI interpretations not using SQR (all <i>P</i> < .001). Conclusion Patient-reported symptom information enabled radiologists to achieve nearly perfect diagnostic agreement with clinical experts. © RSNA, 2024 See also the editorial by Isikbay and Shah in this issue.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"313 1","pages":"e233487"},"PeriodicalIF":12.1,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142522825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"US Attenuation Coefficient for Liver Fat Quantification: A Need for Standardization.","authors":"Aiguo Han","doi":"10.1148/radiol.242511","DOIUrl":"10.1148/radiol.242511","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"313 1","pages":"e242511"},"PeriodicalIF":12.1,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11535872/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142522830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact on Prognosis of Stage I Non-Small Cell Lung Cancer Secondary to Delays in Diagnostic Workup.","authors":"David F Yankelevitz, Rowena Yip, Claudia I Henschke","doi":"10.1148/radiol.240420","DOIUrl":"10.1148/radiol.240420","url":null,"abstract":"<p><p>Background Diagnostic workup of small pulmonary nodules often requires follow-up CT scans to confirm nodule growth before invasive diagnostics or treatment. Purpose To confirm prior results from the International Early Lung Cancer Action Program (I-ELCAP) on quantifying decreases in lung cancer prognosis by using two large databases, the National Lung Screening Trial (NLST) and International Association for the Study of Lung Cancer (IASLC). Materials and Methods In this retrospective study, a model was developed to predict cure rates based on size of solid nodules using the NLST (August 2002 to summer 2007) and IASLC (January 2011 to December 2019) databases, focusing on stage I non-small cell lung cancer (NSCLC). Kaplan-Meier methods were used to calculate 10-year lung cancer-specific survival and 5-year overall survival rates for different tumor sizes. Tumor diameter increases after 90-, 180-, and 365-day delays were estimated using volume doubling times (VDTs) of 60, 120, and 240 days corresponding to fast, moderate, and slow tumor growth. Initial and delayed lung cancer cure rates were assessed across nine scenarios of time delays and tumor growth rates and compared with the previous results of the I-ELCAP database. Results Using regression models based on 166 NLST and 22 590 IASLC patients with NSCLC, 10-year lung cancer-specific survival and 5-year overall survival, respectively, for tumors 4.0-20.0 mm in diameter were estimated. For a 20.0-mm tumor with a 60-day VDT in the NLST database, the lung cancer-specific survival decreased from 83.4% to 76.5%, 66.8%, and 32.3% after 90, 180, and 365 days, respectively. The IASLC database showed similar decreases in 5-year overall survival, from 81.2% to 73.4%, 62.4%, and 23.3% after 90, 180, and 365 days, respectively. Comparison across NLST, IASLC, and I-ELCAP databases revealed minor variations in lung cancer cure rates between 79.9% and 83.4%, with reductions of 6.9%-8.3% after a 180-day delay with a 120-day VDT. Conclusion The NLST and IASLC databases confirmed prior estimates from the I-ELCAP database for the decrease in lung cancer prognosis due to diagnostic delays. © RSNA, 2024 <i>Supplemental material is available for this article.</i> See also the editorial by Park and Lee in this issue.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"313 1","pages":"e240420"},"PeriodicalIF":12.1,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142473354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}