European Journal of Radiology最新文献

{"title":"Prediction of molecular subtypes of endometrial cancer patients on the basis of intratumoral and peritumoral radiomic features from multiparametric MR images","authors":"Jing Zhou ,&nbsp;Xuan Yu ,&nbsp;Yingying Cui ,&nbsp;Qian Zhou ,&nbsp;Qiannan Xu ,&nbsp;Xianwei Zhang ,&nbsp;Yan Bai ,&nbsp;Rushi Chen ,&nbsp;Qingxia Wu ,&nbsp;Meiyun Wang","doi":"10.1016/j.ejrad.2025.112110","DOIUrl":"10.1016/j.ejrad.2025.112110","url":null,"abstract":"<div><h3>Objectives</h3><div>The purpose of this study was to assess the performance of multiparametric MRI-based radiomic models in predicting the molecular subtypes of endometrial cancer (EC) patients.</div></div><div><h3>Methods</h3><div>A total of 310 patients with pathologically confirmed EC who underwent preoperative MRI were enrolled this retrospective study and randomly divided into training (n = 217) and testing (n = 93) cohorts. We extracted 22,640 radiomic features from intratumoral and 3-mm peritumoral regions of interest (ROIs) on MR images. Feature selection was performed using the Mann-Whitney <em>U</em> test, Max-Relevance and Min-Redundancy (mRMR) and the least absolute shrinkage and selection operator (LASSO). Twelve radiomic signatures (RSs) were constructed using logistic regression to predict four molecular subtypes (POLEmut, MMRd, NSMP, and p53abn). The performance of these RSs was assessed using receiving operating characteristic (ROC) curve analysis, and the area under the curve (AUC), sensitivity, specificity, and accuracy were calculated.</div></div><div><h3>Results</h3><div>In the testing cohort, the RSs based on intratumoral features for predicting the POLEmut, MMRd, NSMP and p53abn subtypes yielded AUCs of 0.764, 0.812, 0.893 and 0.731, respectively, whereas those based on peritumoral features yielded AUCs of 0.847, 0.836, 0.871 and 0.804, respectively. The RSs constructed by combining intratumoral and peritumoral features for predicting the POLEmut, MMRd, NSMP and p53abn subtypes had the AUCs of 0.844, 0.880, 0.943 and 0.801, respectively.</div></div><div><h3>Conclusion</h3><div>The combination of intratumoral and peritumoral radiomic features from multiparametric MRI enables effective and noninvasive prediction of EC molecular subtypes.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"187 ","pages":"Article 112110"},"PeriodicalIF":3.2,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143855378","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":"CT-angiography in acute bleeding: Is a non-enhanced scan necessary?","authors":"Johannes Bremm ,&nbsp;Jörn Henze ,&nbsp;Thomas Dratsch ,&nbsp;Roman Klöckner ,&nbsp;David Maintz ,&nbsp;Daniel Pinto dos Santos","doi":"10.1016/j.ejrad.2025.112112","DOIUrl":"10.1016/j.ejrad.2025.112112","url":null,"abstract":"<div><h3>Objective</h3><div>In clinical routine CT-angiography is frequently used to detect hemorrhage and to locate its source. Many centers use a triple phase protocol consisting of non-contrast, arterial and portal venous phase scan. The aim of this study was to clarify the added value of the non-contrast CT scan in detection of hemorrhage and to provide evidence for or against its usage.</div></div><div><h3>Materials &amp; Methods</h3><div>We retrospectively included all patients between 2014 and 2020 who underwent triphasic CT angiography for suspected bleeding and interventional angiography within 6 h of CT confirming bleeding. Two experienced observers re-evaluated all CT scans and established consensus on whether the bleeding could confidently be detected without the non-enhanced CT scan. Additionally, we recorded data on radiation exposure.</div></div><div><h3>Results</h3><div>We included 75 patients (44 male, 31 female, median age 64 years) in the final dataset. Of all bleedings 33 (43 %) were GI bleedings. After consensus reading, non-enhanced CT scan was deemed helpful in only 3 cases (5.2 %) with all of these being GI bleeding. Non-enhanced series contributed substantially to the overall radiation exposure (mean DLP_{non contrast} 927.9 mGy*cm, mean DLP_arterial 631.3 mGy*cm, mean DLP_{portal venous} 915.0 mGy*cm).</div></div><div><h3>Conclusion</h3><div>Our results suggest that in the vast majority of cases non-contrast CT is not necessary to detect hemorrhage. Omission of non-enhanced CT scans results in relevant dose reduction. However, in few cases non-contrast scan can be helpful to exclude false positive findings in particular in suspected gastrointestinal bleeding.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"187 ","pages":"Article 112112"},"PeriodicalIF":3.2,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143823658","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-driven multi-class classification of brain strokes using computed tomography: A step towards enhanced diagnostic precision","authors":"Chathura D. Kulathilake ,&nbsp;Jeevani Udupihille ,&nbsp;Sachith P. Abeysundara ,&nbsp;Atsushi Senoo","doi":"10.1016/j.ejrad.2025.112109","DOIUrl":"10.1016/j.ejrad.2025.112109","url":null,"abstract":"<div><h3>Objective</h3><div>To develop and validate deep learning models leveraging CT imaging for the prediction and classification of brain stroke conditions, with the potential to enhance accuracy and support clinical decision-making.</div></div><div><h3>Materials and methods</h3><div>This retrospective, bi-center study included data from 250 patients, with a dataset of 8186 CT images collected from 2017 to 2022. Two AI models were developed using the Expanded ResNet101 deep learning framework as a two-step model. Model performance was evaluated using confusion matrices, supplemented by external validation with an independent dataset. External validation was conducted by an expert and two external members. Overall accuracy, confidence intervals, Cohen’s Kappa value, and McNemar’s test <em>P</em>-values were calculated.</div></div><div><h3>Results</h3><div>A total of 8186 CT images were incorporated, with 6386 images used for the training and 900 datasets for testing and validation in Model 01. Further, 1619 CT images were used for training and 600 datasets for testing and validation in Model 02. The average accuracy, precision, and F1 score for both models were assessed: Model 01 achieved 99.6 %, 99.4 %, and 99.6 % respectively, whereas Model 02 achieved 99.2 %, 98.8 %, and 99.1 %. The external validation accuracies were 78.6 % (95 % CI: 0.73,0.83; <em>P</em> &lt; 0.001) and 60.2 % (95 % CI: 0.48,0.70; <em>P</em> &lt; 0.001) for Models 01 and 02 respectively, as evaluated by the expert.</div></div><div><h3>Conclusion</h3><div>Deep learning models demonstrated high accuracy, precision, and F1 scores in predicting outcomes for brain stroke patients. With larger cohort and diverse radiologic mimics, these models could support clinicians in prognosis and decision-making.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"187 ","pages":"Article 112109"},"PeriodicalIF":3.2,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143842894","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":"Leveraging GPT-4 enables patient comprehension of radiology reports","authors":"M.H.Elise van Driel ,&nbsp;Noa Blok ,&nbsp;Jan A.J.G. van den Brand ,&nbsp;Davy van de Sande ,&nbsp;Marianne de Vries ,&nbsp;Bram Eijlers ,&nbsp;Fokko Smits ,&nbsp;Jacob J. Visser ,&nbsp;Diederik Gommers ,&nbsp;Cornelis Verhoef ,&nbsp;Michel E. van Genderen ,&nbsp;Dirk J. Grünhagen ,&nbsp;Denise E. Hilling","doi":"10.1016/j.ejrad.2025.112111","DOIUrl":"10.1016/j.ejrad.2025.112111","url":null,"abstract":"<div><h3>Objective</h3><div>To assess the feasibility of using GPT-4 to simplify radiology reports into B1-level Dutch for enhanced patient comprehension.</div></div><div><h3>Methods</h3><div>This study utilised GPT-4, optimised through prompt engineering in Microsoft Azure. The researchers iteratively refined prompts to ensure accurate and comprehensive translations of radiology reports. Two radiologists assessed the simplified outputs for accuracy, completeness, and patient suitability. A third radiologist independently validated the final versions. Twelve colorectal cancer patients were recruited from two hospitals in the Netherlands. Semi-structured interviews were conducted to evaluate patients’ comprehension and satisfaction with AI-generated reports.</div></div><div><h3>Results</h3><div>The optimised GPT-4 tool produced simplified reports with high accuracy (mean score 3.33/4). Patient comprehension improved significantly from 2.00 (original reports) to 3.28 (simplified reports) and 3.50 (summaries). Correct classification of report outcomes increased from 63.9% to 83.3%. Patient satisfaction was high (mean 8.30/10), with most preferring the long simplified report.</div></div><div><h3>Conclusion</h3><div>RADiANT successfully enhances patient understanding and satisfaction through automated AI-driven report simplification, offering a scalable solution for patient-centred communication in clinical practice. This tool reduces clinician workload and supports informed patient decision-making, demonstrating the potential of LLMs beyond English-based healthcare contexts.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"187 ","pages":"Article 112111"},"PeriodicalIF":3.2,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143876615","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":"Ultrasound versus magnetic resonance imaging features in diagnosing placenta accreta: A systematic review and meta-analysis","authors":"Cong Li ,&nbsp;Ying Chen ,&nbsp;Yang Gao ,&nbsp;Yangcan Duan","doi":"10.1016/j.ejrad.2025.112108","DOIUrl":"10.1016/j.ejrad.2025.112108","url":null,"abstract":"<div><h3>Objective</h3><div>The purpose of this study is to conduct a complete analysis of the accuracy of ultrasound and MRI in detecting placenta accreta spectrum (PAS) disorders, as well as to investigate the accuracy of independent imaging findings in these diseases.</div></div><div><h3>Methods</h3><div>Pubmed, Web of Science, Embase, The Cochrane Library, and Google Scholar databases were searched from their establishment to January 1, 2025. Included were all studies that used both ultrasonography and MRI to diagnose pregnant women with PAS disorder. The ability of ultrasonography, MRI, and their independent features to diagnose PAS was evaluated using pooled sensitivity, specificity, diagnostic odds ratio (DOR), and receiver operating curves (ROC). Heterogeneity was calculated using Cochran Q and I² statistics, and the sources of heterogeneity were investigated using <em>meta</em>-regression and subgroup analysis.</div></div><div><h3>Results</h3><div>Following a series of rigorous assessments, the <em>meta</em>-analysis comprised 1989 pregnant women from 30 studies. The sensitivity and specificity of ultrasonography for the diagnosis of PAS were 0.87 (95 % CI, 0.82–0.90) and 0.83 (95 % CI, 0.77–0.88), respectively, whereas the sensitivity and specificity of MRI for the same diagnostic were 0.87 (95 % CI, 0.82–0.90) and 0.84 (95 % CI, 0.80–0.88). Intraplacental lacunae has the best diagnostic accuracy of ultrasound, while placental bulge has the highest diagnostic accuracy of MRI, with their area under the curve (AUC) of the ROC being 0.76 (95 % CI, 0.72–0.79) and 0.89 (95 % CI, 0.85–0.91), respectively.</div></div><div><h3>Conclusion</h3><div>The diagnostic accuracy of ultrasound and MRI for PAS was similar. However, radiographic findings should not be utilized to make an independent diagnosis of PAS disorders.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"187 ","pages":"Article 112108"},"PeriodicalIF":3.2,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143842786","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":"Preliminary evidence that bilateral scaphoid symmetry is not affected by hand dominance or biological sex: volumetric and geometric analysis using high-resolution computed tomography with 0.5 mm slice-thickness","authors":"Michael Roberts ,&nbsp;Susie Lee ,&nbsp;Amy Allen ,&nbsp;Eliza Whiteside ,&nbsp;Edward Bliss ,&nbsp;Rose Nicol ,&nbsp;Polly Burey ,&nbsp;Tristan Shelley ,&nbsp;Christopher Wall ,&nbsp;Vivek Shridhar","doi":"10.1016/j.ejrad.2025.112073","DOIUrl":"10.1016/j.ejrad.2025.112073","url":null,"abstract":"<div><div>The scaphoid bone has a unique anatomy that can lead to complicated injury healing including non-union with or without avascular necrosis and subsequent complex operative treatment. The use of imaging of contralateral bones for operative planning and implant creation such as bone grafting relies on the innate symmetry of the human body. Previous studies of scaphoid anatomy have demonstrated symmetry in three-dimensional space and volume in right-hand dominant individuals. There is a gap in the literature reporting on scaphoid symmetry in left-hand dominant individuals. This study used the computed tomography (CT) scans of 30 healthy participants to create three dimensional (3D) models of left and right scaphoids to assess their symmetry. These bilateral models were quantified with respect to volume, surface area, length, and iterative-closest point (ICP). Paired-sample t-tests found differences in the volumes of contralateral scaphoids in males however surface area, length, and ICP of the scaphoids was observed to be not significantly different suggesting symmetry using these measures. In females, there was a significant difference in length but not the other measures. These results support further investigation using larger sample sizes and greater representation of left hand dominant participants into the use of contralateral scaphoid CT scans in pre-operative planning for the manufacture of patient-specific implants.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"187 ","pages":"Article 112073"},"PeriodicalIF":3.2,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143842998","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 radiomics nomogram based on MRI for differentiating vertebral osteomyelitis from vertebral compression fractures","authors":"Hao Xing ,&nbsp;Zhe Liu ,&nbsp;Zongwei Li ,&nbsp;Huan Liu ,&nbsp;Yanan Wang ,&nbsp;Zhengqi Chang","doi":"10.1016/j.ejrad.2025.112106","DOIUrl":"10.1016/j.ejrad.2025.112106","url":null,"abstract":"<div><h3>Objectives</h3><div>This study aims to investigate the value of a radiomics nomogram based on magnetic resonance imaging (MRI) in distinguishing vertebral compression fractures (VCFs) from vertebral osteomyelitis (VOs).</div></div><div><h3>Materials and methods</h3><div>We conducted a retrospective analysis of the clinical data from 100 patients with VCFs and VOs, respectively at our hospital. The cases were randomly divided into training (n = 140) and testing sets (n = 60) in a 7:3 ratio. Two experienced radiologists outlined the regions of interest (ROI) on the MRI images using T2-weighted fat suppression (T2WI-FS) images and extracted the radiomic features. The Least Absolute Shrinkage and Selection Operator (Lasso) algorithm was used to select and reduce radiomic features to establish a radiomics model (Model 1), and a Logistic Regression algorithm was used to construct a radiomics score. A multivariable logistic regression analysis was conducted to establish a clinical model (Model 2). A combined model (radiomics nomogram, Model 3) was built based on the radiomics score and independent clinical factors. The diagnostic performance of Models 1, 2, and 3 was validated using the Area Under the Curve (AUC) and Decision Curve Analysis (DCA).</div></div><div><h3>Results</h3><div>The training and testing sets included 68/72 VCFs and 32/28 patients with VOs, respectively. There were no statistically significant differences in clinical characteristics such as age, sex, body mass index (BMI), CRP levels, ESR, and lesion stage between the training and testing sets (P &gt; 0.05). A total of 873 radiomic features and 6 clinical features were extracted. After screening, 10 optimal features were selected to build Model 1, while 5 clinical features were used to build Model 2. Models 1 and 2 were combined to create Model 3 and a nomogram was plotted. All the three models were constructed using Logistic Regression algorithms. Model 3 achieved a higher AUC than Models 1 and 2 for both the training and testing sets: 0.946 &gt; 0.904 &gt; 0.871 (training) and 0.900 &gt; 0.854 &gt; 0.818 (testing), respectively. Additionally, the DCA indicated that Model 3 had better clinical utility than Models 1 and 2.</div></div><div><h3>Conclusion</h3><div>Our analysis indicated that the radiomics nomogram, combined with radiomic and clinical features, provides significant clinical guidance in distinguishing vertebral compression fractures from spinal vertebral osteomyelitis.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"187 ","pages":"Article 112106"},"PeriodicalIF":3.2,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143823657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pictorial essay on selected new, emerging, and reclassified entities in the 2020 WHO classification of soft tissue tumors","authors":"Sinchun Hwang","doi":"10.1016/j.ejrad.2025.112093","DOIUrl":"10.1016/j.ejrad.2025.112093","url":null,"abstract":"<div><div>The 2020 WHO classification of soft tissue tumors includes major updates, incorporating new and emerging tumor entities, along with reclassified tumor types, supported by advances in immunohistochemistry and genetic data. This pictorial essay provides an overview of the selected new, “emerging,” and reclassified soft tissue tumors, highlighting their imaging characteristics. Given the rarity of many of these entities, familiarity with their imaging features will aid in accurate diagnosis, ultimately contributing to improved patient care and management of these tumors.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"187 ","pages":"Article 112093"},"PeriodicalIF":3.2,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143834792","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 lymph node metastases in patients with ovarian high-grade serous carcinoma: Incremental diagnostic value of dual-energy CT combined with morphologic parameters","authors":"Aining Zhang ,&nbsp;Wenhui Shao ,&nbsp;Jiacheng Song ,&nbsp;Weiling Zhai ,&nbsp;Shushen Lin ,&nbsp;Wenjun Cheng ,&nbsp;Feiyun Wu ,&nbsp;Ting Chen","doi":"10.1016/j.ejrad.2025.112107","DOIUrl":"10.1016/j.ejrad.2025.112107","url":null,"abstract":"&lt;div&gt;&lt;h3&gt;Objective&lt;/h3&gt;&lt;div&gt;To explore the feasibility of Dual-Energy Computed Tomography (DECT) in distinguishing metastatic from non-metastatic lymph nodes (LNs) in ovarian High-Grade Serous Carcinoma (HGSC), and to assess the incremental diagnostic value of combining DECT with morphologic parameters in differentiating metastatic and non-metastatic LNs.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Methods&lt;/h3&gt;&lt;div&gt;From October 2021 to May 2024, 141 LNs from 39 patients with HGSC who underwent DECT were retrospectively enrolled. LNs were matched with the pathological report. Five morphologic parameters and nine DECT parameters were assessed. DECT parameters were obtained from both the arterial and venous phases, including the attenuation at 40 and 70 keV, slope of the spectral Hounsfield unit curve (λ&lt;em&gt;&lt;sub&gt;Hu&lt;/sub&gt;&lt;/em&gt;), Virtual Non-Contrast (VNC), Iodine Concentration (IC), Normalized Iodine Concentration (NIC), electron density (Rho), effective atomic number (Z&lt;em&gt;&lt;sub&gt;eff&lt;/sub&gt;&lt;/em&gt;) and Dual-Energy Index (DEI). Independent-sample Student’s &lt;em&gt;t&lt;/em&gt; test was used to compare continuous variables, while multivariable binary logistic regression analyses was applied to identify independent predictors for LN metastasis in the morphology, DECT, and combined models. Receiver Operating Characteristic (ROC) analysis was performed to evaluate the diagnostic performance of these three models in differentiating metastatic from non-metastatic LNs.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Results&lt;/h3&gt;&lt;div&gt;86 metastatic LNs and 55 non-metastatic LNs were finally enrolled in our study. The short diameter (S), long diameter (L), and S/L ratio were significantly larger in metastatic LNs compared to non-metastatic LNs (9.69 ± 4.06 vs. 6.37 ± 1.24 mm, &lt;em&gt;P&lt;/em&gt; &lt; 0.001; 13.99 ± 5.36 vs.9.61 ± 2.30 mm, &lt;em&gt;P&lt;/em&gt; &lt; 0.001; 0.70 ± 0.15 vs. 0.67 ± 0.12, &lt;em&gt;P&lt;/em&gt; = 0.023). In the venous phase, λ&lt;sub&gt;HU&lt;/sub&gt;, VNC and Rho were significantly higher in metastatic LNs compared to non-metastatic LNs (−3.596 ± 1.115 vs. −4.234 ± 1.077, &lt;em&gt;P&lt;/em&gt; = 0.001; 24.242 ± 9.867 vs. 15.826 ± 11.830, &lt;em&gt;P&lt;/em&gt; &lt; 0.001; 32.557 ± 8.023 vs. 26.936 ± 9.420, &lt;em&gt;P&lt;/em&gt; &lt; 0.001), while IC, NIC, Z&lt;em&gt;&lt;sub&gt;eff&lt;/sub&gt;&lt;/em&gt;, DEI were significant lower in metastatic LNs than non-metastatic LNs (1.872 ± 0.678 vs. 2.404 ± 1.140, &lt;em&gt;P&lt;/em&gt; = 0.001; 38.309 ± 14.443 vs. 47.247 ± 22.270, &lt;em&gt;P&lt;/em&gt; = 0.005; 8.513 ± 0.320 vs. 8.719 ± 0.360, &lt;em&gt;P&lt;/em&gt; = 0.001; 0.014 ± 0.006 vs. 0.018 ± 0.007, &lt;em&gt;P&lt;/em&gt; = 0.045). The Area Under the Curve (AUC) of morphology model and DECT model were 0.793 (95 %CI: 0.721–0.862) and 0.762(95 %CI: 0.690–0.825), respectively. The combination of the morphology model and DECT model revealed optimal diagnostic performance (AUC = 0.845; 95 %CI: 0.780–0.896), which was significantly higher than that of the individual models (&lt;em&gt;P&lt;/em&gt; = 0.015, &lt;em&gt;P&lt;/em&gt; = 0.006, respectively).&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Conclusion&lt;/h3&gt;&lt;div&gt;DECT parameters provide incremental diagnostic value in assessing metastatic LNs i","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"187 ","pages":"Article 112107"},"PeriodicalIF":3.2,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143820702","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":"Contribution of lesion shape features to the VI-RADS for predicting muscle invasion in bladder tumors","authors":"Mahmut Bilal Doğan ,&nbsp;Nesrin Gündüz ,&nbsp;Hüseyin Özgür Kazan ,&nbsp;Mehmet Çağlar Çakıcı ,&nbsp;Asıf Yıldırım ,&nbsp;Gülnur Erdem","doi":"10.1016/j.ejrad.2025.112104","DOIUrl":"10.1016/j.ejrad.2025.112104","url":null,"abstract":"<div><h3>Objective</h3><div>Muscle invasion in bladder cancer is a crucial factor influencing treatment decisions and prognosis. We hypothesize that the integration of tumor shape characteristics with the VI-RADS scoring system improves the predictive accuracy for assessing muscle invasion in bladder cancer.</div></div><div><h3>Methods</h3><div>This prospective observational study included patients scheduled for transurethral resection of bladder tumor (TURBT) and/or cystectomy due to suspected bladder cancer between March 2022 and November 2024. All patients underwent multiparametric bladder MRI following the VI-RADS protocol. Tumor segmentation was performed using 3D Slicer to assess shape features, including sphericity, surface area, surface-volume ratio, elongation, and flatness. Mann-Whitney U tests were conducted to evaluate the association between shape features and muscle invasion, while ROC (Receiver Operating Characteristic) analysis determined threshold values.</div></div><div><h3>Results</h3><div>The study included 119 patients (98 males, 21 females; mean age 66.9 ± 9.9 years, range 33–89). Using VI-RADS ≥ 3 as the threshold, sensitivity was 100 %, with a specificity of 65.91 %. For VI-RADS ≥ 4, sensitivity was 80.65 %, and specificity was 95.45 %. A significant relation was found between tumor sphericity and muscle invasion. For VI-RADS ≥ 3B, sensitivity was 100 %, and specificity was 66.67 %.</div></div><div><h3>Conclusion</h3><div>The VI-RADS algorithm demonstrated high predictive accuracy for muscle invasion, particularly for tumors scored VI-RADS ≥ 4. Additionally, while a relation was identified between tumor sphericity and muscle invasion, its incorporation into the VI-RADS scoring system did not enhance the overall predictive performance of the algorithm.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"187 ","pages":"Article 112104"},"PeriodicalIF":3.2,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143808287","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}