Frontiers in radiology最新文献

{"title":"Incidence, risk factors, and outcomes of contrast-associated acute kidney injury following interventional radiology procedures: a systematic review and meta-analysis.","authors":"Saad Alhumaid, Mohammed Yousef Almulhim, Hessah Abdulaziz Al Hussaini, Qasem M Alalwan, Hani Almohammed Ali, Sarah A Al Ruzaihan, Fatima A Aborshaid, Abdulrhman Khaled Al Abdulqader, Nourah Al Dossary, Muneera Alabdulqader, Shaden Saleh AlMousa, Khalid Suliman Aljoqiman","doi":"10.3389/fradi.2026.1947256","DOIUrl":"10.3389/fradi.2026.1947256","url":null,"abstract":"<p><strong>Background: </strong>Contrast-associated acute kidney injury (CA-AKI) is a recognized complication of iodinated contrast administration. Although extensively studied in coronary angiography, its incidence, associated factors, and outcomes following interventional radiology and other non-coronary endovascular procedures remain incompletely characterized. We evaluated the incidence, associated factors, and outcomes of CA-AKI in these populations.</p><p><strong>Methods: </strong>This systematic review followed PRISMA 2020 guidelines and a prospectively registered PROSPERO protocol (CRD420261385592). PubMed/MEDLINE, Embase, Scopus, CINAHL, and Web of Science were searched from inception to 30 April 2026. Eligible studies evaluated CA-AKI following catheter-based non-coronary endovascular or interventional radiology procedures. Random-effects meta-analysis estimated pooled incidence, with subgroup and sensitivity analyses.</p><p><strong>Results: </strong>Thirty-nine studies were included, of which 38 contributed to the meta-analysis. The pooled CA-AKI incidence was 6.91% (95% CI 5.69-8.24; I² = 89.5%). In a sensitivity analysis restricted to patient-level estimates (30 studies; 16,825 unique patients), incidence was 7.27% (95% CI 5.77-8.92; I² = 91.5%). Leave-one-out estimates ranged from 6.56% to 7.16%, indicating numerical stability despite substantial heterogeneity. Exploratory subgroup analysis showed higher pooled incidence following embolization/interventional oncology than neuroendovascular/carotid procedures (8.44% vs. 5.48%; <i>p</i> = 0.0171), although substantial residual heterogeneity renders this finding hypothesis-generating. Frequently reported associated factors included baseline renal dysfunction, advanced liver disease, diabetes mellitus, anaemia, hypoalbuminaemia, inflammatory burden, and greater contrast exposure. Heterogeneous observational evidence did not establish a clinically reliable contrast-volume threshold. Across individual studies, CA-AKI was associated with increased mortality, poorer functional outcomes, prolonged hospitalisation, and persistent renal dysfunction, although associations were not consistent across all studies and outcomes.</p><p><strong>Conclusion: </strong>CA-AKI occurs after a range of non-coronary endovascular and interventional radiology procedures and may be associated with clinically important adverse outcomes. Substantial heterogeneity limits the generalizability of a single pooled incidence estimate, and procedure- and population-specific estimates should remain central to interpretation. Standardised definitions and prospective multicentre studies are needed to establish procedure-specific risk profiles and clinically useful preventive strategies.</p><p><strong>Systematic review registration: </strong>https://www.crd.york.ac.uk/PROSPERO/view/CRD420261385592, PROSPERO, CRD420261385592.</p>","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1947256"},"PeriodicalIF":4.0,"publicationDate":"2026-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13642721/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149139167","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":"Editorial: Advances in neuroradiology: emerging diagnostic and therapeutic innovations.","authors":"Corrado Ini', Silvia Gigli, Abhishek Mahajan, Lorenzo Aliotta, Emanuele David","doi":"10.3389/fradi.2026.1984316","DOIUrl":"https://doi.org/10.3389/fradi.2026.1984316","url":null,"abstract":"","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1984316"},"PeriodicalIF":4.0,"publicationDate":"2026-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13638578/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119360","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":"The application of deep neural networks to the detection of lumbar hernias: results from the approaches based on convolutional networks and transformers.","authors":"António Fernandes, João Pedro Mazuco Rodriguez, Susana Moleirinho, Irina Trofimenko, Ekaterina Guseva, Alexander Martinovich, Ilzane Maria de Oliveira Morais, Louise Bisolo, Luís Mendes Gomes, José Machado","doi":"10.3389/fradi.2026.1722312","DOIUrl":"https://doi.org/10.3389/fradi.2026.1722312","url":null,"abstract":"<p><strong>Background: </strong>The increasing demand for lumbar spine MRI exams, combined with radiologist shortages, has underscored the need for automated tools to assist in diagnosing degenerative spinal conditions. Despite the proliferation of AI tools in radiology, no CE or FDA-approved applications currently focus on pathologies in the lumbar spine. This study aimed to develop a pipeline for automatic identification of intervertebral disc herniation, contributing to more efficient clinical decision-making.</p><p><strong>Methods: </strong>A dataset of 484 lumbar spine MRI examinations acquired from four manufacturers was used to develop a multi-stage deep learning pipeline. An overview of the proposed automated lumbar spine MRI analysis framework is presented, illustrating the main stages of the pipeline including dataset preparation, disc segmentation, feature extraction, and classification. A subset of 165 studies (5,200 sagittal slices) was manually annotated by radiologists and used for training and validation of vertebrae and intervertebral disc segmentation models, including U-Net, DeepLabV3+, and MA-Net with EfficientNet-B2 backbones. Anatomically informed post-processing was applied to assign disc-level labels and extract disc-centered volumes. Disc-level binary classification (herniated vs. non-herniated) was then performed using 3D patch-based models, including ResNet, SENet, EfficientNet-B2, and Vision Transformer (ViT) architectures, with all dataset splits performed at the patient level.</p><p><strong>Results: </strong>The best segmentation performance was achieved by MA-Net with EfficientNet-B2, yielding a Dice Score of 0.898 for three-class segmentation (background, vertebrae, discs). For classification, the evaluated models achieved F1-scores between 0.66 and 0.73. The best performance was obtained with a ResNet18-based model, indicating that once anatomical localization and disc extraction are addressed by the segmentation stage, lower-capacity architectures can be effective for binary classification. The simplified three-class segmentation improved model robustness, and post-processing enabled disc-level precision essential for downstream classification, which achieved consistent performance across models under the available data regime.</p><p><strong>Conclusion: </strong>The proposed AI pipeline successfully automates the identification of lumbar disc herniation in MRI exams. This approach has the potential to enhance diagnostic efficiency, reduce radiologist workload, and improve reproducibility in identifying disc pathologies. While limited by sample size and class imbalance, the methodology lays a strong foundation for scalable annotation and integration of AI in routine spinal diagnostics.</p>","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1722312"},"PeriodicalIF":4.0,"publicationDate":"2026-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13632042/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119349","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":"Editorial: Precision neuroimaging for MRgFUS in neurological disorders.","authors":"Federico Bruno, Sotirios Bisdas","doi":"10.3389/fradi.2026.1979646","DOIUrl":"https://doi.org/10.3389/fradi.2026.1979646","url":null,"abstract":"","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1979646"},"PeriodicalIF":4.0,"publicationDate":"2026-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13621381/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149082849","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":"Preparedness of CT technicians and radiographers for severe contrast media reactions: knowledge gaps and training needs.","authors":"Haneen E Abuanzeh, Ayman M Al-Qaaneh","doi":"10.3389/fradi.2026.1940155","DOIUrl":"10.3389/fradi.2026.1940155","url":null,"abstract":"<p><strong>Background: </strong>Severe contrast media reactions during computed tomography (CT) are rare but potentially life-threatening and require rapid recognition and coordinated emergency response. CT technicians and radiographers are often frontline professionals during contrast-enhanced CT, yet their preparedness in Jordan remains underexplored.</p><p><strong>Objective: </strong>To assess knowledge of severe contrast media reactions among CT technicians and radiographers in Jordan and identify factors associated with total knowledge scores.</p><p><strong>Methods: </strong>A descriptive cross-sectional study was conducted using an online questionnaire adapted from a previously published tool. The questionnaire assessed five domains: general knowledge of contrast media, risk factors, precautions, recognition of severe reactions, and management. Scores were converted to percentages. Data were analyzed using descriptive statistics, Mann-Whitney U tests, Kruskal-Wallis tests, Spearman correlation, and multivariable linear regression.</p><p><strong>Results: </strong>The analysis included 314 participants. The median total knowledge score was 76.3% (IQR: 55.3-84.2). General knowledge showed the highest median score (100%, IQR: 80-100), whereas risk factor knowledge was the lowest-performing domain (65%, IQR: 50-80). Radiographers achieved higher total knowledge scores than technicians (78.9% vs. 71.0%, <i>p</i> = 0.002). Total knowledge also differed significantly across educational levels (<i>p</i> = 0.043). In multivariable regression, total knowledge was independently associated with gender, age group, master's-level education, professional role, experience >25 years, and self-reported confidence.</p><p><strong>Conclusion: </strong>CT technicians and radiographers in Jordan demonstrated moderate-to-high overall knowledge of severe contrast media reactions, but important gaps were evident, particularly in risk factor recognition. Structured, recurrent, competency-based training programs focusing on risk assessment, reaction recognition, emergency management, and simulation-based practice are needed to strengthen preparedness and patient safety during contrast-enhanced CT.</p>","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1940155"},"PeriodicalIF":4.0,"publicationDate":"2026-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13601256/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149042187","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":"Diagnostic imaging and emerging image-guided neurointervention in brain tumors: a narrative review.","authors":"Zahin Alam, Triston Messer, Anirudh Maddali, Jake Heath, Kush Desai, Srihari Sundararajan, David Monoky, Brij Reddy","doi":"10.3389/fradi.2026.1914188","DOIUrl":"10.3389/fradi.2026.1914188","url":null,"abstract":"<p><p>Brain tumors are heterogeneous neoplasms requiring multidisciplinary management and precise diagnostic and therapeutic strategies. Diagnostic radiology plays a central role in tumor detection, characterization, treatment planning, and surveillance through advanced imaging modalities such as multiparametric magnetic resonance imaging, perfusion imaging, diffusion techniques, spectroscopy, and molecular imaging. Concurrently, image-guided procedures performed across endovascular neurointerventional and neurosurgical workflows, including embolization, laser interstitial thermal therapy, intra-arterial chemotherapy, convection-enhanced delivery, and blood-brain barrier modulation, are expanding minimally invasive options in selected patients. This review synthesizes current and emerging diagnostic radiology and image-guided approaches across major brain tumor types, including glioblastoma, low-grade glioma, metastases, primary central nervous system lymphoma, and meningioma. Furthermore, this review highlights the growing overlap among diagnostic radiology, interventional radiology, and neurosurgical workflows, emphasizes the increasingly central role of imaging in guiding therapy, and identifies the need in which coordinated multidisciplinary workflows should be prospectively evaluated as diagnostic and therapeutic technologies continue to converge. Lastly, this review distinguishes established clinical tools from selectively used and investigational approaches by summarizing evidence level, patient-selection considerations, and barriers to routine implementation.</p>","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1914188"},"PeriodicalIF":4.0,"publicationDate":"2026-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13594585/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149026734","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":"A wide-detector CT protocol for one-stop cardio-cerebrovascular angiography: a technical feasibility study comparing an integrated protocol with conventional two-scan approach.","authors":"Jie Yan, Feiyan Wang, Shuixian Huang, Yunhui Chen, Yan Long, Bing Ge, Xiao He","doi":"10.3389/fradi.2026.1887780","DOIUrl":"10.3389/fradi.2026.1887780","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;To evaluate the clinical utility of a wide-detector CT protocol with variable helical pitch (vHP) for one-stop cardiovascular and cerebrovascular CT angiography.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This prospective randomized study enrolled 61 patients (25 in the Group A and 36 in the Group B) with suspected cardiovascular and cerebrovascular diseases. Group A underwent the integrated one-stop CTA protocol (which incorporates vHP technology), whereas Group B underwent conventional separate scans (coronary CTA and head-neck CTA). Both groups used automated bolus-tracking triggering. Comparisons included effective scanning time, total operating time, contrast medium volume, radiation dose (dose-length product, DLP), and subjective and objective image quality. Normality was assessed using the Shapiro-Wilk test; continuous variables were compared using independent samples t-test or Mann-Whitney U test as appropriate. The false discovery rate method was applied to correct for multiple comparisons, and analysis of covariance was performed to adjust for potential confounders.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The integrated protocol group (Group A) demonstrated significantly higher contrast-to-noise ratio (CNR) in the coronary arteries and major aortic branches(all FDR-corrected &lt;i&gt;P&lt;/i&gt; &lt; 0.001). In the neck region, Group A showed significantly higher SNR in the common carotid arteries (FDR-corrected &lt;i&gt;P&lt;/i&gt; &lt; 0.001 for RCCA and &lt;i&gt;P&lt;/i&gt; = 0.0044 for LCCA), whereas Group B demonstrated better CNR in the right internal carotid artery (FDR-corrected &lt;i&gt;P&lt;/i&gt; &lt; 0.001) and lower image noise in several vessels (FDR-corrected &lt;i&gt;P&lt;/i&gt; &lt; 0.05 for RICA SD and LVA SD). Notably, ANCOVA models for SNR exhibited poor fit with adjusted R&lt;sup&gt;2&lt;/sup&gt; values frequently near zero or negative, warranting cautious interpretation; the primary evidence for protocol-related image quality improvement is therefore based on the robust CNR findings. ANCOVA confirmed that these intergroup differences remained significant after adjustment (all adjusted &lt;i&gt;P&lt;/i&gt; &lt; 0.05 for key CNR/SNR comparisons), indicating protocol-related rather than baseline-driven advantages. Subjective image quality was excellent in both groups (median 4, IQR 4-4), with no significant intergroup differences. DLP was higher in Group A (909.00 vs. 694.50 mGy·cm, &lt;i&gt;P&lt;/i&gt; &lt; 0.001), but effective scanning time was significantly shorter (8.00 vs. 19.00 s, 57.9% reduction, &lt;i&gt;P&lt;/i&gt; &lt; 0.001), and total operating time was markedly reduced (480.00 vs. 1020.00 s, 52.9% reduction, &lt;i&gt;P&lt;/i&gt; &lt; 0.001). Contrast medium volume was halved in Group A (50-60 vs. 100-120 mL).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusion: &lt;/strong&gt;The integrated wide-detector CT protocol evaluated in this study (which incorporates variable helical pitch as a key enabling component) is technically feasible and offers workflow advantages over conventional scanning, including shorter scan time, reduced contrast volume, and maintained image ","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1887780"},"PeriodicalIF":4.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13575675/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148978850","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":"Use of artificial intelligence in education and training of radiology.","authors":"María Belén Morales-Cevallos, Canva Byron Ma Lam, María José López Pino, Adriana Monserrath Monge Moreno, Diego Fabián Vique López","doi":"10.3389/fradi.2026.1899739","DOIUrl":"10.3389/fradi.2026.1899739","url":null,"abstract":"<p><strong>Motivation: </strong>Artificial intelligence (AI) is reshaping radiology through advances in machine learning, deep learning, and generative AI. As these technologies become embedded in diagnostic workflows, radiology education must adapt to prepare learners for AI-enabled clinical practice. This review aimed to synthesize current evidence, identify educational priorities, and highlight challenges and opportunities for implementation.</p><p><strong>Introduction: </strong>The growing adoption of AI in medical imaging requires radiology curricula to extend beyond image interpretation and encompass AI literacy, ethical reasoning, critical appraisal, and human-AI collaboration. Understanding how AI is currently incorporated into radiology education is essential for developing effective training frameworks. This review examined educational approaches, learner outcomes, and implementation challenges associated with AI in radiology education.</p><p><strong>Methodology: </strong>A scoping review was conducted and reported in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR), using the Population-Concept-Context(PCC) framework to define the review question and eligibility criteria. Searches were performed in Scopus, PubMed, and IEEE Xplore for studies published between 2020 and 2025. After screening and eligibility assessment, 29 original studies were included. Educational outcomes were classified into skill development, engagement, and performance domains.</p><p><strong>Results and discussion: </strong>Skill development was the most frequently investigated outcome (55.2%), followed by performance (27.6%) and engagement (17.2%). Approximately 86% of studies reported positive or improved educational outcomes. AI-based interventions enhanced learner confidence, AI literacy, diagnostic reasoning, and readiness for clinical implementation. Generative AI tools showed promise for tutoring, assessment, and self-directed learning but raised concerns regarding reliability, hallucinations, bias, and ethical use. Common barriers included limited faculty expertise, insufficient formal training, curricular overcrowding, inadequate infrastructure, and governance challenges.</p><p><strong>Conclusion: </strong>AI has significant potential to strengthen radiology education through personalized learning, competency development, and technology-enhanced training. Nevertheless, sustainable implementation requires standardized curricula, faculty development, competency frameworks, and robust ethical oversight. Future research should focus on longitudinal outcomes and evidence-based educational models that prepare radiology professionals for increasingly AI-integrated healthcare systems.</p>","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1899739"},"PeriodicalIF":4.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13574975/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148978866","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":"Slice-level vs. volumetric radiomics for molecular subtyping of breast cancer: impact of patient-level data partitioning on model performance.","authors":"Laila El Jiani, Zouheir Banou, Fatima Zahra Alaoui, Hasnae Sakhi, El Habib Benlahmar, Sanaa El Filali","doi":"10.3389/fradi.2026.1915426","DOIUrl":"10.3389/fradi.2026.1915426","url":null,"abstract":"<p><strong>Introduction: </strong>Molecular subtyping of breast cancer, particularly the discrimination between Luminal A and Basal-like tumours, is critical for guiding treatment decisions and establishing prognosis. Radiomics offers a promising complementary, non-invasive imaging biomarker to support biopsy-based subtyping; however, two methodological gaps limit the validity of existing studies: the absence of controlled 2D-vs.-3D feature comparisons, and the systematic underreporting of patient-level data leakage in multi-slice pipelines.</p><p><strong>Methods: </strong>To address both limitations, this study benchmarks slice-level (2D) and volumetric (3D) radiomic pipelines for the classification of Luminal A vs. Basal-like tumours on the TCGA-BRCA cohort, evaluating seven classifiers combined with two feature selection strategies under a Stratified Group <i>k</i>-Fold (<i>k</i> = 5) cross-validation scheme that enforces strict patient-level isolation.</p><p><strong>Results: </strong>The 3D pipeline achieved a mean AUC of 0.682 vs. 0.631 for the 2D pipeline. In the 3D configuration, the Support Vector Machine with SelectKBest-MI feature selection attained the highest performance (AUC = 0.768 ± 0.066), while the 2D configuration was led by Logistic Regression (AUC = 0.769 ± 0.109), albeit with substantially higher fold-to-fold variability. Six out of seven classifiers yielded higher AUC scores under the 3D configuration, although a paired significance test on fold-level AUC values did not reach statistical significance (<i>p</i> = 0.313).</p><p><strong>Discussion: </strong>These results establish a reproducible, leakage-free baseline for non-invasive breast cancer subtype classification through radiomics, with 3D radiomics offering improved robustness rather than superior peak performance. Results are derived from a single cohort (TCGA-BRCA) and external validation is required before clinical generalizability can be claimed.</p>","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1915426"},"PeriodicalIF":4.0,"publicationDate":"2026-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13572697/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148972578","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":"Systematic review of PET imaging features and clinical applications in pulmonary NUT carcinoma.","authors":"Xue Liu, Li Bin, Yu Zhang, Huiting Liu, Cailiang Gao","doi":"10.3389/fradi.2026.1933175","DOIUrl":"10.3389/fradi.2026.1933175","url":null,"abstract":"<p><strong>Purpose: </strong>Primary pulmonary nuclear protein in testis (NUT) carcinoma is a rare, aggressive malignancy driven by <i>NUTM1</i> rearrangement. Although ¹⁸F-FDG PET/CT is used in clinical management, its imaging features and value have not been systematically evaluated.</p><p><strong>Methods: </strong>This PRISMA 2020 systematic review was registered with PROSPERO (CRD420261292692). PubMed, Embase, Web of Science, Cochrane Library, and grey literature were searched from inception to March 2026. Studies reporting ¹⁸F-FDG PET/CT findings in pathologically confirmed primary pulmonary NUT carcinoma were included. A structured qualitative synthesis was performed.</p><p><strong>Results: </strong>Twenty-three studies (86 patients) were included. Tumours consistently showed marked hypermetabolism (SUVmax 5-40; mean, 12-14) with frequent central necrosis. A proposed imaging triad was identified: (1) bulky central mass with necrosis; (2) ipsilateral coalescent mediastinal/hilar lymphadenopathy; and (3) extensive ipsilateral pleural involvement. The contralateral lung remained relatively spared and brain metastases were rare at initial diagnosis. PET/CT led to M-stage reclassification in 55% of patients through occult metastasis detection, was superior to bone scintigraphy for osteolytic lesions, and revealed initial treatment response followed by rapid progression on serial monitoring.</p><p><strong>Conclusions: </strong>Primary pulmonary NUT carcinoma demonstrates a characteristic hypermetabolic phenotype with a proposed imaging triad on ¹⁸F-FDG PET/CT. PET/CT is crucial for staging modification, metastasis detection, and treatment response monitoring. Recognition of this profile may facilitate earlier diagnosis and clinical management.</p><p><strong>Systematic review registration: </strong>https://www.crd.york.ac.uk/PROSPERO/view/CRD420261292692, identifier CRD420261292692.</p>","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":"6 ","pages":"1933175"},"PeriodicalIF":4.0,"publicationDate":"2026-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13562259/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148957435","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}