Radiology最新文献

{"title":"Moral Distress, Moral Injury, and Burnout in Radiology Practice.","authors":"Bettina Siewert, Rama Ayyala","doi":"10.1148/radiol.241174","DOIUrl":"https://doi.org/10.1148/radiol.241174","url":null,"abstract":"<p><p>Moral distress, which causes burnout, is a growing issue in health care since its initial description in 1984. The relationship among moral distress, moral injury (sustained moral distress), and burnout is critical to understanding the implications for physicians' mental and physical health and the impact on patient care. Moral distress can lead to an increase in medical errors and result in low quality of care for patients. There are five common causes of moral distress in radiology that can affect patient care. These include high workload, lack of leadership support, clinical demands interfering with teaching mission, lack of team communication, and disregard for professional expertise by pressuring radiologists to perform unnecessary or inappropriate imaging. This article analyzes current work environment challenges contributing to these issues, including causes of high workload, staffing crisis in radiology, and lack of time for nonclinical missions (eg, teaching, research, continuing medical education, practice building, reading literature, mentoring, and society volunteering). Moral distress and intention to leave were compared between radiology and other specialties. Concrete solutions to address causes of moral distress are outlined. These solutions include developing guidelines for safe workloads, servant leadership models, and tips for maintaining the teaching mission in a busy academic work environment and improving communication between clinicians. Possible solutions to national problems such as high workload, reduction of inappropriate imaging, seeking reimbursement for noninterpretative tasks, and short staffing are also described.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"315 2","pages":"e241174"},"PeriodicalIF":12.1,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144111790","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":"Cinematic Rendering of Tumor-related Arteriovenous Fistula of the Kidney.","authors":"Yu Zhang, Tao Shuai","doi":"10.1148/radiol.242600","DOIUrl":"https://doi.org/10.1148/radiol.242600","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"315 2","pages":"e242600"},"PeriodicalIF":12.1,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144151437","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":"Adrenal Vein Sampling: The Value of Multisampling and Adrenocorticotropic Hormone Stimulation and a Call to Arms.","authors":"Christos Georgiades","doi":"10.1148/radiol.250797","DOIUrl":"https://doi.org/10.1148/radiol.250797","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"315 1","pages":"e250797"},"PeriodicalIF":12.1,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144021618","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":"Sarcopenia, Obesity, and Sarcopenic Obesity: Retrospective Audit of Electronic Health Record Documentation versus Automated CT Analysis in 17 646 Patients.","authors":"Juan M Zambrano Chaves, Jason Hom, Leon Lenchik, Akshay S Chaudhari, Robert D Boutin","doi":"10.1148/radiol.243525","DOIUrl":"https://doi.org/10.1148/radiol.243525","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"315 1","pages":"e243525"},"PeriodicalIF":12.1,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144012224","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":"MRISegmenter: A Fully Accurate and Robust Automated Multiorgan and Structure Segmentation Tool for T1-weighted Abdominal MRI.","authors":"Yan Zhuang, Tejas Sudharshan Mathai, Pritam Mukherjee, Brandon Khoury, Boah Kim, Benjamin Hou, Nusrat Rabbee, Abhinav Suri, Ronald M Summers","doi":"10.1148/radiol.241979","DOIUrl":"https://doi.org/10.1148/radiol.241979","url":null,"abstract":"<p><p>Background There is a pressing demand to develop an automated segmentation tool for abdominal MRI that can provide accurate and robust segmentation in more than 60 abdominal organs and structures. Purpose To develop and evaluate the accuracy and robustness of an automated multiorgan and structure segmentation tool for T1-weighted abdominal MRI. Materials and Methods In this retrospective study, a T1-weighted abdominal MRI dataset composed of axial precontrast T1-weighted and contrast-enhanced T1-weighted arterial, portal venous, and delayed phases for each patient in a randomly selected sample was included at the National Institutes of Health Clinical Center. Each MRI series contained voxel-level annotations of 62 abdominal organs and structures. A three-dimensional segmentation (nnU-Net) model, called MRISegmenter, was trained on this dataset. This internal dataset was then randomly split into training and internal test sets. Evaluation was conducted on the internal test set and two external test sets (Abdominal Multi-Organ Segmentation Challenge 2022 [AMOS22] and Duke Liver). The predicted segmentations were compared against the radiologist-verified reference standard annotations using means ± SDs for the Dice similarity coefficient (Dice score) and normalized surface distance (NSD). The segmentation tool and dataset are publicly available at <i>https://github.com/rsummers11/MRISegmenter</i>. Results A total of 195 patients (training set, 135 patients [mean age, 54.7 years ± 16.3 {SD}; 72 male patients, 63 female patients]; internal test set, 60 patients [mean age, 51.1 years ± 14.4; 26 male patients, 34 female patients]) with 780 MRI scans containing 62 annotations each were included. On the internal test set, MRISegmenter achieved a mean Dice score of 0.861 ± 0.118 and a mean NSD of 0.924 ± 0.073. On external test sets AMOS22 (60 MRI scans) and Duke Liver (95 patients; 172 MRI scans), MRISegmenter attained a mean Dice score of 0.829 ± 0.133 and a mean NSD of 0.908 ± 0.067 and a mean Dice score of 0.933 ± 0.015 and a mean NSD of 0.929 ± 0.021, respectively. Conclusion MRISegmenter provided accurate and robust segmentation of 62 organs and structures at T1-weighted abdominal MRI. © RSNA, 2025 <i>Supplemental material is available for this article.</i> See also the editorial by Murphy in this issue.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"315 1","pages":"e241979"},"PeriodicalIF":12.1,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144018532","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":"The Updated ACR Manual on MR Safety and How It Will Affect Your Practice.","authors":"Emanuel Kanal","doi":"10.1148/radiol.242954","DOIUrl":"https://doi.org/10.1148/radiol.242954","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"315 1","pages":"e242954"},"PeriodicalIF":12.1,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143754337","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":"Angiofibroma of Soft Tissue in the Liver.","authors":"Xi Jia, Mengsu Zeng","doi":"10.1148/radiol.242524","DOIUrl":"https://doi.org/10.1148/radiol.242524","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"315 1","pages":"e242524"},"PeriodicalIF":12.1,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143804168","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":"Predicting Regional Lymph Node Metastases at CT in Microsatellite Instability-High Colon Cancer.","authors":"Zhen Guan, Zheng-Hang Wang, Xiao-Yan Zhang, Shuo Yan, Ting Xu, Jian Li, Lin Shen, Ying-Shi Sun","doi":"10.1148/radiol.242122","DOIUrl":"10.1148/radiol.242122","url":null,"abstract":"<p><p>Background Early identification of lymph node metastasis is crucial for microsatellite instability-high (MSI-H) colon cancer caused by deficient mismatch repair, but accuracy of CT is poor. Purpose To determine whether CT-detected lymph node distribution patterns can improve lymph node evaluation in MSI-H colon cancer. Materials and Methods This two-center retrospective study included patients with MSI-H colon cancer who underwent pretreatment CT and radical surgery (development set, December 2017-December 2022; test set, January 2016-January 2024). Lymph node characteristics associated with pathologic lymph node metastasis (pN+), including clinical lymph node stage (cN) and distribution patterns (vascular distribution, jammed cluster, and partial fusion), were selected (logistic regression and Kendall tau-b correlation) to create a distribution-based clinical lymph node stage (dcN) in the development set. Diagnostic performance was verified in the test set. Interobserver agreement was assessed by using Fleiss κ. Clinical value of dcN was assessed using univariable logistic analysis among patients in the treatment set receiving neoadjuvant immunotherapy (August 2017-February 2024). Results The study included 368 patients (median age, 60 years [IQR, 50-70 years]; 211 male): 230 from the development set (median age, 59 years [IQR, 49-70 years]), 86 from the test set (median age, 66 years [IQR, 55-79 years]), and 52 from the treatment set (median age, 54 years [IQR, 42-65 years]). Only jammed cluster and partial fusion were associated with higher odds of pN+ (odds ratio, 78.9 and 21.5, respectively; both <i>P</i> < .001). dcN outperformed cN in the test set (accuracy, 90% [78 of 87] vs 46% [40 of 87]; <i>P</i> < .001; specificity, 97% [55 of 57] vs 26% [15 of 57]; <i>P</i> < .001). Interobserver agreement was moderate for dcN (κ = 0.67) and poor for cN (κ = 0.48). dcN was associated with a complete response after neoadjuvant immunotherapy (odds ratio, 0.05; <i>P</i> < .001). Conclusion dcN showed high performance for identifying regional lymph node metastases and helped predict complete response after neoadjuvant immunotherapy in MSI-H colon cancer using a surgical reference standard. © RSNA, 2025 <i>Supplemental material is available for this article.</i> See also the editorial by Lev-Cohain and Sosna in this issue.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"315 1","pages":"e242122"},"PeriodicalIF":12.1,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143804177","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 Pair to Echo: AI Segmentation of CT and MRI.","authors":"Paul M Murphy","doi":"10.1148/radiol.250843","DOIUrl":"https://doi.org/10.1148/radiol.250843","url":null,"abstract":"","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"315 1","pages":"e250843"},"PeriodicalIF":12.1,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144021616","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":"RadSearch, a Semantic Search Model for Accurate Radiology Report Retrieval with Large Language Model Integration.","authors":"Cody H Savage, Gunvant Chaudhari, Andrew D Smith, Jae Ho Sohn","doi":"10.1148/radiol.240686","DOIUrl":"https://doi.org/10.1148/radiol.240686","url":null,"abstract":"<p><p>Background Current radiology report search tools are limited to keyword searches, which lack semantic understanding of underlying clinical conditions and are prone to false positives. Semantic search models address this issue, but their development requires scalable methods for generating radiology-specific training data. Purpose To develop a scalable method for training semantic search models for radiology reports and to evaluate a model, RadSearch, trained using this method. Materials and Methods In this retrospective study, a scalable method for generating training examples for semantic search was applied to CT and MRI reports generated between December 2021 and January 2022, and was used to train the model RadSearch. RadSearch performance was evaluated using four internal test sets (including one subset) and one external test set from another large tertiary medical center, including chest, abdomen, and head CT reports generated between December 2015 and June 2023. Performance was evaluated for findings-to-impression matching, retrieving reports with the same examination type, retrieving reports relevant to free-text queries, and improving the ability of a large language model (LLM) (Llama 3.1 8B Instruct) to provide accurate diagnoses from report finding descriptions. RadSearch performance was compared with that of other embedding models specialized for symmetric (All MPNet Base) and asymmetric (MS MARCO DistilBERT Base) semantic search and a state-of-the-art semantic search model (GTE-large). A reference set of 100 diagnoses with common radiologic descriptions was used for the LLM evaluation. Findings-to-impression matching and free-text query accuracy <i>P</i> values were calculated using χ² and McNemar tests. Results The training set included 16 690 reports; the internal test sets included 13 598, 6178, and 9954 reports; and the external test set included 13 958 reports. For simulated free-text clinical queries, RadSearch successfully retrieved reports containing the specified findings for 83.0% (498 of 600) of reports and matching location for 89.8% (521 of 580) of reports, outperforming GTE-large, with performance at 65.7% (394 of 600; <i>P</i> < .001) and 58.8% (341 of 580; <i>P</i> < .001), respectively. For 100 report finding descriptions, the baseline accuracy of Llama 3.1 8B Instruct in providing the correct diagnosis without any embedding model search assistance was 30% (30 of 100), improving to 61% (61 of 100) with RadSearch integration (<i>P</i> < .001), which outperformed GTE-large integration (47% [47 of 100]; <i>P</i> = .03). Conclusion A semantic search model trained with scalable methods achieved state-of-the-art performance in retrieving reports with relevant findings and improved LLM diagnostic accuracy. © RSNA, 2025 <i>Supplemental material is available for this article.</i> See also the editorial by Yasaka and Abe in this issue.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"315 1","pages":"e240686"},"PeriodicalIF":12.1,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143991774","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}