European Journal of Radiology Open最新文献

{"title":"Magnetic resonance imaging radiomics-based machine learning model for preoperative prediction of pathological grade in pancreatic cancer: A preliminary study","authors":"Jiayi Bao ,&nbsp;Yuanqing Liu ,&nbsp;Yang Yu ,&nbsp;Ximing Wang ,&nbsp;Chunhong Hu ,&nbsp;Su Hu","doi":"10.1016/j.ejro.2025.100703","DOIUrl":"10.1016/j.ejro.2025.100703","url":null,"abstract":"<div><h3>Background</h3><div>To explore the value of MRI radiomics-based machine learning models for predicting the pathological grade of pancreatic cancer preoperatively.</div></div><div><h3>Methods</h3><div>125 patients with pathologically confirmed pancreatic cancer who underwent preoperative MRI were retrospectively enrolled. The primary cohort was randomized in an 8:2 ratio into a training cohort (n = 100) and a validation cohort (n = 25). 1316 radiomics features were extracted from contrast-enhanced T₁WI arterial phase (AP) or portal venous phase (PVP) images, respectively. After feature reduction and filtering, the best features were selected to construct machine learning models (K-nearest neighbor, KNN; support vector machine, SVM; logistic regression, LR; random forest, RF). Finally, the performance of these models was evaluated using the receiver operating characteristic curve (ROC).</div></div><div><h3>Results</h3><div>There were no statistical differences in clinical characteristics between the low-grade and high-grade cohorts (<em>P</em> &gt; 0.05). The best radiomics features selected from the AP, PVP and AP+PVP images were 6, 6 and 10, respectively. Among the four models, the LR machine learning model achieved the best predictive performance. The distribution of the Radscore values was clinically significant between the low-grade and high-grade groups both in the training cohort (median, 0.26 vs 0.99; <em>P</em> &lt; 0.001) and validation cohort (median, 0.63 vs 1.48; <em>P</em> = 0.011). LR model of AP+PVP performed the best with AUC value of 0.81 (95 % CI: 0.72–0.91) for the training cohort and 0.82 (95 % CI: 0.62–1.00) for the validation cohort.</div></div><div><h3>Conclusions</h3><div>MRI radiomics-based machine learning model is a potential non-invasive method to predict the pathological grade of pancreatic cancer.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"15 ","pages":"Article 100703"},"PeriodicalIF":2.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145464879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnostic accuracy of AI in chest radiography for pneumonia and lung cancer: A meta-analysis","authors":"Mohammed Elmujtba Adam Essa","doi":"10.1016/j.ejro.2025.100701","DOIUrl":"10.1016/j.ejro.2025.100701","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>Chest radiography (CXR) is the most common imaging test worldwide for evaluating pulmonary disease, yet its sensitivity for pneumonia and lung cancer is limited. Artificial intelligence (AI) based image analysis has shown promise to aid radiographic diagnosis. A meta-analysis was performed for AI algorithms evaluation for detecting pneumonia or lung nodules on CXR, and AI performance was compared to human readers.</div></div><div><h3>Materials and Methods</h3><div>Following PRISMA guidelines, searched PubMed/Medline, Embase, Cochrane, and IEEE Xplore (Jan 2017–July 2025) for diagnostic accuracy studies of AI on CXR. Eligible studies included any prospective or retrospective design reporting sensitivity and specificity for AI-based pneumonia or lung nodule detection, with an independent reference standard. Data were extracted using a standardized form and quality was assessed with QUADAS2.</div></div><div><h3>Results</h3><div>Fifteen studies (≈12,000 CXRs) met inclusion criteria; individual AI algorithms achieved sensitivities of ∼70–97 % and specificities of ∼85–95 %. Meta-analysis yielded a pooled sensitivity of 88 % and specificity of 90 % for AI pneumonia detection. For lung nodules, pooled AI sensitivity was ≈ 72 % and specificity ≈ 95 %. One representative deep-learning model for detecting nodules. AI tended to miss very small or central nodules but detected ∼90 % of larger nodules. Crucially, using AI as a second reader improved radiologist performance, increasing sensitivity by approximately 9–10 %age points.</div></div><div><h3>Conclusion</h3><div>AI algorithms demonstrate high diagnostic accuracy for pneumonia on CXR and can markedly increase the detection of occult lung nodules when used as a second reader. However, performance varies by lesion characteristics. Overall, AI has strong potential to enhance clinical chest radiograph interpretation.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"15 ","pages":"Article 100701"},"PeriodicalIF":2.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145464878","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnostic performance of dual-layer spectral CT Radiomics and deep learning for differentiating osteoblastic bone metastases from bone islands","authors":"Yuchao Xiong ,&nbsp;Wei Guo ,&nbsp;Xuwen Zeng ,&nbsp;Fan Xu ,&nbsp;Li Wu ,&nbsp;Jiahui Ou","doi":"10.1016/j.ejro.2025.100679","DOIUrl":"10.1016/j.ejro.2025.100679","url":null,"abstract":"<div><h3>Background</h3><div>This study aimed to compare the diagnostic performance of radiomic features derived from dual-layer spectral detector computed tomography (DLSCT) and a deep learning (DL) model applied to conventional CT images in the differentiation of osteoblastic bone metastases (OBM) from bone islands (BI).</div></div><div><h3>Methods</h3><div>This retrospective study included patients with osteogenic lesions who underwent DLSCT examinations between March 2023 and September 2023. We extracted first-order radiomic features (e.g., mean, maximum, entropy) from both conventional and spectral images. A previously validated DL model was applied to the conventional CT images. We evaluated diagnostic performance using ROC curve analysis, comparing AUC, sensitivity, and specificity.</div></div><div><h3>Results</h3><div>The study included 216 lesions from 94 patients (66 ± 12 years; 48 males, 46 females): 125 BI and 91 OBM lesions. Significant differences were observed between OBM and BI groups for the mean, maximum, entropy, and uniformity of first-order radiomic features (all P &lt; 0.05). DLSCT (entropy from VMI40keV) and the DL model had comparable AUCs (0.93 vs. 0.96; P = 0.274). However, DLSCT showed superior sensitivity (92 % vs. 62 %; P = 0.002) but comparable specificity (88 % vs. 96 %; P = 0.07) for diagnosing OBM compared to the DL model.</div></div><div><h3>Conclusion</h3><div>Radiomic features from DLSCT differentiate between BI and OBM with diagnostic performance comparable to that of a DL model. Furthermore, VMI40keV image-derived entropy demonstrated superior sensitivity in diagnosing OBM compared to the DL model.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"15 ","pages":"Article 100679"},"PeriodicalIF":2.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144879230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of a hybrid 2.5D deep learning model for glioma survival prediction using T1-weighted MRI from the CGGA database","authors":"Kai Jin,&nbsp;Caixing Sun,&nbsp;Liang Xia","doi":"10.1016/j.ejro.2025.100697","DOIUrl":"10.1016/j.ejro.2025.100697","url":null,"abstract":"<div><h3>Background</h3><div>Current glioma survival prediction relies on invasive molecular profiling. To overcome this, a non-invasive deep learning framework using T1-weighted contrast-enhanced MRI (T1CE) was developed to predict overall survival. This framework addresses computational limitations associated with the volumetric analysis while preserving important spatial information.</div></div><div><h3>Methods</h3><div>We designed a hybrid 2.5D convolutional neural network to process multi-slice inputs, including the center slice and its adjacent slices, from 217 patients in the CGGA database. Transfer learning using ResNet and DenseNet architectures were employed to initialize the models. These models were subsequently fine-tuned with the Cox proportional hazards loss function. After the fine-tuning process was completed, the imaging signature was combined with clinical and molecular variables, including IDH and 1p19q status, to build an integrated model. Performance was evaluated via C-index, time-dependent AUC, and Kaplan-Meier analysis in independent training (70 %) and testing (30 %) cohorts.</div></div><div><h3>Results</h3><div>The Combined model achieved superior discrimination, with a training C-index of 0.819 (95 % CI: 0.758–0.880) and a testing C-index of 0.804 (95 % CI: 0.708–0.900). It significantly outperformed the isolated Radiomic, deep learning (2D and 2.5D), and Clinical models (all p &lt; 0.05). Moreover, time-dependent ROC analysis demonstrated consistent model performance over 1–5 years, with AUC values ranging from 0.851 to 0.906. The stratified survival curves clearly revealed distinct prognostic groups (log-rank p &lt; 0.001).</div></div><div><h3>Conclusions</h3><div>The 2.5D multi-source framework provides a clinically feasible, non-invasive tool for preoperative survival prediction, enabling personalized therapeutic strategies for glioma patients.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"15 ","pages":"Article 100697"},"PeriodicalIF":2.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145415984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Differences in myocardial involvement between new onset and longstanding systemic lupus erythematosus patients assessed by cardiovascular magnetic resonance","authors":"Zhen Wang ,&nbsp;Xing Tang ,&nbsp;Chaohui Hang ,&nbsp;Hui Gao ,&nbsp;Jinxiu Yang ,&nbsp;Yuchi Han ,&nbsp;Yongqiang Yu ,&nbsp;Zongwen Shuai ,&nbsp;Ren Zhao ,&nbsp;Xiaohu Li","doi":"10.1016/j.ejro.2024.100623","DOIUrl":"10.1016/j.ejro.2024.100623","url":null,"abstract":"<div><h3>Objectives</h3><div>Subclinical myocardial involvement is common in systemic lupus erythematosus (SLE), but differences between new onset and longstanding SLE are not fully elucidated. This study compared myocardial involvement in new onset versus longstanding SLE using cardiovascular magnetic resonance (CMR).</div></div><div><h3>Materials and methods</h3><div>We prospectively enrolled 24 drug-naïve new onset SLE patients, 27 longstanding SLE patients, and 20 healthy controls. All participants underwent clinical evaluation and CMR examination. We analyzed left ventricular (LV) morphological, functional parameters, and tissue characterization parameters: native T1, T2, extracellular volume fraction (ECV), and late gadolinium enhancement (LGE).</div></div><div><h3>Results</h3><div>Both new onset and longstanding SLE groups showed elevated native T1, T2, and ECV values compared to the control group (all P &lt; 0.05). Additionally, the new onset SLE group exhibited higher T2 values compared to the longstanding SLE group [55.3 vs. 52.8 ms, P &lt; 0.05]. The new onset group also demonstrated higher left ventricular (LV) end-diastolic volume index (LVEDVi), LV end-systolic volume index (LVSVi), and LV mass index (LVMi) than controls (all P &lt; 0.05), with LVEDVi significantly higher than in the longstanding group (P &lt; 0.05).</div></div><div><h3>Conclusion</h3><div>CMR tissue characterization imaging can detect early myocardial involvement in patients with new onset and longstanding SLE. Patients with new onset SLE exhibit more pronounced myocardial edema than those with longstanding SLE. This suggests that SLE patients are at risk of myocardial damage at various stages of the disease, underscoring the need for early monitoring and long-term management to prevent the progression of myocardial remodeling.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"14 ","pages":"Article 100623"},"PeriodicalIF":1.8,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11731982/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142985000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of large language models in generating pulmonary nodule follow-up recommendations","authors":"Junzhe Wen ,&nbsp;Wanyue Huang ,&nbsp;Huzheng Yan ,&nbsp;Jie Sun ,&nbsp;Mengshi Dong ,&nbsp;Chao Li ,&nbsp;Jie Qin","doi":"10.1016/j.ejro.2025.100655","DOIUrl":"10.1016/j.ejro.2025.100655","url":null,"abstract":"<div><h3>Rationale and objectives</h3><div>To evaluate the performance of large language models (LLMs) in generating clinically follow-up recommendations for pulmonary nodules by leveraging radiological report findings and management guidelines.</div></div><div><h3>Materials and methods</h3><div>This retrospective study included CT follow-up reports of pulmonary nodules documented by senior radiologists from September 1st, 2023, to April 30th, 2024. Sixty reports were collected for prompting engineering additionally, based on few-shot learning and the Chain of Thought methodology. Radiological findings of pulmonary nodules, along with finally prompt, were input into GPT-4o-mini or ERNIE-4.0-Turbo-8K to generate follow-up recommendations. The AI-generated recommendations were evaluated against radiologist-defined guideline-based standards through binary classification, assessing nodule risk classifications, follow-up intervals, and harmfulness. Performance metrics included sensitivity, specificity, positive/negative predictive values, and F1 score.</div></div><div><h3>Results</h3><div>On 1009 reports from 996 patients (median age, 50.0 years, IQR, 39.0–60.0 years; 511 male patients), ERNIE-4.0-Turbo-8K and GPT-4o-mini demonstrated comparable performance in both accuracy of follow-up recommendations (94.6 % vs 92.8 %, P = 0.07) and harmfulness rates (2.9 % vs 3.5 %, P = 0.48). In nodules classification, ERNIE-4.0-Turbo-8K and GPT-4o-mini performed similarly with accuracy rates of 99.8 % vs 99.9 % sensitivity of 96.9 % vs 100.0 %, specificity of 99.9 % vs 99.9 %, positive predictive value of 96.9 % vs 96.9 %, negative predictive value of 100.0 % vs 99.9 %, f1-score of 96.9 % vs 98.4 %, respectively.</div></div><div><h3>Conclusion</h3><div>LLMs show promise in providing guideline-based follow-up recommendations for pulmonary nodules, but require rigorous validation and supervision to mitigate potential clinical risks. This study offers insights into their potential role in automated radiological decision support.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"14 ","pages":"Article 100655"},"PeriodicalIF":1.8,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143886442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CT-based intratumoral and peritumoral radiomics nomogram to predict spread through air spaces in lung adenocarcinoma with diameter ≤ 3 cm: A multicenter study","authors":"Yangfan Su ,&nbsp;Junli Tao ,&nbsp;Xiaosong Lan ,&nbsp;Changyu Liang ,&nbsp;Xuemei Huang ,&nbsp;Jiuquan Zhang ,&nbsp;Kai Li ,&nbsp;Lihua Chen","doi":"10.1016/j.ejro.2024.100630","DOIUrl":"10.1016/j.ejro.2024.100630","url":null,"abstract":"<div><h3>Purpose</h3><div>The aim of this study was to explore and develop a preoperative and noninvasive model for predicting spread through air spaces (STAS) status in lung adenocarcinoma (LUAD) with diameter ≤ 3 cm.</div></div><div><h3>Methods</h3><div>This multicenter retrospective study included 640 LUAD patients. Center I included 525 patients (368 in the training cohort and 157 in the validation cohort); center II included 115 patients (the test cohort). We extracted radiomics features from the intratumor, extended tumor and peritumor regions. Multivariate logistic regression and boruta algorithm were used to select clinical independent risk factors and radiomics features, respectively. We developed a clinical model and four radiomics models (the intratumor model, extended tumor model, peritumor model and fusion model). A nomogram based on prediction probability value of the optimal radiomics model and clinical independent risk factors was developed to predict STAS status.</div></div><div><h3>Results</h3><div>Maximum diameter and nodule type were clinical independent risk factors. The extended tumor model achieved satisfactory STAS status discrimination performance with the AUC of 0.74, 0.71 and 0.80 in the three cohorts, respectively, performed better than other radiomics models. The integrated discrimination improvement value revealed that the nomogram outperformed compared to the clinical model with the value of 12 %. Patients with high nomogram score (≥ 77.31) will be identified as STAS-positive.</div></div><div><h3>Conclusions</h3><div>Peritumoral information is significant to predict STAS status. The nomogram based on the extended tumor model and clinical independent risk factors provided good preoperative prediction of STAS status in LUAD with diameter ≤ 3 cm, aiding surgical decision-making.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"14 ","pages":"Article 100630"},"PeriodicalIF":1.8,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11754163/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143029858","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Low KV-low contrast medium dose one-stop dual source CT high pitch integrated coronary-carotid-cerebral-aortic CTA improves image quality and reduces both radiation and contrast medium doses","authors":"Meng Wang,&nbsp;Chao Zheng,&nbsp;Lin Yang,&nbsp;Juan Su,&nbsp;Bo Wang,&nbsp;JieXin Sheng","doi":"10.1016/j.ejro.2025.100637","DOIUrl":"10.1016/j.ejro.2025.100637","url":null,"abstract":"<div><h3>Rationale and objectives</h3><div>To evaluate the impact of low dose-low contrast medium injection protocol on radiation dose and image quality of one-stop dual source high pitch integrated coronary -carotid -cerebral- aortic CTA.</div></div><div><h3>Methods</h3><div>A total of 211 non-obese patients, consisting of 44 females with an average age of 59 years, were split into two groups: low dose group (LD group n = 136) and routine dose group (RD group n = 75). Noise, attenuation, signal to noise ratio (SNR), and contrast to noise ratio (CNR) were compared between the groups by setting region of interest (ROI) in target vessels to evaluate objective image quality. Two radiologists assessed subjective image quality using the 5-point scale. volumetric CT dose index (CTDIvol), dose length production (DLP), and effective radiation dose (ED) were compared, while contrast medium (CM) dose was assessed by CM volume and iodine uptake (IU).</div></div><div><h3>Results</h3><div>Both radiation and CM dose were significantly reduced in the LD group compared with the RD group, DLP and ED were reduced by 51 %, and CM volume and IU were reduced by 13 % (all p &lt; 0.05). Attenuation and noise were higher, while SNR and CNR were close to or slightly higher in the LD group compared with the RD group. The LD group had higher subjective image quality scores while all scores in the two groups satisfied the diagnostic requirements.</div></div><div><h3>Conclusion</h3><div>Low-kV, low-CM one-stop dual-source high-pitch integrated coronary-carotid-cerebral-aortic CTA can ensure image quality while significantly reducing the doses of contrast medium and radiation</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"14 ","pages":"Article 100637"},"PeriodicalIF":1.8,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of lymph node metastasis in papillary thyroid carcinoma using non-contrast CT-based radiomics and deep learning with thyroid lobe segmentation: A dual-center study","authors":"Hao Wang ,&nbsp;Xuan Wang ,&nbsp;Yusheng Du ,&nbsp;You Wang ,&nbsp;Zhuojie Bai ,&nbsp;Di Wu ,&nbsp;Wuliang Tang ,&nbsp;Hanling Zeng ,&nbsp;Jing Tao ,&nbsp;Jian He","doi":"10.1016/j.ejro.2025.100639","DOIUrl":"10.1016/j.ejro.2025.100639","url":null,"abstract":"<div><h3>Objectives</h3><div>This study aimed to develop a predictive model for lymph node metastasis (LNM) in papillary thyroid carcinoma (PTC) patients by deep learning radiomic (DLRad) and clinical features.</div></div><div><h3>Methods</h3><div>This study included 271 thyroid lobes from 228 PTC patients who underwent preoperative neck non-contrast CT at Center 1 (May 2021–April 2024). LNM status was confirmed via postoperative pathology, with each thyroid lobe labeled accordingly. The cohort was divided into training (n = 189) and validation (n = 82) cohorts, with additional temporal (n = 59 lobes, Center 1, May–August 2024) and external (n = 66 lobes, Center 2) test cohorts. Thyroid lobes were manually segmented from the isthmus midline, ensuring interobserver consistency (ICC ≥ 0.8). Deep learning and radiomics features were selected using LASSO algorithms to compute DLRad scores. Logistic regression identified independent predictors, forming DLRad, clinical, and combined models. Model performance was evaluated using AUC, calibration, decision curves, and the DeLong test, compared against radiologists' assessments.</div></div><div><h3>Results</h3><div>Independent predictors of LNM included age, gender, multiple nodules, tumor size group, and DLRad. The combined model demonstrated superior diagnostic performance with AUCs of 0.830 (training), 0.799 (validation), 0.819 (temporal test), and 0.756 (external test), outperforming the DLRad model (AUCs: 0.786, 0.730, 0.753, 0.642), clinical model (AUCs: 0.723, 0.745, 0.671, 0.660), and radiologist evaluations (AUCs: 0.529, 0.606, 0.620, 0.503). It also achieved the lowest Brier scores (0.167, 0.184, 0.175, 0.201) and the highest net benefit in decision-curve analysis at threshold probabilities &gt; 20 %.</div></div><div><h3>Conclusions</h3><div>The combined model integrating DLRad and clinical features exhibits good performance in predicting LNM in PTC patients.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"14 ","pages":"Article 100639"},"PeriodicalIF":1.8,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143474694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Role of region-of-interest magnetic resonance imaging fusion biopsy in mitigating overtreatment of localized prostate cancer – A retrospective cohort study","authors":"Carrie Wang ,&nbsp;Purvish Trivedi ,&nbsp;Esther Katende ,&nbsp;Varun Awasthi ,&nbsp;Riley Smith ,&nbsp;Ryan Putney ,&nbsp;Yahya Bondokji ,&nbsp;Jong Y. Park ,&nbsp;Jasreman Dhillon ,&nbsp;Kosj Yamoah","doi":"10.1016/j.ejro.2025.100642","DOIUrl":"10.1016/j.ejro.2025.100642","url":null,"abstract":"<div><h3>Background</h3><div>Traditional ultrasonography-based prostate biopsy uses a transrectal approach for systematic sampling of 12 cores. The magnetic resonance imaging (MRI) fusion biopsy uses a targeted approach, first identifying regions of interest (ROI) clinically suspicious for prostate cancer (PCa) through MRI, before performing a prostate biopsy aided by ultrasonography.</div></div><div><h3>Methods</h3><div>The single-center institutional retrospective cohort study used 442 men who were recommended for localized PCa management. Cohort A (n = 346) comprised patients who underwent MRI-guided TRUS biopsies, which included both standard 12-core TRUS biopsies and MRI-targeted biopsies performed simultaneously. Cohort B (n = 96) comprised patients who received only standard TRUS biopsy. The primary endpoint was Gleason reclassification, defined as the change in Gleason scores between standard TRUS and targeted region-of-interest (ROI) biopsies among cohort A. Secondary endpoint assessed the role of ROI biopsies in mitigating overtreatment by analyzing the probability of undergoing treatment and the duration of active surveillance (AS).</div></div><div><h3>Results</h3><div>Among men classified as no tumor on standard biopsy, 16.9 % showed Gleason disease on subsequent ROI biopsy. Additionally, ROI group also had a longer time to receive primary treatment (<em>P</em> = .017), as they were more likely to opt for AS (54 %). Lastly, median time spent on AS was longer for the ROI group compared with the non-ROI cohort (<em>P</em> = .002).</div></div><div><h3>Conclusion</h3><div>Adding multiparametric MRI (mpMRI) biopsy to standard TRUS biopsy may increase the detection of PCa. Additionally, mpMRI may allow patients to remain safely on AS, thereby reducing the need of prostate biopsies and improving cost-effectiveness.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"14 ","pages":"Article 100642"},"PeriodicalIF":1.8,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143563569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}