European Journal of Radiology最新文献

{"title":"Comparison of clinical, radiomics, deep learning, and fusion models for predicting early recurrence in locally advanced rectal cancer based on multiparametric MRI: a multicenter study","authors":"Zhiheng Li ,&nbsp;Yangyang Qin ,&nbsp;Xiaoqing Liao ,&nbsp;Enqi Wang ,&nbsp;Rongzhi Cai ,&nbsp;Yuning Pan ,&nbsp;Dandan Wang ,&nbsp;Yan Lin","doi":"10.1016/j.ejrad.2025.112173","DOIUrl":"10.1016/j.ejrad.2025.112173","url":null,"abstract":"<div><h3>Objective</h3><div>Predicting early recurrence (ER) in locally advanced rectal cancer (LARC) is critical for clinical decision-making. This study aimed at comparing clinical, deep learning (DL), radiomics, and two fusion models for ER prediction based on multiparametric MRI.</div></div><div><h3>Methods</h3><div>This retrospective study involved 337 LARC patients from four centers between January 2016 and September 2021. Radiomics and DL features were extracted from preoperative multiparametric MRI, including T2WI, DWI, T1WI, and contrast-enhanced T1WI (CET1WI). The extreme gradient boosting (XGBoost) classifier was applied to establish the clinical model, radiomics model, DL model, and two fusion models (the feature-based early fusion model and the decision-based late fusion model). The area under the curve (AUC), DeLong test, calibration curve, and decision curve analysis (DCA) were used to assess models. Kaplan-Meier analysis was conducted to determine the prognostic value of the models by evaluating the differences in recurrence-free survival (RFS) between the high- and low-risk patients of ER.</div></div><div><h3>Results</h3><div>The late fusion model demonstrated the best performance compared with the early fusion model, clinical, radiomics and DL models, with the highest AUC (0.863–0.880) across all cohorts. In addition, the late fusion model exhibited the highest clinical net benefit, and good calibration. Kaplan-Meier survival curves showed that high-risk patients of ER defined by the late fusion model had a worse RFS than low-risk ones of ER (log-rank <em>p</em> &lt; 0.001).</div></div><div><h3>Conclusions</h3><div>The late fusion model can accurately predict ER in LARC and may serve as a clinically useful, non-invasive tool for optimizing treatment strategies and monitoring disease progression.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"189 ","pages":"Article 112173"},"PeriodicalIF":3.2,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144098914","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 anaesthesia and pain management in image-guided breast interventions: Empathy in action","authors":"Rodrigo Alcantara ,&nbsp;E.Natalia Arenas ,&nbsp;Javier Azcona ,&nbsp;Mireia Pitarch ,&nbsp;Elisenda Vall ,&nbsp;Elisabet Vila-Trias ,&nbsp;Belen Ejarque ,&nbsp;José Maria Maiques ,&nbsp;Antonio Montes","doi":"10.1016/j.ejrad.2025.112176","DOIUrl":"10.1016/j.ejrad.2025.112176","url":null,"abstract":"<div><div>Effective pain management is critical in image-guided breast interventions, directly contributing to patient comfort and procedural success. This review provides breast radiologists with actionable insights into pain mechanisms, the optimisation of local anaesthetic delivery, and practical supplementary methods to minimise injection discomfort. Evidence-based techniques, including buffering, warming of solutions, and the addition of vasoconstrictors, are explored. Pharmacological properties, safety considerations, and innovative approaches, including patient-centred care and anxiety management strategies, are also discussed. Together, these considerations form a comprehensive framework to advance practices and elevate the standard of care in breast interventions.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"189 ","pages":"Article 112176"},"PeriodicalIF":3.2,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144134646","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":"Abdominal vascular compression syndromes: A pictorial review","authors":"Daniel L. Cardoso ,&nbsp;Beatriz A. de Macedo ,&nbsp;Roddie M. Neto ,&nbsp;Maria Tereza L. Cardoso ,&nbsp;Larissa Marciano ,&nbsp;Lucas de Pádua Gomes de Farias ,&nbsp;José A.B. Araújo Filho ,&nbsp;Giovanni G. Cerri ,&nbsp;Rodrigo L. Azambuja ,&nbsp;Thiago D.R. Vieira","doi":"10.1016/j.ejrad.2025.112169","DOIUrl":"10.1016/j.ejrad.2025.112169","url":null,"abstract":"<div><div>Abdominal vascular compression syndromes (AVCS) refer to the entrapment of blood vessels between surfaces in a restricted space, a phenomenon that may cause clinical manifestations and can be identified using imaging methods. Although uncommon, their hemodynamic repercussions may lead to potential morbidity and should therefore be recognized by radiologists, who play a crucial role in diagnosing these conditions. Contrast-enhanced computed tomography (CECT) is the imaging modality of choice, primarily valued for its precision in identifying anatomical abnormalities, thereby facilitating appropriate management and reducing the risk of subsequent complications. Follow-up may range from conservative to invasive approaches, including surgical and endovascular procedures. This pictorial review focuses on the main imaging patterns of AVCS. Our objective is to enhance radiologists’ ability to discern abdominal vascular anatomy, its interrelations with neighboring structures and its variants, and assist in the analysis of potential etiologies and pathophysiological mechanisms associated with these anomalies.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"189 ","pages":"Article 112169"},"PeriodicalIF":3.2,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144083990","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":"Deep-learning based automated pancreas segmentation on CT scans of chronic pancreatitis patients","authors":"Surenth Nalliah ,&nbsp;Esben Bolvig Mark ,&nbsp;Marjolein Henrieke Liedenbaum ,&nbsp;Mille Kristence Lillien Mosegaard ,&nbsp;Tobias Hellström ,&nbsp;Erlend Hodneland ,&nbsp;Ingfrid Helene Salvesen Haldorsen ,&nbsp;Trond Engjom ,&nbsp;Asbjørn Mohr Drewes ,&nbsp;Søren Schou Olesen ,&nbsp;Jens Brøndum Frøkjær","doi":"10.1016/j.ejrad.2025.112175","DOIUrl":"10.1016/j.ejrad.2025.112175","url":null,"abstract":"<div><h3>Objectives</h3><div>This study aimed to develop an artificial intelligence (AI)-based segmentation model for accurate delineation of the complex pancreas in patients with chronic pancreatitis (CP) using computer tomography (CT) scans obtained during routine clinical work-up. Validation was performed with internal and external test datasets. A secondary objective was to evaluate the impact of visceral fat area (at the third lumbar level), pancreas volume, and CT parameters on model performance.</div></div><div><h3>Methods</h3><div>This multicenter study included 550 retrospectively collected CT scans from Aalborg (n = 373; 224 CP, 150 healthy subjects) and Bergen Hospitals (n = 97 CP), and an online dataset from the National Institutes of Health (NIH) (n = 80, healthy subjects). The Aalborg dataset was divided into a training cohort (n = 326) and an internal test set (n = 47), while the Bergen and NIH datasets served as external test sets. The AI model employed the nnU-Net architecture, with performance evaluated using the Sørensen-Dice index. Correlations with visceral fat, pancreas volume, and CT parameters were assessed.</div></div><div><h3>Results</h3><div>The pancreas segmentation AI model achieved a Dice score of 0.85 ± 0.08 on the Aalborg test set, 0.79 ± 0.19 on the Bergen dataset, and 0.79 ± 0.18 on the NIH dataset. Visceral fat and pancreas volume positively correlated with Dice scores (r = 0.45 and r = 0.53, both <em>p</em> &lt; 0.0001), while CT parameters had no significant impact (all <em>p</em>-values &gt; 0.07).</div></div><div><h3>Conclusion</h3><div>The AI model demonstrated high accuracy and robustness in pancreas segmentation of both CP patients and healthy subjects, and across diverse sites and scanners, suggesting its potential for clinical application.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"189 ","pages":"Article 112175"},"PeriodicalIF":3.2,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144105712","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":"Diagnosis of thyroid cartilage invasion by laryngeal and hypopharyngeal cancers based on CT with deep learning","authors":"Yuki Takano ,&nbsp;Noriyuki Fujima ,&nbsp;Junichi Nakagawa ,&nbsp;Hiroki Dobashi ,&nbsp;Yukie Shimizu ,&nbsp;Motoma Kanaya ,&nbsp;Satoshi Kano ,&nbsp;Akihiro Homma ,&nbsp;Kohsuke Kudo","doi":"10.1016/j.ejrad.2025.112168","DOIUrl":"10.1016/j.ejrad.2025.112168","url":null,"abstract":"<div><h3>Objectives</h3><div>To develop a convolutional neural network (CNN) model to diagnose thyroid cartilage invasion by laryngeal and hypopharyngeal cancers observed on computed tomography (CT) images and evaluate the model’s diagnostic performance.</div></div><div><h3>Methods</h3><div>We retrospectively analyzed 91 cases of laryngeal or hypopharyngeal cancer treated surgically at our hospital during the period April 2010 through May 2023, and we divided the cases into datasets for training (n = 61) and testing (n = 30). We reviewed the CT images and pathological diagnoses in all cases to determine the invasion positive- or negative-status as a ground truth. We trained the new CNN model to classify thyroid cartilage invasion-positive or −negative status from the pre-treatment axial CT images by transfer learning from Residual Network 101 (ResNet101), using the training dataset. We then used the test dataset to evaluate the model’s performance. Two radiologists, one with extensive head and neck imaging experience (senior reader) and the other with less experience (junior reader) reviewed the CT images of the test dataset to determine whether thyroid cartilage invasion was present.</div></div><div><h3>Results</h3><div>The following were obtained by the CNN model with the test dataset: area under the curve (AUC), 0.82; 90 % accuracy, 80 % sensitivity, and 95 % specificity. The CNN model showed a significant difference in AUCs compared to the junior reader (p = 0.035) but not the senior reader (p = 0.61).</div></div><div><h3>Conclusions</h3><div>The CNN-based diagnostic model can be a useful supportive tool for the assessment of thyroid cartilage invasion in patients with laryngeal or hypopharyngeal cancer.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"189 ","pages":"Article 112168"},"PeriodicalIF":3.2,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144069065","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":"Thoracic perforators (IMAP, LICAP, DICAP) for P-to-P and perforator flaps − analysis of localization and anatomy using computed tomography angiography","authors":"Jonas Brandt ,&nbsp;Matthias Aitzetmüller-Klietz ,&nbsp;Walter Heindel ,&nbsp;Maximilian Kückelhaus ,&nbsp;Tobias Hirsch ,&nbsp;Max Masthoff ,&nbsp;Sascha Wellenbrock","doi":"10.1016/j.ejrad.2025.112162","DOIUrl":"10.1016/j.ejrad.2025.112162","url":null,"abstract":"<div><h3>Background</h3><div>Perforator-to-perforator (P-to-P) free flaps and local to regional perforator flaps are increasingly important in thoracic reconstructive surgery. However, limited anatomical and imaging data on internal mammary (IMAPs), lateral (LICAPs), and dorsal intercostal artery perforators (DICAPs) hinder presurgical planning and clinical use. This study aimed to evaluate the feasibility of computed tomography angiography (CTA) for thoracic perforator mapping.</div></div><div><h3>Materials and Methods</h3><div>Non-ECG triggered CTAs of the thoracoabdominal aorta of patients with suspected aortal pathology were retrospectively reviewed. After applying exclusion criteria (aortal pathology, major hardening artifacts, aortal stent prothesis, anasarca or other thoracic wall pathology), absolute count, localization and diameter of thoracic perforators were analyzed for 150 patients (age: 67.3 ± 15.11, m = 99, f = 51) using integrated imaging software.</div></div><div><h3>Results</h3><div>Using CTA, IMAPs were detected in 99 % of patients, with a mean count of 3.35 ± 1.30 per patient, typically located in the 3.35 ± 1.30 intercostal space (ICS) and having a mean diameter of 1.41 ± 0.35 mm. LICAPs were present in 91 % of patients, averaging 3.46 ± 1.93 per patient, found in the 9.83 ± 1.41 ICS with a mean diameter of 1.26 ± 0.30 mm. DICAPs were identified in 87 % of patients, with an average of 2.71 ± 1.64 per patient, typically located in the 7.49 ± 2.27 ICS and having a mean diameter of 1.25 ± 0.31 mm.</div></div><div><h3>Conclusions</h3><div>CTA is capable of non-invasive <em>in vivo</em> anatomical mapping of IMAPs, LICAPs and DICAPs and thus has the potential to guide state-of-the-art plastic surgery.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"189 ","pages":"Article 112162"},"PeriodicalIF":3.2,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144069066","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":"Brain pulsation demonstrated by CSF flow artifacts on FLAIR images might be associated with brain function","authors":"Toshio Imaizumi,&nbsp;Kengo Suzuki,&nbsp;Kyoya Sakashita,&nbsp;Riku Ohwada,&nbsp;Shoichi Komura,&nbsp;Tomoaki Tamada","doi":"10.1016/j.ejrad.2025.112164","DOIUrl":"10.1016/j.ejrad.2025.112164","url":null,"abstract":"<div><div>The glymphatic system works to excrete waste products from the brain. If it breaks down, cognitive impairment can occur. The system is mainly driven by arterial and brain pulsation. Brain pulsation is recognized as cerebrospinal fluid (CSF) flow artifacts on fluid-attenuated inversion recovery (FLAIR) imaging. We investigated the factors associated with human brain pulsation.</div><div>CSF flow artifact grade (score) was defined by comparing the highest intensity in a given region of interest (ROI) to those in reference ROIs of normal white matter in the centrum semiovale on FLAIR imaging. CSF flow scores for eight sites (lateral, third and fourth ventricles, aqueduct, and prepontine cisterns) were measured and summed for a total score (range, 0–16). The prevalence of each finding, specifically risk factors and neuroradiological findings, was compared using multivariate logistic regression models.</div><div>We evaluated the findings in 1,000 adults (62.8 ± 9.5 years, 569 females) with no history of neurological disorders. Mean CSF flow score was 12.8 ± 1.6. Stepwise and multivariate analyses demonstrated that the score ≤11 as a dependent factor was positively associated with 100–7 test result ≤3, and frontal polar-cranium distance ≥2 mm, and negatively associated with female gender.</div><div>In addition to frontal atrophy and female gender, the reduction of brain pulsation was associated with brain function during simple calculations as frontal lobe function. Brain pulsation might drive the glymphatic system, and reduction of the pulsation might disturb brain function.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"189 ","pages":"Article 112164"},"PeriodicalIF":3.2,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144069067","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":"Effects and safety of the transradial artery approach for cerebral angiography: A comparative observational study","authors":"Jinchao Xia ,&nbsp;Shuxin Xiao ,&nbsp;Gangqin Xv ,&nbsp;Tianxiao Li ,&nbsp;Ziliang Wang","doi":"10.1016/j.ejrad.2025.112165","DOIUrl":"10.1016/j.ejrad.2025.112165","url":null,"abstract":"<div><h3>Background</h3><div>Conventionally,the transfemoral artery approach has been the primary approach for neurointervention. However, this approach has been associated with perioperative complications. Thus, the purpose of this study was to evaluate the safety and feasibility of the transradial artery approach in cerebral angiography.</div></div><div><h3>Methods</h3><div>This study collected 2504 patients who received cerebral angiography at our center from November 2017 to June 2021. There were 1105 patients in the transradial artery group and 1399 patients in the transfemoral artery group.</div></div><div><h3>Results</h3><div>There were 1088 successful cases in the transradial artery group and 1386 cases in the transfemoral artery group. However, there was no significant difference in the success rate and intraoperative radiographic exposure time between the two groups (P &gt; 0.05). The length of hospital stay and perioperative complications were significantly less in the transradial artery group than in the transfemoral artery group (P &lt; 0.05). The logistic regression analysis for risk factors shows that age (OR = 1.891, 95 % CI 0.057–3.382, P = 0.032) and hypertension (OR = 3.265, 95 % CI 1.003–10.627, P = 0.049) were independent risk factors for angiographic success in TRA group.</div></div><div><h3>Conclusion</h3><div>Compared to the transfemoral artery approach, the transradial artery approach was associated with shorter hospital stays, less perioperative complications and can be used as a available approach in cerebral angiography. Age and hypertension were independent risk factors for angiographic success in TRA group.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"188 ","pages":"Article 112165"},"PeriodicalIF":3.2,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143937254","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":"Assessment of biventricular cardiac function using free-breathing artificial intelligence cine with motion correction: Comparison with standard multiple breath-holding cine","authors":"Lingping Ran ,&nbsp;Xianghu Yan ,&nbsp;Yun Zhao ,&nbsp;Zhaoxia Yang ,&nbsp;Zihao Chen ,&nbsp;Fenggang Jia ,&nbsp;Xiaopeng Song ,&nbsp;Lu Huang ,&nbsp;Liming Xia","doi":"10.1016/j.ejrad.2025.112133","DOIUrl":"10.1016/j.ejrad.2025.112133","url":null,"abstract":"&lt;div&gt;&lt;h3&gt;Purpose&lt;/h3&gt;&lt;div&gt;To assess the image quality and biventricular function utilizing a free-breathing artificial intelligence cine method with motion correction (FB AI MOCO).&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Methods&lt;/h3&gt;&lt;div&gt;A total of 72 participants (mean age 38.3 ± 15.4 years, 40 males) prospectively enrolled in this single-center, cross-sectional study underwent cine scans using standard breath-holding (BH) cine and FB AI MOCO cine at 3.0 Tesla. The image quality of the cine images was evaluated with a 5-point Ordinal Likert scale based on blood-pool to myocardium contrast, endocardial edge definition, and artifacts, and overall quality score was calculated by the equal weight average of all three criteria, apparent signal to noise ratio (aSNR), estimated contrast to noise ratio (eCNR) were assessed. Biventricular functional parameters including Left Ventricular (LV), Right Ventricular (RV) End-Diastolic Volume (EDV), End-Systolic Volume (ESV), Stroke Volume (SV), Ejection Fraction (EF), and LV End-Diastolic Mass (LVEDM) were also assessed. Comparison between two sequences was assessed using paired &lt;em&gt;t&lt;/em&gt;-test and Wilcoxon signed-rank test, correlation using Pearson correlation. The agreement of quantitative parameters was assessed using intraclass correlation coefficient (ICC) and Bland-Altman analysis. P &lt; 0.05 was statistically significant.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Results&lt;/h3&gt;&lt;div&gt;The total acquisition time of the entire stack for FB AI MOCO cine (14.7 s ± 1.9 s) was notably shorter than that for standard BH cine (82.6 s ± 11.9 s, P &lt; 0.001). The aSNR between FB AI MOCO cine and standard BH cine has no significantly difference (76.7 ± 20.7 vs. 79.8 ± 20.7, P = 0.193). The eCNR of FB AI MOCO cine was higher than standard BH cine (191.6 ± 54.0 vs. 155.8 ± 68.4, P &lt; 0.001), as was the scores of blood-pool to myocardium contrast (4.6 ± 0.5 vs. 4.4 ± 0.6, P = 0.003). Qualitative scores including endocardial edge definition (4.2 ± 0.5 vs. 4.3 ± 0.7, P = 0.123), artifact presence (4.3 ± 0.6 vs. 4.1 ± 0.8, P = 0.085), and overall image quality (4.4 ± 0.4 vs. 4.3 ± 0.6, P = 0.448), showed no significant differences between the two methods. Representative RV and LV functional parameters — including RVEDV (102.2 (86.4, 120.4) ml vs. 104.0 (88.5, 120.3) ml, P = 0.294), RVEF (31.0 ± 11.1 % vs. 31.2 ± 11.0 %, P = 0.570), and LVEDV (106.2 (86.7, 131.3) ml vs. 105.8 (84.4, 130.3) ml, P = 0.450) — also did not differ significantly between the two methods. Strong correlations (r &gt; 0.900) and excellent agreement (ICC &gt; 0.900) were found for all biventricular functional parameters between the two sequences. In subgroups with reduced LVEF (&lt;50 %, n = 24) or elevated heart rate (≥80  bpm, n = 17), no significant differences were observed in any biventricular functional metrics (P &gt; 0.05 for all) between the two sequences.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Conclusion&lt;/h3&gt;&lt;div&gt;In comparison to multiple BH cine, the FB AI MOCO cine achieved comparable image qualit","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"188 ","pages":"Article 112133"},"PeriodicalIF":3.2,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143946998","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":"Digital twins in radiology: A systematic review of applications, challenges, and future perspectives","authors":"E. Faiella ,&nbsp;M. Pileri ,&nbsp;R. Ragone ,&nbsp;R.F. Grasso ,&nbsp;B.Beomonte Zobel ,&nbsp;D. Santucci","doi":"10.1016/j.ejrad.2025.112166","DOIUrl":"10.1016/j.ejrad.2025.112166","url":null,"abstract":"<div><h3>Background</h3><div>Digital twins (DTs) represent a transformative advancement in radiology, integrating multimodal imaging, artificial intelligence (AI), and computational modeling to create dynamic, patient-specific virtual representations.</div></div><div><h3>Methods</h3><div>This systematic review evaluated DTs applications across different imaging modalities. A total of 24 studies were analyzed, encompassing abdominal, musculoskeletal, interventional, dental, head and neck, cardiothoracic, breast, and general radiology. QUADAS-2 tool was used to assess risk of bias and applicability evaluation of the included studies.</div></div><div><h3>Results</h3><div>Key findings highlighted the role of DTs in predicting disease risk, optimizing therapies, and improving diagnostic accuracy, with applications including portal hypertension, scoliosis progression, liver ablation, brain tumor characterization, and noninvasive cardiothoracic assessment. Broader uses in general radiology included predictive modeling, automated dosimetry, and radiographer training. DTs are increasingly applied in major clinical domains such as oncology, cardiovascular imaging, and hepatic surgery, underscoring their emerging translational impact in radiology.</div></div><div><h3>Conclusions</h3><div>While DTs demonstrate significant potential, challenges such as computational demands, data integration, and clinical validation persist. Future research endeavors should focus on standardization, improved computational efficiency, and interdisciplinary collaboration to advance DTs from research to routine clinical practice, heralding a new era of personalized radiology.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"189 ","pages":"Article 112166"},"PeriodicalIF":3.2,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144072081","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}