European Journal of Radiology最新文献

{"title":"[18F]-FAPI-04 PET/CT improves metastatic lesions detection for patients with uterine malignancy after radical surgery: prospectively compared with [18F]-FDG PET/CT","authors":"Haipeng Chen ,&nbsp;Hao Peng ,&nbsp;Jiucen Liang ,&nbsp;Shuqin Jiang ,&nbsp;Shuyi Li ,&nbsp;Zhidong Liu ,&nbsp;Jingjing Song ,&nbsp;Yuanlin Chen ,&nbsp;Yan Hao ,&nbsp;Linqi Zhang ,&nbsp;Rusen Zhang","doi":"10.1016/j.ejrad.2025.112270","DOIUrl":"10.1016/j.ejrad.2025.112270","url":null,"abstract":"<div><h3>Objectives</h3><div>This prospective study aimed to investigate the potential of [¹⁸F]-fibroblast activation protein inhibitor ([¹⁸F]-FAPI)-04 PET/CT for evaluating suspected recurrent uterine malignancy after radical surgery, and prospectively compared it with [¹⁸F]-Fluorodeoxyglucose ([¹⁸F]-FDG) PET/CT.</div></div><div><h3>Methods</h3><div>From August 2022 to August 2024, patients with suspected recurrent/metastatic uterine malignancy following radical surgery received both [¹⁸F]-FDG PET/CT and [¹⁸F]-FAPI-04 PET/CT examinations, with imaging data prospectively evaluated. The comparative diagnostic efficacy of two PET/CT modalities for recurrence detection was statistically assessed using McNemar’s test and the difference of lesion tracer uptake parameters [Maximum standardized uptake value (SUV_max) and Tumor-to-Background Ratio (TBR)] were analyzed by Wilcoxon signed-rank tests.</div></div><div><h3>Results</h3><div>36 patients with 482 local relapses and distant metastases were included. Local relapses demonstrated comparable diagnostic performance between [¹⁸F]-FAPI-04 and [¹⁸F]-FDG PET/CT, with no significant differences in SUV_max and TBR. In nodal metastases assessment, [¹⁸F]-FAPI-04 PET/CT exhibited superior detection capability over [¹⁸F]-FDG PET/CT (p &lt; 0.01), with the diagnostic advantage most evident in abdominal lymph node metastases. Visceral metastatic lesions demonstrated significantly elevated [¹⁸F]-FAPI-04 PET/CT uptake parameters (SUV_max and TBR) compared to [¹⁸F]-FDG PET/CT imaging, especially in peritoneal and brain metastases.</div></div><div><h3>Conclusions</h3><div>[¹⁸F]-FAPI-04 PET/CT demonstrated superior detection capability for postoperative metastatic lesions in uterine cancer patients compared to [¹⁸F]-FDG PET/CT, with particularly diagnostic advantage in abdominal lymph node, brain, and peritoneal metastases.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"190 ","pages":"Article 112270"},"PeriodicalIF":3.2,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144524271","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":"Feasibility of bioresorbable gelatin microspheres for organ-preserving transarterial embolization in arterial bleeding","authors":"Jae Hwan Lee ,&nbsp;Chong-ho Lee ,&nbsp;Kun Yung Kim ,&nbsp;Young-Min Han ,&nbsp;Minuk Kim ,&nbsp;Sung-hwan Yoon ,&nbsp;Chang Jin Yoon","doi":"10.1016/j.ejrad.2025.112269","DOIUrl":"10.1016/j.ejrad.2025.112269","url":null,"abstract":"<div><h3>Purpose</h3><div>Bioresorbable gelatin microspheres (R-GMs) allow controlled and temporary embolic effects with adjustable degradation times. This study aimed to assess the feasibility and safety of R-GMs for temporary embolization in a porcine kidney model of arterial bleeding.</div></div><div><h3>Methods</h3><div>The pigs were randomly assigned to the R-GM group or conventional gelatin microsphere (C-GM) group. Active bleeding was induced in ten male pigs by perpendicular puncturing the lower polar artery of the right kidney under ultrasound guidance. Immediate angiography confirmed arterial bleeding. Proximal embolization of the lower polar artery was performed in each group. Follow-up angiography to monitor embolization status, re-bleeding, and recanalization, with the follow-up time points assessing both the short- and long-term re-bleeding risk. On day 7, the pigs were sacrificed, and a histopathologic examination was performed to evaluate residual embolic material, inflammatory response, and tissue damage within the embolized lower polar area.</div></div><div><h3>Results</h3><div>None of the animals showed re-bleeding. In the R-GM group, perfusion surrounding the injured vessel was restored as early as at 2 post-intervention hours, while the lower polar artery remained occluded in the C-GM group until day 7. Further, the R-GM group had a smaller infarct area in the lower pole of the right kidney than the C-GM group (5.80 ± 9.46 % vs. 93.32 ± 13.21 %, p &lt; 0.001), with markedly lower levels of inflammatory cell infiltration and fibrosis.</div></div><div><h3>Conclusion</h3><div>Temporary embolization with R-GMs effectively achieved hemostasis and allowed controlled recanalization, which minimized collateral tissue damage. These findings support the feasibility of R-GMs for organ-preserving embolization in acute arterial bleeding.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"190 ","pages":"Article 112269"},"PeriodicalIF":3.2,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144513559","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":"Role of imaging-guided biopsy for hepatocellular carcinoma","authors":"Roberto Cannella ,&nbsp;Zachary T. Berman ,&nbsp;Nikhil V. Tirukkovalur ,&nbsp;Samer T. Tohme ,&nbsp;Marta I. Minervini ,&nbsp;Alessandro Furlan","doi":"10.1016/j.ejrad.2025.112271","DOIUrl":"10.1016/j.ejrad.2025.112271","url":null,"abstract":"<div><div>Percutaneous imaging-guided biopsy of hepatocellular carcinoma (HCC) is a relatively safe procedure with an established diagnostic role, and a growing value in providing prognostic and treatment information for patient’s management. Because of the high specificity and positive predictive value of tumoral features on cross-sectional imaging studies, the number of biopsies performed for HCC is limited to certain specific clinical scenarios. However, routine imaging fails to fully capture the tumor’s molecular heterogeneity, and as research unravels the potential of tumoral histopathological and molecular stratification, biopsy is poised to transition from a diagnostic tool to a powerful prognostication instrument, contributing to guiding personalized treatment management for patients with HCC. In this review paper, we explore the role of percutaneous, imaging-guided biopsy in the diagnosis, prognosis, and treatment of HCC.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"191 ","pages":"Article 112271"},"PeriodicalIF":3.2,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144579629","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":"One-Stop multienergy pancreatic dynamic volume perfusion imaging using photon-counting detector CT: Initial experience","authors":"Yanzhao Yang ,&nbsp;Naiyi Zhu ,&nbsp;Huimin Lin ,&nbsp;Zhihan Xu ,&nbsp;Rui Chang ,&nbsp;Weimin Chai ,&nbsp;Fuhua Yan","doi":"10.1016/j.ejrad.2025.112268","DOIUrl":"10.1016/j.ejrad.2025.112268","url":null,"abstract":"<div><h3>Purpose</h3><div>This study reports initial experience with a modified one-stop, multienergy pancreatic VPCT protocol using PCCT, designed for comprehensive morphologic analysis and functional perfusion assessment of pancreatic ductal adenocarcinoma (PDAC).</div></div><div><h3>Materials and Methods</h3><div>From April 2024 to October 2024, participants with suspected PDAC were prospectively enrolled and underwent preoperative pancreatic dynamic VPCT. Individual phase images were extracted from perfusion datasets using T3D, virtual monoenergetic images (VMIs) at 55 and 70 keV reconstruction for diagnostic interpretation. Diagnostic image quality was assessed both quantitatively and subjectively. Perfusion maps were generated for analysis. Perfusion parameters were compared between PDAC lesions and normal parenchyma, as well as among PDAC histopathological differentiation. Radiation doses were recorded.</div></div><div><h3>Results</h3><div>A total of 65 participants (39 male; mean age, 66.2 ± 6.3 years) with histologically confirmed PDAC were included. The protocol achieved a mean effective radiation dose of 16.4 ± 4.5 mSv. All individual phase images met diagnostic quality standards (subjective scores ≥ 3). Among these, 55 keV VMIs demonstrated the highest CNR for PDAC lesions and adjacent vasculature, and superior subjective scores for lesion conspicuity in both pancreatic parenchymal and portal venous phases (all p &lt; 0.05). Perfusion parameters, including blood flow (BF), blood volume (BV), time to drain (TTD), mean transit time, time to start, Tmax, and flow extraction product (FEP), differed significantly between PDAC lesions and normal parenchyma (all p &lt; 0.05). Poorly differentiated PDAC lesions exhibited significantly lower BF, BV, TTD, and Tmax values and reduced lesion-to-parenchyma ratios of BF, BV, and FEP compared to moderately-to-well-differentiated PDAC lesions.</div></div><div><h3>Conclusion</h3><div>The one-stop, multienergy pancreatic VPCT protocol using PCCT enables high-quality morphologic imaging and reliable functional perfusion assessment at reduced radiation doses. It provides valuable insights into PDAC differentiation and histopathological grading, with potential implications for improved clinical management.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"190 ","pages":"Article 112268"},"PeriodicalIF":3.2,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144524270","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":"Magnetic resonance imaging features of mesonephric-like adenocarcinoma of the uterine corpus in comparison with endometrial endometrioid carcinoma: Multi-institutional study","authors":"Saki Yamamoto ,&nbsp;Mitsuru Matsuki ,&nbsp;Sota Masuoka ,&nbsp;Tomohiro Kikuchi ,&nbsp;Hiroyuki Fujii ,&nbsp;Atsushi Kihara ,&nbsp;Naoki Sano ,&nbsp;Noriyoshi Fukushima ,&nbsp;Hiroyuki Fujiwara ,&nbsp;Hiroki Kato ,&nbsp;Yuki Himoto ,&nbsp;Hideyuki Fukui ,&nbsp;Takahiro Tsuboyama ,&nbsp;Yoshiko Ueno ,&nbsp;Shinya Fujii ,&nbsp;Kaori Yamada ,&nbsp;Harushi Mori","doi":"10.1016/j.ejrad.2025.112260","DOIUrl":"10.1016/j.ejrad.2025.112260","url":null,"abstract":"<div><h3>Purpose</h3><div>To examine magnetic resonance imaging (MRI) features of mesonephric-like adenocarcinoma (MLA) of the uterine corpus.</div></div><div><h3>Method</h3><div>MRI features of 19 patients with pathologically proven MLA of the uterine corpus were retrospectively compared with those of 95 patients with endometrial endometrioid carcinoma (EEC).</div></div><div><h3>Results</h3><div>Most patients with MLA were postmenopausal. Advanced FIGO stages were more common in the MLA than in the EEC group (63.2 % vs. 18.9 %, <em>p</em> &lt; 0.001). On MRI, endophytic growth into the myometrium were more frequent in the MLA than in the EEC group (68.4 % vs. 14.7 %, <em>p</em> = 0.005). The median maximum tumor diameter in the MLA group (52.4 mm) tended to be larger than that in the EEC group (38.9 mm), although the difference was not statistically significant (<em>p</em> = 0.374). The tumor-to-muscle signal intensity ratio (SIR) on fat-suppressed gadolinium-enhanced T1-weighted gradient-echo imaging was higher in the MLA group than in the EEC group. (1.67 vs. 1.36, <em>p</em> = 0.002). The SIR on diffusion-weighted imaging (DWI) was comparable between the two groups (8.35 vs. 6.72, <em>p</em> = 0.330). The apparent diffusion coefficient value was lower in the MLA than in the EEC group (0.69 10^-3 mm²/s vs. 0.76 × 10^-3 mm²/s, <em>p</em> = 0.003). Coexisting adenomyosis was more frequent in the MLA than in the EEC group (52.6 % vs. 21.1 %, <em>p</em> = 0.034). The concordance rate between MRI and pathology for adenomyosis coexistence was 84.2 % for MLA, 87.4 % for EEC, and 86.8 % overall. MLA of the uterine corpus was identified in two patients, characterized by development independent of and discontinuous from the endometrium, whereas EEC in all patients demonstrated continuity with the endometrium.</div></div><div><h3>Conclusions</h3><div>MRI of MLA of the uterine corpus typically demonstrates large, diffuse, and endophytic growth into the myometrium, with strong contrast enhancement and more restricted diffusion compared to EEC, with coexisting adenomyosis present in over 50% of patients. Therefore, postmenopausal women with adenomyosis should be carefully evaluated for MLA on MRI, particularly using DWI.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"190 ","pages":"Article 112260"},"PeriodicalIF":3.2,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144513558","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":"Explainable classification of Parkinson’s disease with different motor subtypes by analyzing the synthetic MRI quantitative parameters of subcortical nuclei","authors":"Dongliang Cheng ,&nbsp;Junyan Wen ,&nbsp;Yulin Liu ,&nbsp;Nan Ding ,&nbsp;Zhenpeng Duan ,&nbsp;Yunjun Yang ,&nbsp;Yaozhong Wu ,&nbsp;Hang Wang ,&nbsp;Jincheng Ma ,&nbsp;Jialu Zhang ,&nbsp;Zhifeng Xu ,&nbsp;Hai Zhao ,&nbsp;Ge Wen","doi":"10.1016/j.ejrad.2025.112272","DOIUrl":"10.1016/j.ejrad.2025.112272","url":null,"abstract":"<div><h3>Objectives</h3><div>To explore differences in quantitative parameters of subcortical nuclei using synthetic MRI across different motor subtypes of Parkinson’s Disease (PD), and to develop an interpretable model for distinguishing PD subtypes.</div></div><div><h3>Methods</h3><div>A total of 102 PD patients, including 43 Tremor-Dominant (TD) subtype and 59 Postural Instability and Gait Difficulty (PIGD) subtype and 42 age- and gender-matched healthy controls (HCs) were included. T1, T2, Proton Density (PrD), and Myelin Content (MYC) were extracted from 16 subcortical nuclei. We used Least Absolute Shrinkage and Selection Operator (LASSO) regression to select features for Support Vector Machine (SVM) classification models and construct three classification models using one-vs-one strategy. Shapley analysis (SHAP) was used to explain the model.</div></div><div><h3>Results</h3><div>The PIGD subtype exhibited more extensive changes in SyMRI parameters in basal ganglia nuclei than the TD subtype, particularly in T1 and T2. AUC values in the training and validation sets were as follows: 0.897/0.818 (PIGD vs. HC), 0.847/0.787 (TD vs. HC), and 0.820/0.769 (PIGD vs. TD). SHAP analysis revealed that in the PIGD vs. HC comparison, the top three features were T2_R_putamen (positive association) and MYC_L_GPi and MYC_R_SN (both negatively associated). In the TD vs. HC comparison, the top three features were T2_R_putamen, T1_R_SN, and T1_L_STN (all positively associated). In the PIGD vs. TD comparison, PrD_R_GPe and T2_R_SN were positively correlated, while MYC_L_GPi and MYC_R_GPe were negatively correlated.</div></div><div><h3>Conclusion</h3><div>SyMRI effectively detect brain microdamage in PD and distinguish between motor subtypes. Additionally, SHAP analysis identifies key predictive features for distinguishing these subtypes.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"190 ","pages":"Article 112272"},"PeriodicalIF":3.2,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144535942","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 transfer learning radiomics combined with explainable machine learning for preoperative thymoma risk prediction based on CT","authors":"Shujian Wu ,&nbsp;Lifang Fan ,&nbsp;Yimin Wu ,&nbsp;Jingya Xu ,&nbsp;Yong Guo ,&nbsp;Hu Zhang ,&nbsp;Zhengyuan Xu","doi":"10.1016/j.ejrad.2025.112266","DOIUrl":"10.1016/j.ejrad.2025.112266","url":null,"abstract":"<div><h3>Objective</h3><div>To develop and validate a computerized tomography (CT)‑based deep transfer learning radiomics model combined with explainable machine learning for preoperative risk prediction of thymoma.</div></div><div><h3>Methods</h3><div>This retrospective study included 173 pathologically confirmed thymoma patients from our institution in the training group and 93 patients from two external centers in the external validation group. Tumors were classified according to the World Health Organization simplified criteria as low‑risk types (A, AB, and B1) or high‑risk types (B2 and B3). Radiomics features and deep transfer learning features were extracted from venous‑phase contrast‑enhanced CT images by using a modified Inception V3 network. Principal component analysis and least absolute shrinkage and selection operator regression identified 20 key predictors. Six classifiers—decision tree, gradient boosting machine, k‑nearest neighbors, naïve Bayes, random forest (RF), and support vector machine—were trained on five feature sets: CT imaging model, radiomics feature model, deep transfer learning feature model, combined feature model, and combined model. Interpretability was assessed with SHapley Additive exPlanations (SHAP), and an interactive web application was developed for real‑time individualized risk prediction and visualization.</div></div><div><h3>Results</h3><div>In the external validation group, the RF classifier achieved the highest area under the receiver operating characteristic curve (AUC) value of 0.956. In the training group, the AUC values for the CT imaging model, radiomics feature model, deep transfer learning feature model, combined feature model, and combined model were 0.684, 0.831, 0.815, 0.893, and 0.910, respectively. The corresponding AUC values in the external validation group were 0.604, 0.865, 0.880, 0.934, and 0.956, respectively. SHAP visualizations revealed the relative contribution of each feature, while the web application provided real‑time individual prediction probabilities with interpretative outputs.</div></div><div><h3>Conclusion</h3><div>We developed a CT‑based deep transfer learning radiomics model combined with explainable machine learning and an interactive web application; this model achieved high accuracy and transparency for preoperative thymoma risk stratification, facilitating personalized clinical decision‑making.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"190 ","pages":"Article 112266"},"PeriodicalIF":3.2,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144502661","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":"Performance of conventional MRI and endoscopy in assessing complete tumor response following immunotherapy-based neoadjuvant therapy for rectal cancer","authors":"Gengyun Miao ,&nbsp;Jingjing Liu ,&nbsp;Wentao Tang ,&nbsp;Lechi Ye ,&nbsp;Lamei Deng ,&nbsp;Tianyong Xu ,&nbsp;Mengjiang He ,&nbsp;Wei Su ,&nbsp;Jiyuan Zhang ,&nbsp;Shaohua Lu ,&nbsp;Lingli Chen ,&nbsp;Haoxiang Xuan ,&nbsp;Fei Liang ,&nbsp;Guoxiang Hu ,&nbsp;Shengxiang Rao ,&nbsp;Mengsu Zeng ,&nbsp;Liheng Liu","doi":"10.1016/j.ejrad.2025.112267","DOIUrl":"10.1016/j.ejrad.2025.112267","url":null,"abstract":"<div><h3>Purpose</h3><div>Endoscopy and MRI are essential tools for assessing treatment response in locally advanced rectal cancer (LARC). However, their accuracy in identifying pathological complete response (pCR; ie, ypT0N0) following immunotherapy-based neoadjuvant chemoradiotherapy (iNCRT) remains uncertain. This study evaluates the performance of endoscopy and MRI in reflecting ypT0 status and assesses MRI efficacy for lymph node metastasis in LARC following iNCRT.</div></div><div><h3>Materials and methods</h3><div>A retrospective study was conducted on LARC patients who underwent total mesorectal excision after iNCRT between March 2022 and June 2023. A cohort of 130 NCRT-only patients was matched in a 1:2 ratio based on age, sex, and clinical stage. Restaging assessments included endoscopy, and T2-weighted/diffusion-weighted MRI (T2DWI) for primary tumors, as well as MRI for lymph node evaluation. Sensitivity, specificity, positive predictive value, and negative predictive value were calculated, and areas under the receiver operating characteristic curves (AUCs) were determined.</div></div><div><h3>Results</h3><div>Among 130 NCRT-treated patients (mean age 57.1 years; 90 male patients), T2DWI showed comparable specificity to endoscopy (85.1 % vs. 88.8 %) but limited sensitivity (50 % vs. 16.7 %) in diagnosing ypT0. In 65 patients (mean age 56.6 years; 45 male patients) treated with iNCRT, MRI and endoscopy showed poor performance for ypT0, with AUCs ranging from 0.54 to 0.57. A 3 mm short-axis diameter cutoff effectively identified ypN0 status (AUC 0.76, 95 % CI: 0.64–0.86).</div></div><div><h3>Conclusion</h3><div>Endoscopy and MRI cannot reliably identify ypT0 status, but a 3 mm cutoff for short-axis diameter on MRI may assist in diagnosing ypN0 in LARC patients treated with iNCRT.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"190 ","pages":"Article 112267"},"PeriodicalIF":3.2,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144518883","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":"Predicting brain metastases in EGFR-positive lung adenocarcinoma patients using pre-treatment CT lung imaging data","authors":"Xinliu He ,&nbsp;Chao Guan ,&nbsp;Ting Chen ,&nbsp;Houde Wu ,&nbsp;Liuchao Su ,&nbsp;Mingfang Zhao ,&nbsp;Li Guo","doi":"10.1016/j.ejrad.2025.112265","DOIUrl":"10.1016/j.ejrad.2025.112265","url":null,"abstract":"<div><h3>Objectives</h3><div>This study aims to establish a dual-feature fusion model integrating radiomic features with deep learning features, utilizing single-modality pre-treatment lung CT image data to achieve early warning of brain metastasis (BM) risk within 2 years in EGFR-positive lung adenocarcinoma.</div></div><div><h3>Materials and methods</h3><div>After rigorous screening of 362 EGFR-positive lung adenocarcinoma patients with pre-treatment lung CT images, 173 eligible participants were ultimately enrolled in this study, including 93 patients with BM and 80 without BM. Radiomic features were extracted from manually segmented lung nodule regions, and a selection of features was used to develop radiomics models. For deep learning, ROI-level CT images were processed using several deep learning networks, including the novel vision mamba, which was applied for the first time in this context. A feature-level fusion model was developed by combining radiomic and deep learning features. Model performance was assessed using receiver operating characteristic (ROC) curves and decision curve analysis (DCA), with statistical comparisons of area under the curve (AUC) values using the DeLong test.</div></div><div><h3>Results</h3><div>Among the models evaluated, the fused vision mamba model demonstrated the best classification performance, achieving an AUC of 0.86 (95% CI: 0.82–0.90), with a recall of 0.88, F1-score of 0.70, and accuracy of 0.76. This fusion model outperformed both radiomics-only and deep learning-only models, highlighting its superior predictive accuracy for early BM risk detection in EGFR-positive lung adenocarcinoma patients.</div></div><div><h3>Conclusion</h3><div>The fused vision mamba model, utilizing single CT imaging data, significantly enhances the prediction of brain metastasis within two years in EGFR-positive lung adenocarcinoma patients. This novel approach, combining radiomic and deep learning features, offers promising clinical value for early detection and personalized treatment.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"190 ","pages":"Article 112265"},"PeriodicalIF":3.2,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144513557","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 clinical value of second-opinion reporting by subspecialist musculoskeletal radiologists","authors":"Ajay Patel ,&nbsp;Amanda Isaac","doi":"10.1016/j.ejrad.2025.112262","DOIUrl":"10.1016/j.ejrad.2025.112262","url":null,"abstract":"<div><h3>Introduction</h3><div>This systematic review aims to evaluate the added clinical value of secondary interpretations produced by specialist musculoskeletal radiologists. Additional aims are to identify clinical settings producing more discrepant cases between the initial and secondary interpreters.</div></div><div><h3>Methods</h3><div>A systematic search of the MEDLINE and Scopus databases was performed for original research studies, which included a discrepancy rate or a number of discordant reports between a primary interpreter of any training level and a secondary subspecialist musculoskeletal radiologist. Full texts included were screened by two reviewers to determine inclusion. A modified version of the QUADAS-2 tool was used to evaluate the risk of bias for each study.</div></div><div><h3>Results</h3><div>Eight studies with 11,186 initial imaging examinations reinterpreted by a specialist musculoskeletal radiologist met the inclusion criteria. Across the studies, clinically significant discrepancies were generally defined as discrepant cases impacting a patient’s management. Most initial reports were produced by radiologists of varying experience without musculoskeletal specialisation. The secondary reports were produced mainly by multiple experienced subspecialised musculoskeletal radiologists. The range of clinically significant discrepancies reported across the eight studies was between 1.4–27.9%. High discrepancy rates were seen in musculoskeletal oncologic cases, and lower discrepancy rates were seen in appendicular radiographs; however, it was concluded that both areas require greater awareness of the potential discrepancies.</div></div><div><h3>Conclusion</h3><div>Second opinion reports initially interpreted by a non-musculoskeletal radiologist and reinterpreted by a specialist musculoskeletal radiologist were established as beneficial for patients and impacted their management, especially in musculoskeletal oncology cases, fractures within the appendicular extremities and multiple myeloma focal lesion detection. Greater attention to these clinical settings can potentially advise policymaking to formalise second opinion reinterpretations, which could reduce the risk of misdiagnosis and enhance patient safety and survival. Findings highlight areas requiring greater focus in radiology education, guiding resource allocation to address knowledge gaps and enhance diagnostic accuracy.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"190 ","pages":"Article 112262"},"PeriodicalIF":3.2,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144491983","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}