Clinical radiology最新文献

{"title":"Clinician-led artificial intelligence in imaging – The Royal College of Radiologists global AI conference 2025 and beyond","authors":"O.J. Arthurs , K. Halliday , S. Harden","doi":"10.1016/j.crad.2025.107003","DOIUrl":"10.1016/j.crad.2025.107003","url":null,"abstract":"","PeriodicalId":10695,"journal":{"name":"Clinical radiology","volume":"88 ","pages":"Article 107003"},"PeriodicalIF":2.1,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144678998","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-parameter MRI deep learning model for lymphovascular invasion assessment in invasive breast ductal carcinoma: A multicenter, retrospective study","authors":"J. Xu ,&nbsp;G. Wang ,&nbsp;Y. Wei ,&nbsp;S. Wu ,&nbsp;X. Li ,&nbsp;X. Lv ,&nbsp;L. Xia ,&nbsp;J. Zhai","doi":"10.1016/j.crad.2025.107002","DOIUrl":"10.1016/j.crad.2025.107002","url":null,"abstract":"<div><h3>Aims</h3><div>To investigate the value of multi-parametric magnetic resonance imaging (MRI)-based deep learning (DL) in predicting the Lymphovascular Invasion (LVI) status of invasive breast ductal cancer (IBDC).</div></div><div><h3>Materials and Methods</h3><div>A retrospective analysis of 448 IBDC patients from two centers was conducted, with Center 1 split into training and validation sets (8:2 ratio) and Center 2 used as the test set. A MobileNetV2-3D DL model was used to compare T1WI-CE2 and T1WI-CE3 performance, selecting the latter for fusion tasks. The combined model integrates clinical-radiological features (CRF) and multi-parameter MRI DL features to improve predictive accuracy for LVI. The predictive performance of the model was evaluated by calculating the area under the ROC curve (AUC). Calibration curves were used to evaluate the agreement between predicted outcomes and observations. Furthermore, decision curve analysis (DCA) quantified the net benefit across decision thresholds.</div></div><div><h3>Results</h3><div>The T1WI-CE3 DL model achieved AUCs of 0.842 and 0.774 on the validation and test sets, respectively, outperforming the T1WI-CE2 DL model, which had AUCs of 0.748 and 0.619. The combined model achieved a validation set AUC of 0.939 with 0.892 accuracy and a test set AUC of 0.941 with 0.872 accuracy. Calibration curves showed good prediction consistency, while DCA confirmed the combined model's clinical utility, supporting its accuracy, reliability, and potential for application.</div></div><div><h3>Conclusions</h3><div>This study offers a novel tool for preoperative LVI assessment in IBDC patients by integrating multi-parametric MRI with DL, potentially aiding clinicians in devising more precise treatment strategies.</div></div>","PeriodicalId":10695,"journal":{"name":"Clinical radiology","volume":"88 ","pages":"Article 107002"},"PeriodicalIF":2.1,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144678858","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Imaging features of Brucella-infected aneurysms: high prevalence of concurrent spondylitis and absence of ectopic gas","authors":"Z. Guo ,&nbsp;Y. Wu ,&nbsp;Z. Wang ,&nbsp;Z. Wu ,&nbsp;S. Wu ,&nbsp;R. Ma ,&nbsp;Y. Shen ,&nbsp;Y. Wang","doi":"10.1016/j.crad.2025.106999","DOIUrl":"10.1016/j.crad.2025.106999","url":null,"abstract":"<div><h3>Aim</h3><div>Arterial involvement in brucellosis is an underrecognized disease. This study aimed to identify the distinctive imaging features of Brucella-infected aneurysms (BIA).</div></div><div><h3>Materials and methods</h3><div>A retrospective cohort study was conducted at a tertiary referral hospital between January 2012 and November 2024, enrolling 26 patients with BIA (confirmed via serological examination and positive blood culture) and 22 common infected aneurysm controls without brucella. Diagnosis followed established consensus criteria. Clinical, laboratory, and computed tomography angiography (CTA) data were analyzed. Two radiologists independently assessed imaging features.</div></div><div><h3>Results</h3><div>Patients with BIA exhibited lower mean leukocyte counts [6.82 ± 1.99 standard deviation (SD) versus 13.62 ± 12.74 (SD) × 10⁹/L, <em>P</em>=0.010] and fewer positive blood cultures (15.4% versus 68.2%, <em>P</em>=0.001). CTA revealed no ectopic gas in BIA (0% versus 22.7% in controls, <em>P</em>=0.004) but a higher spondylitis prevalence (46.2% versus 18.2%, <em>P</em>=0.041). Other features, including saccular morphology, calcification (84.6% versus 77.3%), perianeurysmal findings, and infrarenal location (57.7% versus 72.7%), were comparable. A diagnostic strategy combining spondylitis and absent ectopic gas demonstrated high specificity (86.26%) and positive predictive value (80.00%) for BIA. This effect was even more pronounced when tuberculosis was excluded (specificity = 95.00%).</div></div><div><h3>Conclusion</h3><div>BIA shares key imaging features (e.g., saccular shape, perianeurysmal inflammation) with other infected aneurysms. However, the absence of ectopic gas and the high prevalence of concurrent spondylitis are distinctive for BIA. These findings support early Brucella-specific testing to guide timely antimicrobial therapy in suspected cases.</div></div>","PeriodicalId":10695,"journal":{"name":"Clinical radiology","volume":"88 ","pages":"Article 106999"},"PeriodicalIF":2.1,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144670378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Non-biopsy of fibroadenomas in the UK and Ireland: a British Society of Breast Radiology survey of national practice","authors":"S. Lowes ,&nbsp;E. Gibson ,&nbsp;T. Kulkarni ,&nbsp;J. Nash ,&nbsp;N. Sharma ,&nbsp;S. Sharma ,&nbsp;T. Suaris ,&nbsp;M. Telesca ,&nbsp;G. Lip ,&nbsp;N. Healy","doi":"10.1016/j.crad.2025.106997","DOIUrl":"10.1016/j.crad.2025.106997","url":null,"abstract":"<div><h3>Aim</h3><div>Fibroadenomas are the commonest solid breast mass in young women. Current Royal College of Radiologists' (RCR) guidance, produced by the British Society of Breast Radiology (BSBR), recommends that needle biopsy can be safely avoided in women aged under 25, provided strict imaging criteria are met, but may be increased to under 30 years with robust audit. The aim was to assess national practice against current guidance prior to its planned update.</div></div><div><h3>Materials &amp; Methods</h3><div>A BSBR survey of practice investigated non-biopsy of fibroadenomas in breast units across the UK and Ireland.</div></div><div><h3>Results</h3><div>Data were analysed from 55 breast units, with a representative geographic spread across all nations. 30/55 units (55%) currently use the ‘under 25 years’ biopsy age range; 20/55 (36 %) use ‘under 30 years’, and 5/55 (9 %) use another age range. All units using ‘under 30 years’ are happy with the cut-off; most have audited their practice, all confirming it as safe. 29 of 30 units still using ‘under 25 years’ would be prepared to move to ‘under 30’ pending definitive guidance or further evidence. Only 3 units use elastography alongside greyscale ultrasound for assessing fibroadenomas.</div></div><div><h3>Conclusion</h3><div>Findings reflect an underlying change in practice and demonstrate support for RCR guidance to extend non-biopsy of typical fibroadenomas to women under 30 years, provided strict imaging and clinical criteria are followed. Although elastography may support decision-making, it is currently not in widespread use. Units should ensure safe practice through a robust audit. Further published evidence to support safe practice post-implementation is also encouraged.</div></div>","PeriodicalId":10695,"journal":{"name":"Clinical radiology","volume":"88 ","pages":"Article 106997"},"PeriodicalIF":2.1,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144654849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predictive value of multiparametric diagnostic model based on 2-[18F]-fluoro-D-glucose (2-[18F]-FDG) positron emission tomography/computed tomography (PET/CT) metabolic parameters in differentiating between neuroblastoma and ganglioneuroblastoma","authors":"S.-Q. Li ,&nbsp;G.-Y. Wang ,&nbsp;J. Liu,&nbsp;Y. Kan,&nbsp;W. Wang,&nbsp;J.-G. Yang","doi":"10.1016/j.crad.2025.106998","DOIUrl":"10.1016/j.crad.2025.106998","url":null,"abstract":"<div><h3>Aim</h3><div>To evaluate the diagnostic performance of a multiparametric diagnostic model integrating intratumoral metabolic heterogeneity parameter and clinical parameters for differentiating neuroblastoma (NB) from ganglioneuroblastoma (GNB).</div></div><div><h3>Materials and Methods</h3><div>This retrospective study included 107 patients (64 NB and 43 GNB) who underwent 2-[¹⁸F]-fluoro-D-glucose positron emission tomography/computed tomography (2-[¹⁸F]-FDG PET/CT). Baseline characteristics, clinical data, and metabolic parameters of the primary lesions, including peak standardised uptake value, maximum standardised uptake value, mean standardised uptake value, tumour metabolic volume, total lesion glycolysis, and the area under the curve of a cumulative standardised uptake value-volume histogram (AUC-CSH) index, were collected and analysed. Diagnostic performance of the model and predictors was assessed using area under the curve of the receiver operating characteristic curve, with integrated discriminatory improvement, net reclassification improvement, Delong test for performance improvement, and decision curve analysis for clinical utility evaluation.</div></div><div><h3>Results</h3><div>Among the metabolic parameters, the AUC-CSH index demonstrated the highest diagnostic performance. Multivariate analysis identified the AUC-CSH index, age, and serum neuron-specific enolase level as independent predictors. The multiparametric model integrating these factors significantly outperformed individual metabolic parameters, and its clinical utility was validated by decision curve analysis.</div></div><div><h3>Conclusion</h3><div>A multiparametric diagnostic model integrating intratumoral metabolic heterogeneity parameter derived from 2-[¹⁸F]-FDG PET/CT with clinical parameters improves diagnostic performance for differentiating NB from GNB, offering potential for clinical application.</div></div>","PeriodicalId":10695,"journal":{"name":"Clinical radiology","volume":"88 ","pages":"Article 106998"},"PeriodicalIF":2.1,"publicationDate":"2025-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144695355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computed tomography (CT)-based classification and management pathways for hybrid lesions in children: a comparative analysis of congenital pulmonary airway malformation (CPAM) and bronchopulmonary sequestration (BPS)","authors":"C. Zhou ,&nbsp;D. He ,&nbsp;J. Li ,&nbsp;Q. He ,&nbsp;J. Tian ,&nbsp;H. Wu","doi":"10.1016/j.crad.2025.106996","DOIUrl":"10.1016/j.crad.2025.106996","url":null,"abstract":"<div><h3>AIM</h3><div>To establish a CT-based classification system for hybrid lesions in children, elucidate misdiagnosis mechanisms, and propose optimized clinical management pathways through comparative analysis with isolated CPAM and BPS.</div></div><div><h3>MATERIALS AND Methods</h3><div>This retrospective study analyzed 393 children with surgically confirmed congenital lesions (87 hybrids, 218 CPAMs, 88 BPS) from two centers (2010-2022). Hybrid lesions were classified preoperatively: Type A: cystic lesion + systemic arterial supply; Type B: solid lesion + systemic arterial supply; Type C: solid lesion - systemic arterial supply. Comparative analysis of clinical and imaging features was performed.</div></div><div><h3>Results</h3><div>Type A(51 cases, 58.6%): Predominantly Type 2 CPAMs (cyst diameter &lt;2.85 cm, AUC = 0.963) with intralobar BPS (88.2%). Prenatal detection rate: 70.6% (36/51); symptomatic rate: 37.3% (19/51). Type B (33 cases, 37.9%): Solid lesions with extralobar BPS (78.8%). Prenatal detection rate: 84.8% (28/33); symptomatic rate: 24.2% (8/33). Type C (3 cases, 3.4%): 100% misdiagnosis due to absent systemic arterial supply. Hybrid lesions demonstrated significantly higher prenatal detection rates than isolated CPAMs and BPS (75.9% vs. 51.4% vs. 56.8%, P&lt;0.001) but lower symptomatic rates (31.0% vs. 62.4% vs. 48.9%, P&lt;0.001). Radiologically, hybrid lesions predominantly involved the left lower lobe (66.7% vs. 28.0% in CPAMs, P&lt;0.001).</div></div><div><h3>Conclusions</h3><div>CT demonstrated 54.1% diagnostic accuracy for hybrid lesions. The proposed A/B/C classification clarifies misdiagnosis mechanisms, with left lower lobe predominance (66.7%) and systemic arterial supply (95.4%) as hallmark features. Microcystic Type 2 CPAMs (&lt;2.85 cm) and extralobar BPS anatomical isolation synergistically reduce complication risks, providing an imaging-guided framework for risk-stratified management.</div></div>","PeriodicalId":10695,"journal":{"name":"Clinical radiology","volume":"88 ","pages":"Article 106996"},"PeriodicalIF":2.1,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144633917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Local trainee assessment: insights from a UK national survey of radiology training programme directors","authors":"A. Sawer ,&nbsp;T.J. Sadler ,&nbsp;P. Set ,&nbsp;P. Riede","doi":"10.1016/j.crad.2025.106995","DOIUrl":"10.1016/j.crad.2025.106995","url":null,"abstract":"<div><h3>Aim</h3><div>Clinical radiology training in the UK follows the competency-based model of medical education, which holds trainee assessment as a core component in providing evidence of progress and the capability to work independently upon completion. The training curriculum published by the Royal College of Radiologists defines a set of competencies and a framework of assessment for these purposes. Nonetheless, it is postulated that many training schemes also employ additional locally-administered assessments of their trainees, which are not described in the training curriculum. This study aims to explore the extent, purpose, and validation of such assessments within UK radiology training programmes.</div></div><div><h3>Materials &amp; methods</h3><div>An electronic survey was distributed to clinical radiology training programme directors and heads of schools, using multiple choice and free-text questions. Responses were analysed qualitatively.</div></div><div><h3>Results</h3><div>29 responses were received, representing 17 out of 20 Local Training and Education Boards. 88% reported employing local assessments, with 53 individual assessments described overall. These primarily involved trainees in the initial years of training (ST1-2), aimed at authorising independent reporting (68%). The majority were found to be summative in nature, with performance affecting progression, on-call eligibility and often requiring resitting. Formal evaluation or audit processes for these assessments were absent in 40% of training schemes.</div></div><div><h3>Conclusion</h3><div>Despite their prevalence and perceived value amongst trainers, the absence of robust evaluation and published evidence raises questions as to their validity and fairness. The study highlights the need for further investigation and guidance for their implementation locally in radiology training schemes.</div></div>","PeriodicalId":10695,"journal":{"name":"Clinical radiology","volume":"88 ","pages":"Article 106995"},"PeriodicalIF":2.1,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144633918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pictorial review of the use of percutaneous mechanical thromboaspiration in peripheral vascular occlusions","authors":"H. Sabey-Corkindale ,&nbsp;M. Finzel ,&nbsp;R. Miles ,&nbsp;N. Gafoor ,&nbsp;M. Vasquez-Rios ,&nbsp;M. Macanovic ,&nbsp;S. Ghauri ,&nbsp;P. Jenkins","doi":"10.1016/j.crad.2025.106994","DOIUrl":"10.1016/j.crad.2025.106994","url":null,"abstract":"","PeriodicalId":10695,"journal":{"name":"Clinical radiology","volume":"88 ","pages":"Article 106994"},"PeriodicalIF":2.1,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144695354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Empowering Radiology: Why Failing to Teach AI Could Cost the Specialty Its Leadership","authors":"James Baker","doi":"10.1016/j.crad.2025.106992","DOIUrl":"10.1016/j.crad.2025.106992","url":null,"abstract":"","PeriodicalId":10695,"journal":{"name":"Clinical radiology","volume":"88 ","pages":"Article 106992"},"PeriodicalIF":2.1,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144579367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"RCR Meetings","authors":"","doi":"10.1016/S0009-9260(25)00187-4","DOIUrl":"10.1016/S0009-9260(25)00187-4","url":null,"abstract":"","PeriodicalId":10695,"journal":{"name":"Clinical radiology","volume":"86 ","pages":"Article 106982"},"PeriodicalIF":2.1,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144306635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}