Pediatric Radiology最新文献

{"title":"Diffuse sclerosing papillary thyroid carcinoma in a child.","authors":"A Yigitcan Tacyıldız, H Nursun Ozcan","doi":"10.1007/s00247-026-06691-2","DOIUrl":"10.1007/s00247-026-06691-2","url":null,"abstract":"","PeriodicalId":19755,"journal":{"name":"Pediatric Radiology","volume":" ","pages":"2612"},"PeriodicalIF":2.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13669039/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148252639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Widely available, general-purpose generative AI applications for radiology education: determining the teaching quality of synthetic pediatric neuroradiology images.","authors":"Thomas P Reith, Donna M D'Alessandro, Krishnakumari A Modi, Mohammed Sabawi, Catherina S Zadeh, Mikhael G Sebaaly, Lillian M Lai, Takashi Shawn P Sato, Simon C Kao, Yutaka Sato, Michael P D'Alessandro","doi":"10.1007/s00247-026-06708-w","DOIUrl":"10.1007/s00247-026-06708-w","url":null,"abstract":"<p><strong>Background: </strong>Artificial intelligence (AI) is increasingly incorporated into medical education. Widely available, general-purpose generative AI applications are increasingly capable of producing high-fidelity synthetic medical images, which may have potential educational uses.</p><p><strong>Objective: </strong>To assess the ability of widely available, general-purpose generative AI applications to produce synthetic pediatric neuroradiology images of teaching quality.</p><p><strong>Materials and methods: </strong>Ten significant diagnostic errors in pediatric neuroradiologic emergencies were identified and divided into 22 individual clinical scenarios. Two widely available, general-purpose generative AI applications, GPT-5 (OpenAI, San Francisco, CA) and Gemini 3 Pro with the Nano Banana Pro image-generation engine (Google, Mountain View, CA), were prompted to generate five separate images for each scenario, yielding a total of 220 images. Eight fellowship-trained pediatric radiologists independently assessed each image for teaching quality. Ratings were recorded and analyzed. Differences between applications were evaluated using Fisher's exact test.</p><p><strong>Results: </strong>Overall, 8.6% of generated images (19/220) were deemed suitable for teaching by more than half of the pediatric radiologists. GPT-5 produced a higher proportion of acceptable images meeting this >50% criterion compared to Gemini 3 Pro (12.7% [14/110] vs. 4.5% [5/110]; P=0.031).</p><p><strong>Conclusion: </strong>At present, widely available, general-purpose generative AI applications should not be used to produce synthetic radiological images for educational purposes. Inaccuracies and inconsistencies limit reliability and may actively impair learning.</p>","PeriodicalId":19755,"journal":{"name":"Pediatric Radiology","volume":" ","pages":"2564-2572"},"PeriodicalIF":2.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13669131/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148391376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pediatric SARS-CoV-2 long term outcomes study: chest radiographic and computed tomography findings at baseline.","authors":"Jonathan Zember, Evrim B Turkbey, Eric Chu, Allyson Mateja, C Jason Liang, Karyl Barron, Gina A Montealegre Sanchez, Roberta L DeBiasi, Meagan E Williams, Dorothy I Bulas","doi":"10.1007/s00247-026-06701-3","DOIUrl":"10.1007/s00247-026-06701-3","url":null,"abstract":"<p><strong>Background: </strong>Radiologic findings associated with SARS-CoV-2 infection have been well described since its emergence. However, long-term clinical and radiologic complications of pediatric SARS-CoV-2 infection are less defined, including radiologic findings in children following recovery.</p><p><strong>Objective: </strong>This study compares chest radiographic (CXR) and low-dose chest computed tomography (CT) findings in pediatric participants; a longitudinal cohort of children who have recovered from SARS-CoV-2 infection and uninfected controls.</p><p><strong>Materials and methods: </strong>Eight hundred forty-six children (700 laboratory confirmed SARS-CoV-2-infected children and 146 uninfected controls) completed a radiologic exam at the baseline visit, which occurred 9.8 months (mean) post-infection. CXR (n=485) and CT (n=362) images were evaluated by three radiologists for known radiologic manifestations of COVID-19 including various patterns of opacities (ground glass, reticular, consolidation), nodules, perihilar thickening, effusions, and/or cystic changes. Comparisons were made using generalized estimating equations with cohort (infected vs. uninfected) as the predictor.</p><p><strong>Results: </strong>Overall, the incidence of radiologic abnormalities detected at baseline was 32.1% in the infected cohort and 24.0% in the uninfected cohorts. Infected participants were more likely to have CXR abnormalities than uninfected (21.2% vs. 12.4%; OR 2.44; 95% CI 1.19-5.02; P=0.016). This was primarily due to an increased incidence of perihilar peribronchial thickening (17.4% in infected vs. 10.1% in noninfected). There were no statistically significant differences between cohorts for CT abnormalities (46.2% vs. 42.1%; OR 1.24; 95% CI 0.71-2.16; P=0.46). Radiologic abnormalities were not statistically significantly associated with presence of pulmonary symptoms after recovery.</p><p><strong>Conclusions: </strong>At the baseline visit, infected participants were more likely than uninfected controls to have chest radiographic abnormalities, limited to perihilar peribronchial thickening. There was no significant difference in CT abnormalities between the two cohorts. There was no increased frequency of radiographic findings in children with underlying asthma, nor in children who experienced pulmonary symptoms following recovery at the baseline visit.</p>","PeriodicalId":19755,"journal":{"name":"Pediatric Radiology","volume":" ","pages":"2459-2467"},"PeriodicalIF":2.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148318317","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":"A reliable measurement is not the same as a reliable diagnosis: reply to Peter et al.","authors":"Hasan Nawaz Tahir, Mohammad Idrees, Umema Tariq, Muhammad Zuhair Yusuf, Yousaf Ali","doi":"10.1007/s00247-026-06752-6","DOIUrl":"10.1007/s00247-026-06752-6","url":null,"abstract":"","PeriodicalId":19755,"journal":{"name":"Pediatric Radiology","volume":" ","pages":"2581-2583"},"PeriodicalIF":2.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148796427","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":"Prediction of early recurrence in primary intussusception: development of an ultrasound-based radiomics and deep learning nomogram.","authors":"Rongying Tan, Jinwei Zhou, Shaomei Wang, Xi Zhang, Yanlin Mou, Djibril Adam Mahamat, Qinming Chen, Daiyue Yu, Yi Lu, Jianjun Wang, Kai Wu","doi":"10.1007/s00247-026-06696-x","DOIUrl":"10.1007/s00247-026-06696-x","url":null,"abstract":"<p><strong>Background: </strong>Early recurrence of intussusception frequently occurs within 48 h after reduction, yet current assessments lack objective tools for accurate risk prediction.</p><p><strong>Objective: </strong>This multicenter study sought to develop and validate a predictive model for early intussusception recurrence using abdominal ultrasound imaging.</p><p><strong>Materials and methods: </strong>We retrospectively collected data from 1,314 primary pediatric intussusception cases across three hospitals (2016-2024). Cases from center 1 were split into training (60%) and internal validation (40%) sets, and those from centers 2 and 3 composed the external test sets. An automated segmentation model (DeepLabv3 with ResNet101) was developed for lesion delineation. Radiomics and deep learning features were extracted from the segmented regions. Three classifiers (K-nearest neighbors, random forest, and extreme gradient boosting) were evaluated on the radiomics, deep learning, and fused feature sets. We integrated the fused model with clinical variables to construct a nomogram.</p><p><strong>Results: </strong>The Dice coefficients of the segmentation model were 0.935 (seg-training) and 0.862 (seg-test). The key clinical predictors were age, onset-to-presentation time, and vomiting. After seven radiomics features and nine deep learning features were selected, we integrated the fused model with clinical variables to construct a nomogram. It showed good discrimination (internal validation area under the receiver operating characteristic curve (AUC), 0.892; external test set AUCs, 0.884 and 0.851, respectively). The results of the calibration and decision curve analyses supported its potential as a risk stratification tool.</p><p><strong>Conclusion: </strong>Integrating ultrasound-derived deep learning, radiomics, and clinical data shows promise for predicting recurrence of primary intussusception within 48 h. The model may aid early risk stratification, although prospective validation in diverse populations is needed.</p>","PeriodicalId":19755,"journal":{"name":"Pediatric Radiology","volume":" ","pages":"2498-2510"},"PeriodicalIF":2.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148339507","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":"Reply to Keceli M.","authors":"Paulina Vargova, Beatriz Izquierdo-Hernandez, Cristina Gutierrez-Alonso, Diasol Villa-Viñas, Carolina Corona-Bellostas","doi":"10.1007/s00247-026-06658-3","DOIUrl":"10.1007/s00247-026-06658-3","url":null,"abstract":"","PeriodicalId":19755,"journal":{"name":"Pediatric Radiology","volume":" ","pages":"2606-2607"},"PeriodicalIF":2.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147983048","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":"The radiographic bubbly fecal pattern of intestinal pneumatosis in newborns revisited.","authors":"Magdalena Sophie Schmidt, Ina Bettzieche, Michael Zellner, Christian J Kellenberger, Irmhild Altmann-Schneider","doi":"10.1007/s00247-026-06703-1","DOIUrl":"10.1007/s00247-026-06703-1","url":null,"abstract":"<p><strong>Background: </strong>A bubbly fecal pattern on abdominal radiographs of neonates was described in the 1980s as a potential sign of intestinal pneumatosis, particularly in preterm infants during the first 2 weeks of life. This sign has not been systematically re-evaluated or correlated with sonographic findings.</p><p><strong>Objective: </strong>To assess whether, and up to which age, a radiographic bubbly fecal pattern represents intestinal pneumatosis, using bowel ultrasound as the reference standard.</p><p><strong>Materials and methods: </strong>Infants aged 0-97 days who underwent abdominal radiography and bowel ultrasound for suspected ischemic enterocolitis in the neonatal intensive care unit were retrospectively included between January 2012 and December 2023. Radiography and ultrasound had to be performed within 24 h of each other. Imaging findings were analyzed per patient and per imaging episode.</p><p><strong>Results: </strong>A total of 191 infants (82 female) were included, resulting in 402 paired examinations. Median age at imaging was 18 days. A bubbly fecal pattern was identified on 212 radiographs in 119 infants, with sonographic intestinal pneumatosis present in 172 cases (81.1%). Positive predictive values were consistently high, reaching 80.7% overall, while specificity and negative predictive values remained low across all age groups. A negative ultrasound in the presence of a bubbly fecal pattern was associated with a low surgical rate (6.5%). Sonographic pneumatosis was present in 90% of infants who underwent surgery.</p><p><strong>Conclusion: </strong>In infants evaluated for suspected necrotizing/ischemic enterocolitis, a radiographic bubbly fecal pattern is a relevant imaging sign associated with intestinal pneumatosis, particularly during the first 8 weeks of life.</p>","PeriodicalId":19755,"journal":{"name":"Pediatric Radiology","volume":" ","pages":"2511-2519"},"PeriodicalIF":2.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148361922","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":"Thermal ablation of lung metastases in children: what every paediatric radiologist should know.","authors":"Giulia Cassanelli, Frederic Deschamps, Fernando Gomez Munoz, Simon P McGuirk","doi":"10.1007/s00247-026-06700-4","DOIUrl":"10.1007/s00247-026-06700-4","url":null,"abstract":"<p><p>Thermal ablation is increasingly used as a lung-sparing local treatment for selected children with pulmonary metastases, and diagnostic paediatric radiologists play a central role in lesion detection, procedural planning support, and post-treatment interpretation. This review focuses on the imaging appearance of pulmonary metastases before, during, and after percutaneous thermal ablation, highlighting the practical findings that every diagnostic radiologist should recognise. Pre-procedural imaging assessment is discussed with emphasis on lesion size, location, morphology, proximity to pleura, vessels and bronchi, and features that may affect feasibility, safety, and expected ablation margins. Intra-procedural imaging appearances are reviewed across the main techniques, including expected peri-lesional ground-glass change during heat-based ablation and ice-ball formation during cryoablation, with attention to imaging endpoints that suggest adequate target coverage and to findings that may indicate incomplete treatment or early complications. Post-ablation evolution is summarised from immediate computed tomography (CT) to short- and long-term follow-up, including expected changes in ablation zone size, density and contour, and the temporal patterns that help distinguish normal post-treatment appearances from residual viable tumour or local recurrence. Common interpretative pitfalls-such as inflammatory change, haemorrhage, atelectatic/parenchymal distortion, and pleural reaction-are addressed, together with practical reporting recommendations to improve communication within the multidisciplinary oncology team. By providing an imaging-centred framework, this article aims to support more confident and consistent interpretation of ablated lung lesions in children.</p>","PeriodicalId":19755,"journal":{"name":"Pediatric Radiology","volume":" ","pages":"2376-2388"},"PeriodicalIF":2.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148353021","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":"Death by neurologic criteria: a nuclear medicine approach based on the 2023 AAN/AAP/CNS/SCCM Guideline and 2025 SNMMI Procedure Standard.","authors":"Murat Alp Oztek, Marguerite T Parisi","doi":"10.1007/s00247-026-06742-8","DOIUrl":"10.1007/s00247-026-06742-8","url":null,"abstract":"<p><p>Death by neurologic criteria, previously called brain death, is a medicolegal concept, fraught with legal, ethical, and emotional considerations. The diagnosis is established clinically as described in the appropriate interdisciplinary guidelines. When adequate clinical evaluation cannot be performed, imaging including radionuclide brain perfusion scintigraphy (RBPS), four-vessel catheter angiography, or transcranial Doppler can be used as ancillary tests. Of these, RBPS is the more commonly performed test, used to establish the presence or absence of intracranial perfusion. Scintigraphic imaging for the presence or absence of intracranial perfusion is infrequently requested, which limits familiarity with both performing and interpreting these studies. The purpose of this article is to help the radiologist and nuclear medicine physician better understand the concept of death by neurologic criteria and the role of scintigraphic imaging in supporting the clinical diagnosis in the light of most recent multidisciplinary guidelines. A second goal is to describe how to interpret and report the relevant imaging studies, emphasizing differences between children and adults where applicable.</p>","PeriodicalId":19755,"journal":{"name":"Pediatric Radiology","volume":" ","pages":"2345-2359"},"PeriodicalIF":2.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148664246","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":"Reply to Sridharan K et al.","authors":"Ceren Altintas Mese, Ismail Mese, Tugba Akinci D'Antonoli","doi":"10.1007/s00247-026-06740-w","DOIUrl":"10.1007/s00247-026-06740-w","url":null,"abstract":"","PeriodicalId":19755,"journal":{"name":"Pediatric Radiology","volume":" ","pages":"2489-2490"},"PeriodicalIF":2.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148592848","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}