Mihaela Rata, Nina Tunariu, Yun Jiang, Julie Hughes, Georgina Hopkinson, Erica Scurr, Jessica M Winfield, Vikas Gulani, Dow-Mu Koh, Matthew R Orton
{"title":"Serial T<sub>1</sub> and T<sub>2</sub> measurements of metastatic bone lesions in prostate cancer patients: MR fingerprinting vs conventional MRI.","authors":"Mihaela Rata, Nina Tunariu, Yun Jiang, Julie Hughes, Georgina Hopkinson, Erica Scurr, Jessica M Winfield, Vikas Gulani, Dow-Mu Koh, Matthew R Orton","doi":"10.1007/s00330-025-12071-5","DOIUrl":"https://doi.org/10.1007/s00330-025-12071-5","url":null,"abstract":"<p><strong>Objectives: </strong>This study evaluated serial magnetic resonance fingerprinting (MRF)-derived T<sub>1</sub> and T<sub>2</sub> relaxivities of prostate bone metastasis compared with conventional T<sub>1</sub> and T<sub>2</sub> measurements.</p><p><strong>Materials and methods: </strong>This prospective study (July 2020 to July 2022) included MRF and conventional MRI acquisitions (T<sub>1</sub>: inversion-recovery turbo spin echo; T<sub>2</sub>: dual spin echo) from participants with bone metastasis from primary prostate cancer from two cohorts: pre-treatment (N = 34) and pre/post-treatment (N = 19). Phantom/human data were acquired on a 1.5-T scanner using an MRF sequence outputting T<sub>1</sub> and T<sub>2</sub> maps. Regions of interest (ROIs) of bone metastasis were drawn per visit on both MRF and conventional MRI. Inter-method reproducibility of T<sub>1</sub> and T<sub>2</sub> was assessed using Bland-Altman plots, reproducibility, intraclass correlation, and Spearman correlation coefficients. A delta parameter [post-treatment - pre-treatment] of method-specific T<sub>1</sub> and T<sub>2</sub> was reported.</p><p><strong>Results: </strong>Thirty-four patients with metastatic prostate cancer (mean age, 68 years ± 7 [standard deviation]) were evaluated pre-treatment; 19 participants were further scanned post-treatment. MRF-derived mean T<sub>1</sub> and T<sub>2</sub> in bone metastasis were slightly higher than the conventional MR measurements: 10.8% (T<sub>1</sub>) and 15.5% (T<sub>2</sub>). The reproducibility coefficient (r%) was 19.3% for T<sub>1</sub> and 32.5% for T<sub>2</sub>, whilst the Spearman correlation coefficient was strong for both parameters (0.66, p < 0.001 and 0.70, p < 0.001). The MRF-derived delta T<sub>1</sub> parameter was moderately correlated to the inversion-recovery method (0.59, p = 0.008), whilst the MRF-derived delta T<sub>2</sub> was very strongly correlated to the dual spin echo method (0.80, p < 0.001).</p><p><strong>Conclusion: </strong>A good correlation of MRF-derived T<sub>1</sub> and T<sub>2</sub> measurements with conventional quantitative methods was demonstrated in bone metastasis.</p><p><strong>Key points: </strong>Question MR fingerprinting (MRF)-derived T<sub>1</sub> and T<sub>2</sub> values have the potential to characterise bone metastasis and treatment response, but their performance against conventional MRI is unclear. Findings The inter-method reproducibility coefficient was 19.3% for T<sub>1</sub> and 32.5% for T<sub>2</sub>, whilst the Spearman correlation coefficient was strong for both parameters. Clinical relevance Serial MRF-derived T<sub>1</sub> and T<sub>2</sub> measurements in bone metastasis in patients with prostate cancer correlated well with conventional MRI measurements, supporting MRF use for faster quantitative measurements in bone lesions.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145354136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Reply to the Letter to the Editor: Neonatal laryngeal and tracheal ultrasound-normative data or measurement variability.","authors":"Łukasz Paprocki, Bartosz Migda, Renata Bokiniec","doi":"10.1007/s00330-025-12074-2","DOIUrl":"https://doi.org/10.1007/s00330-025-12074-2","url":null,"abstract":"","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145343928","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ahmed Marey, Ona Ambrozaite, Ahmed Afifi, Ritu Agarwal, Rama Chellappa, Sola Adeleke, Muhammad Umair
{"title":"A perspective on AI implementation in medical imaging in LMICs: challenges, priorities, and strategies.","authors":"Ahmed Marey, Ona Ambrozaite, Ahmed Afifi, Ritu Agarwal, Rama Chellappa, Sola Adeleke, Muhammad Umair","doi":"10.1007/s00330-025-12031-z","DOIUrl":"https://doi.org/10.1007/s00330-025-12031-z","url":null,"abstract":"<p><strong>Objectives: </strong>Artificial intelligence (AI) promises to accelerate and democratize medical imaging, yet low- and middle-income countries (LMICs) face distinct barriers to adoption. This perspective identifies those barriers and proposes an action-oriented roadmap.</p><p><strong>Materials and methods: </strong>Insights were synthesized from a Johns Hopkins Science Diplomacy Hub workshop (18 experts in radiology, AI, and health policy) and a scoping review of peer-reviewed and grey literature. Workshop discussions were transcribed, thematically coded, and iteratively validated to reach consensus.</p><p><strong>Results: </strong>Five interlocking barriers were prioritized: (1) infrastructure gaps-scarce imaging devices, unstable power, and limited bandwidth; (2) data deficiencies-small, non-representative, or ethically constrained datasets; (3) workforce shortages and brain drain; (4) uncertain ethical, regulatory, and medicolegal frameworks; and (5) financing and sustainability constraints. Case studies from Nigeria, Uganda, and Colombia showed that low-field MRI, cloud-based PACS, community-engaged data collection, and public-private partnerships can successfully mitigate several of these challenges.</p><p><strong>Conclusions: </strong>Targeted policy levers-including shared procurement of low-cost hardware, regional AI and data hubs, train-the-trainer workforce programs, and harmonized regulation-can enable LMIC health systems to deploy AI imaging responsibly, shorten diagnostic delays, and improve patient outcomes. Lessons are transferable to resource-constrained settings worldwide.</p><p><strong>Key points: </strong>Question How can LMICs overcome infrastructure, data, workforce, regulatory, and financing barriers to implement artificial-intelligence tools in clinical medical imaging? Findings Our multinational consensus identifies five obstacles and maps each to actionable levers: low-cost hardware, regional data hubs, train-the-trainer schemes, harmonized regulation, blended financing. Clinical relevance Implementing these targeted measures enables LMIC health systems to deploy AI imaging reliably, shorten diagnostic delays, and improve patient outcomes while reducing dependence on external expertise.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145344355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Julien Ognard, Aysha Alateya, Gerard El Hajj, Annouk Bisdorff, Lambros Tselikas, Ahmed Ayad, Tor Lindell, Zain Alateya, Sherief Ghozy, Ramanathan Kadirvel, David F Kallmes, Waleed Brinjikji
{"title":"Simply the (B)EST: what the interventionalist needs to know about (bleomycin) electrosclerotherapy for vascular anomalies.","authors":"Julien Ognard, Aysha Alateya, Gerard El Hajj, Annouk Bisdorff, Lambros Tselikas, Ahmed Ayad, Tor Lindell, Zain Alateya, Sherief Ghozy, Ramanathan Kadirvel, David F Kallmes, Waleed Brinjikji","doi":"10.1007/s00330-025-12077-z","DOIUrl":"https://doi.org/10.1007/s00330-025-12077-z","url":null,"abstract":"<p><strong>Background: </strong>Vascular anomalies (VAs) require specialized multidisciplinary management. Bleomycin electrosclerotherapy (B)EST combines electroporation with intralesional bleomycin to enhance drug uptake while preserving surrounding tissue. Its role in treating VAs remains largely unexplored.</p><p><strong>Objective: </strong>This systematic review evaluates the efficacy, safety, and procedural protocols of BEST in VA treatment.</p><p><strong>Materials and methods: </strong>Following PRISMA guidelines, a systematic search was conducted in PubMed, Web of Science, and Scopus. Inclusion criteria included peer-reviewed studies on (B)EST for VAs, excluding reviews, editorials, and animal studies.</p><p><strong>Results: </strong>Among 1237 records, 15 studies met the inclusion criteria, published between 2012 and 2025, primarily from Europe (13/15). A total of 566 patients were treated, including 445 with vascular malformations and 121 with vascular tumors (Kaposi sarcoma, angiosarcoma). (B)EST was mainly applied to slow-flow malformations. Across VA types, lesion-volume or symptom reduction rate was high, with five studies each reporting a 100% rate. Complete response in vascular tumors ranged from 65 to 100%. Most studies followed current guidelines, with bleomycin doses between 200 and 10,000 IU per session. Adverse effects were primarily local and self-limiting (Cardiovascular and Interventional Radiological Society of Europe classification CIRSE 1a-2); ulcerations occurred mainly in vascular tumors (CIRSE 3a); and skin hyperpigmentation (CIRSE 1a) was observed frequently, often partially resolving over time.</p><p><strong>Conclusion: </strong>BEST shows promise for VA treatment, particularly venous and lymphatic malformations. While results suggest efficacy and safety, treatment heterogeneity and long-term outcomes require further investigation. Optimizing tailored protocols for each VA subtype and presentation is essential for defining (B)EST's role in VA management.</p><p><strong>Key points: </strong>Question What is the role and efficacy of (bleomycin) electrosclerotherapy (B)EST in managing vascular anomalies resistant to conventional treatments, including tumors and malformations? Findings (B)EST demonstrated significant efficacy, achieving 65-100% complete responses in vascular tumors and 54.9-100% lesion or symptom reduction in vascular malformations. Clinical relevance (B)EST offers an option for patients with treatment-resistant or recurrent vascular anomalies, improving symptom-related outcomes. This is tempered by the absence of controlled trials, the need for cumulative dose pulmonary monitoring and the potential cosmetic burden of hyperpigmentation.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145343881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Letter to the Editor: Neonatal laryngeal and tracheal ultrasound: normative data or measurement variability.","authors":"Enes Gurun, Mesut Ozturk, Ismail Akdulum","doi":"10.1007/s00330-025-12073-3","DOIUrl":"https://doi.org/10.1007/s00330-025-12073-3","url":null,"abstract":"","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145343938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zi-Ang Li, Yu Gao, Kai Ji, Kai-Yue Zhang, Qiang Zhang, Jie Wang, Lin Han, Xiao-Yang Zhai, Wen-Peng Wang, Wen-Ling Liu, Han-Yu Wei, Rui-Jing Qin, Yong-Dong Li, Hong-Ling Zhao, Rui-Fang Yan, Hong-Kai Cui
{"title":"AI-driven diagnosis of vulnerable intracranial atherosclerotic plaques using large language models and vision transformers: a multi-center study.","authors":"Zi-Ang Li, Yu Gao, Kai Ji, Kai-Yue Zhang, Qiang Zhang, Jie Wang, Lin Han, Xiao-Yang Zhai, Wen-Peng Wang, Wen-Ling Liu, Han-Yu Wei, Rui-Jing Qin, Yong-Dong Li, Hong-Ling Zhao, Rui-Fang Yan, Hong-Kai Cui","doi":"10.1007/s00330-025-12065-3","DOIUrl":"https://doi.org/10.1007/s00330-025-12065-3","url":null,"abstract":"<p><strong>Objectives: </strong>High-resolution vessel wall imaging (HR-VWI) is essential for diagnosing vulnerable intracranial atherosclerotic plaques, but its interpretation requires expertise. This study investigates the integration of large language models (LLMs) and deep learning (DL) for more efficient diagnosis.</p><p><strong>Materials and methods: </strong>A retrospective study of symptomatic intracranial atherosclerotic stenosis patients (June 2018-June 2024) was conducted. LLMs (ChatGPT-4o, DeepSeek-V3, and Moonshot AI) were trained on HR-VWI reports to extract diagnostic insights. Additionally, DL models, ResNet50 and Vision Transformer (ViT), were used to classify vulnerable plaques. Diagnostic accuracy, sensitivity, specificity, and time efficiency were evaluated with both junior and senior doctors.</p><p><strong>Results: </strong>A total of 1806 plaques from 726 patients were analyzed. ChatGPT-4o exhibited the highest diagnostic performance (AUC: 0.874). Among DL models, ViT outperformed ResNet50 (AUC: 0.913 vs. 0.845). LLMs and ViT significantly improved junior doctors' diagnostic accuracy and reduced plaque assessment time (from 301 s to 174 s, p < 0.05).</p><p><strong>Conclusion: </strong>The integration of LLMs and DL models enhanced diagnostic performance and efficiency, especially for junior doctors. This approach could reduce the burden on healthcare systems, particularly in resource-limited settings, by improving diagnostic accuracy and reducing the time required for plaque analysis.</p><p><strong>Key points: </strong>Question How can AI models assist less experienced doctors in accurately identifying vulnerable intracranial plaques on high-resolution vessel wall imaging (HR-VWI) and improve diagnostic efficiency? Findings The integration of large language models (LLMs) and deep learning (ViT) significantly improves diagnostic accuracy and efficiency, reducing assessment time for vulnerable plaques. Clinical relevance This study demonstrates that combining LLMs and deep learning enables junior doctors to achieve near-expert accuracy in diagnosing vulnerable plaques, potentially reducing stroke risk and easing diagnostic burdens in resource-limited healthcare environments.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145344416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jelle Barentsz, Sebastianus Wilheimus van Koeverden, Marloes van der Leest
{"title":"VI-RADS is not enough: why image quality is the key to reliable bladder cancer staging.","authors":"Jelle Barentsz, Sebastianus Wilheimus van Koeverden, Marloes van der Leest","doi":"10.1007/s00330-025-12086-y","DOIUrl":"https://doi.org/10.1007/s00330-025-12086-y","url":null,"abstract":"","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145344248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Towards destigmatization of mucin in the era of TNT for locally advanced rectal cancer.","authors":"Sofia Gourtsoyianni","doi":"10.1007/s00330-025-12063-5","DOIUrl":"https://doi.org/10.1007/s00330-025-12063-5","url":null,"abstract":"","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145344274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The CT-based attenuation index of peri-bowel adipose tissue can predict disease progression in inflammatory bowel disease patients.","authors":"Jun Lu, Hui Xu, Jingxuan Zhang, Tianxin Cheng, Jing Zheng, Xinjun Han, Yuxin Wang, Xuxu Meng, Xiaoyang Li, Jiahui Jiang, Xue Dong, Zhenchang Wang, Zhenghan Yang, Lixue Xu","doi":"10.1007/s00330-025-12079-x","DOIUrl":"https://doi.org/10.1007/s00330-025-12079-x","url":null,"abstract":"<p><strong>Objectives: </strong>Peri-bowel fat inflammation is a prominent feature of inflammatory bowel disease (IBD). The peri-bowel fat attenuation index (FAI) can capture fat inflammation on abdominal CT. This study aimed to investigate the prognostic value of the peri-bowel FAI in IBD patients.</p><p><strong>Materials and methods: </strong>Totally, 207 IBD patients were retrospectively collected. Regions of interest were placed at 5 different locations, namely, mesenteric side (MS) and opposite side of MS (OMS) around the most severe bowel lesion, spaces around the normal bowel wall (Nor), retroperitoneal space (RS), and subcutaneous area. The Kaplan-Meier curves were plotted. The prognostic value of the peri-bowel FAI was evaluated by multivariable Cox regression models.</p><p><strong>Results: </strong>High peri-bowel FAI values of MS and OMS were predictors of disease progression and correlated strongly with each other (r = 0.840, p < 0.001), while the FAI of Nor and RS were not. Therefore, peri-bowel FAI of MS was used as a representative biomarker for the prediction of IBD disease progression (HR = 1.161 [1.110-1.215], p < 0.001) with an optimum cutoff of 25.1 HU, which was confirmed in the subgroup analysis with different disease subtypes. With the addition of the peri-bowel FAI to the current noninvasive risk prediction model, the AUC increased from 0.706 (0.638-0.767) to 0.864 (0.810-0.90) with integrated discrimination improvement (IDI = 0.293 [0.229-0.356], p < 0.001) and net reclassification improvement (NRI = 1.053 [0.821-1.284], p < 0.001).</p><p><strong>Conclusion: </strong>The peri-bowel FAI is promising for IBD disease progression prediction and risk stratification by quantifying peri-bowel fat inflammation. High peri-bowel FAI values are an independent indicator of increased IBD disease progression and could guide early targeted prevention and intensive therapy.</p><p><strong>Key points: </strong>Questions The peri-bowel fat attenuation index (FAI) helps detect peri-bowel fat inflammation noninvasively, but its importance for risk stratification and prediction of clinical outcomes remains unknown. Findings The peri-bowel FAI was an independent predictor of inflammatory bowel disease (IBD) disease progression with an optimum cutoff of 25.1 HU. Clinical relevance The peri-bowel FAI is a promising biomarker for contributing to the identification of so-called high-risk patients with uncontrolled inflammation, who might be candidates for more intensive treatment for addressing underlying inflammation at early stages and ultimately improve long-term prognosis.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145344268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}