European Radiology最新文献

{"title":"Machine-learning model based on ultrasomics for non-invasive evaluation of fibrosis in IgA nephropathy.","authors":"Qun Huang, Fangyi Huang, Chengcai Chen, Pan Xiao, Jiali Liu, Yong Gao","doi":"10.1007/s00330-025-11368-9","DOIUrl":"10.1007/s00330-025-11368-9","url":null,"abstract":"<p><strong>Objectives: </strong>To develop and validate an ultrasomics-based machine-learning (ML) model for non-invasive assessment of interstitial fibrosis and tubular atrophy (IF/TA) in patients with IgA nephropathy (IgAN).</p><p><strong>Materials and methods: </strong>In this multi-center retrospective study, 471 patients with primary IgA nephropathy from four institutions were included (training, n = 275; internal testing, n = 69; external testing, n = 127; respectively). The least absolute shrinkage and selection operator logistic regression with tenfold cross-validation was used to identify the most relevant features. The ML models were constructed based on ultrasomics. The Shapley Additive Explanation (SHAP) was used to explore the interpretability of the models. Logistic regression analysis was employed to combine ultrasomics, clinical data, and ultrasound imaging characteristics, creating a comprehensive model. A receiver operating characteristic curve, calibration, decision curve, and clinical impact curve were used to evaluate prediction performance.</p><p><strong>Results: </strong>To differentiate between mild and moderate-to-severe IF/TA, three prediction models were developed: the Rad_SVM_Model, Clinic_LR_Model, and Rad_Clinic_Model. The area under curves of these three models were 0.861, 0.884, and 0.913 in the training cohort, and 0.760, 0.860, and 0.894 in the internal validation cohort, as well as 0.794, 0.865, and 0.904 in the external validation cohort. SHAP identified the contribution of radiomics features. Difference analysis showed that there were significant differences between radiomics features and fibrosis. The comprehensive model was superior to that of individual indicators and performed well.</p><p><strong>Conclusions: </strong>We developed and validated a model that combined ultrasomics, clinical data, and clinical ultrasonic characteristics based on ML to assess the extent of fibrosis in IgAN.</p><p><strong>Key points: </strong>Question Currently, there is a lack of a comprehensive ultrasomics-based machine-learning model for non-invasive assessment of the extent of Immunoglobulin A nephropathy (IgAN) fibrosis. Findings We have developed and validated a robust and interpretable machine-learning model based on ultrasomics for assessing the degree of fibrosis in IgAN. Clinical relevance The machine-learning model developed in this study has significant interpretable clinical relevance. The ultrasomics-based comprehensive model had the potential for non-invasive assessment of fibrosis in IgAN, which helped evaluate disease progress.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"3707-3720"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143032722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Refining the need for prostate biopsy and the evolving role of MRI.","authors":"Anwar R Padhani, Sungmin Woo","doi":"10.1007/s00330-024-11322-1","DOIUrl":"10.1007/s00330-024-11322-1","url":null,"abstract":"","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"4013-4015"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142863787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Generalizability, robustness, and correction bias of segmentations of thoracic organs at risk in CT images.","authors":"Corentin Guérendel, Liliana Petrychenko, Kalina Chupetlovska, Zuhir Bodalal, Regina G H Beets-Tan, Sean Benson","doi":"10.1007/s00330-024-11321-2","DOIUrl":"10.1007/s00330-024-11321-2","url":null,"abstract":"<p><strong>Objective: </strong>This study aims to assess and compare two state-of-the-art deep learning approaches for segmenting four thoracic organs at risk (OAR)-the esophagus, trachea, heart, and aorta-in CT images in the context of radiotherapy planning.</p><p><strong>Materials and methods: </strong>We compare a multi-organ segmentation approach and the fusion of multiple single-organ models, each dedicated to one OAR. All were trained using nnU-Net with the default parameters and the full-resolution configuration. We evaluate their robustness with adversarial perturbations, and their generalizability on external datasets, and explore potential biases introduced by expert corrections compared to fully manual delineations.</p><p><strong>Results: </strong>The two approaches show excellent performance with an average Dice score of 0.928 for the multi-class setting and 0.930 when fusing the four single-organ models. The evaluation of external datasets and common procedural adversarial noise demonstrates the good generalizability of these models. In addition, expert corrections of both models show significant bias to the original automated segmentation. The average Dice score between the two corrections is 0.93, ranging from 0.88 for the trachea to 0.98 for the heart.</p><p><strong>Conclusion: </strong>Both approaches demonstrate excellent performance and generalizability in segmenting four thoracic OARs, potentially improving efficiency in radiotherapy planning. However, the multi-organ setting proves advantageous for its efficiency, requiring less training time and fewer resources, making it a preferable choice for this task. Moreover, corrections of AI segmentation by clinicians may lead to biases in the results of AI approaches. A test set, manually annotated, should be used to assess the performance of such methods.</p><p><strong>Key points: </strong>Question While manual delineation of thoracic organs at risk is labor-intensive, prone to errors, and time-consuming, evaluation of AI models performing this task lacks robustness. Findings The deep-learning model using the nnU-Net framework showed excellent performance, generalizability, and robustness in segmenting thoracic organs in CT, enhancing radiotherapy planning efficiency. Clinical relevance Automatic segmentation of thoracic organs at risk can save clinicians time without compromising the quality of the delineations, and extensive evaluation across diverse settings demonstrates the potential of integrating such models into clinical practice.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"4335-4346"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142908849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"External validation of a CT score for predicting ischaemia in adhesive small-bowel obstruction.","authors":"Valentin Vadot, Adeline Guiraud, Amadou Kalilou Sow, Isabelle Fournel, Gabriel Simon, Adrien Acquier, Ségolène Mvouama, Olivier Chevallier, Pablo Ortega-Deballon, Romaric Loffroy","doi":"10.1007/s00330-025-11362-1","DOIUrl":"10.1007/s00330-025-11362-1","url":null,"abstract":"<p><strong>Objectives: </strong>To assess the diagnostic accuracy, in a validation cohort, of a score based on three CT items, which has shown good performance for predicting ischaemia complicating acute adhesive small-bowel obstruction (SBO).</p><p><strong>Methods: </strong>This retrospective single-centre study of diagnostic accuracy included consecutive patients admitted for acute adhesive SBO in 2015-2022, who were treated conservatively or underwent surgery within 24 h after CT. The gold standard for ischaemia was an intraoperative diagnosis for operated patients, while the absence of ischaemia was confirmed either by its absence during surgery or by clinical follow-up in patients who did not undergo surgery. Three radiologists independently assessed the three score items, namely, decreased bowel-wall enhancement, diffuse mesenteric haziness, and closed-loop mechanism. Inter-observer agreement was evaluated by computing Fleiss' kappa. The diagnostic performance characteristics of the score were computed.</p><p><strong>Results: </strong>Of the 164 patients analysed (median age, 70 [57-80] years; 88 [54%] males), 57 (34.8%) had surgery, including 41 (71.9%) with intra-operative evidence of bowel ischaemia, whereas 107 (65.2%) were treated conservatively. A score ≥ 2/3 had a sensitivity of 78% (95% CI: 62-89%), a specificity of 97% (95% CI: 92-99%), a positive predictive value of 89% (95% CI: 74-97%), and a positive likelihood ratio of 24 (95% CI: 9.03-63.79). Adding increased unenhanced bowel-wall attenuation and requiring ≥ 2/4 items did not improve score performance. Fleiss' kappa values indicated moderate to substantial agreement between observers: 0.64 [0.56-0.73] for decreased bowel-wall enhancement, 0.57 [0.48-0.66] for diffuse mesenteric haziness, and 0.68 [0.59-0.76] for closed-loop mechanism.</p><p><strong>Conclusions: </strong>The results of this external validation study support the reproducibility and good diagnostic performance of the score based on three CT items for predicting bowel ischaemia complicating acute adhesive SBO.</p><p><strong>Key points: </strong>Question The Millet score with three enhanced CT items for predicting bowel ischaemia complicating acute adhesive SBO has not been assessed in an external validation cohort. Findings Adding \"increased unenhanced bowel-wall attenuation\" to the \"decreased bowel-wall enhancement\", \"diffuse mesenteric haziness\", and \"closed-loop mechanism\" items did not improve score performance. Clinical relevance In an external validation cohort, a score based on three CT items performed well for predicting ischaemia in patients with acute adhesive SBO and showed acceptable inter-observer agreement. This score may help identify patients for surgery.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"4203-4212"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143032716","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of immunotherapy response in nasopharyngeal carcinoma: a comparative study using MRI-based radiomics signature and programmed cell death ligand 1 expression score.","authors":"Hui Mai, Li Li, Xin Xin, Zhike Jiang, Yongfang Tang, Jie Huang, Yanxing Lei, Lianzhi Chen, Tianfa Dong, Xi Zhong","doi":"10.1007/s00330-025-11350-5","DOIUrl":"10.1007/s00330-025-11350-5","url":null,"abstract":"<p><strong>Objectives: </strong>To compare an MRI-based radiomics signature with the programmed cell death ligand 1 (PD-L1) expression score for predicting immunotherapy response in nasopharyngeal carcinoma (NPC).</p><p><strong>Methods: </strong>Consecutive patients with NPC who received immunotherapy between January 2019 and June 2022 were divided into training (n = 111) and validation (n = 66) sets. Tumor radiomics features were extracted from pretreatment MR images. PD-L1 combined positive score (CPS) was calculated using immunohistochemistry. The least absolute shrinkage and selection operator (LASSO) algorithm was used for feature selection and radiomics signature construction. Receiver operating characteristic (ROC) curve analysis was performed to assess prediction performance.</p><p><strong>Results: </strong>A total of eleven radiomics features with the greatest discrimination capability were identified by the LASSO algorithm to construct the radiomics signature. In predicting patients with objective response to immunotherapy, radiomics score (Rd-score) yielded a significantly higher area under the ROC curve than that of CPS in both the training (0.790 vs. 0.645, p = 0.025) and the validation (0.735 vs. 0.608, p = 0.038) sets. Multivariate analysis identified the Rd-score as an independent influencing factor in predicting immunotherapy response (odds ratio = 19.963, p < 0.001). Kaplan-Meier analysis indicated that patients with Rd-score ≥ 0.5 showed longer progression-free survival than patients with Rd-score < 0.5 (log-rank p < 0.01).</p><p><strong>Conclusion: </strong>An MRI-based radiomics signature demonstrated greater efficacy than the PD-L1 expression score in predicting immunotherapy response in patients with NPC.</p><p><strong>Key points: </strong>Question How does an MRI-based radiomics signature compare with the programmed cell death ligand 1 expression score for predicting immunotherapy response in nasopharyngeal carcinoma? Findings The MRI-based radiomics signature demonstrated superior predictive value compared with programmed cell death ligand 1 expression score in identifying immunotherapy responders. Clinical relevance MRI-based radiomics are a promising novel noninvasive tool for predicting immunotherapy outcomes in nasopharyngeal carcinoma.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"4403-4414"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143032730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multicenter study of thermal ablation versus partial thyroidectomy for paratracheal papillary thyroid microcarcinoma.","authors":"Haoyu Jing, Zixin Wang, Lin Yan, Jing Xiao, Xinyang Li, Zhen Yang, Mingbo Zhang, Hui Wang, Yujiang Liu, Yukun Luo","doi":"10.1007/s00330-024-11326-x","DOIUrl":"10.1007/s00330-024-11326-x","url":null,"abstract":"<p><strong>Objective: </strong>To compare the clinical outcomes of patients with unifocal paratracheal papillary thyroid microcarcinoma (PTMC) after thermal ablation (TA) vs. partial thyroidectomy (PT).</p><p><strong>Materials and methods: </strong>This retrospective multicenter study included 436 patients with unifocal, clinical N0 paratracheal PTMC who underwent TA (210 patients) or PT (236 patients) between June 2014 and December 2020. The propensity score matching method was used to mitigate confounding factors between the two groups. Disease progression, progression-free survival (PFS), complications, and treatment variables were compared. Adjusted Cox regression models were utilized to assess the impact of treatment on disease progression.</p><p><strong>Results: </strong>After matching, a comparable incidence of disease progression (3.3% vs. 2.2%, p = 0.79) and comparable 5-year PFS rates (97.0% vs. 97.4%, p = 0.75) were observed between the TA and PT groups. Adjusted Cox regression models showed no significant correlation between TA and disease progression. TA was associated with shorter hospitalization (0 vs. 6.0 days), less estimated blood loss (0 vs. 15.0 mL), shorter incision length (0.3 vs. 6.0 cm), and lower costs ($1748.3 vs. $2898.0) compared with PT (all p < 0.001). The complication rate was 1.1% after TA and 3.3% after PT (p = 0.28), with permanent complications were exclusively observed in the PT group.</p><p><strong>Conclusion: </strong>The mid-term incidence of disease progression and PFS rates were similar between TA and PT in patients with unifocal paratracheal PTMC. TA might represent a promising alternative treatment to PT for eligible patients with paratracheal PTMC.</p><p><strong>Key points: </strong>Question Is thermal ablation a viable alternative treatment to partial thyroidectomy for treating paratracheal papillary thyroid microcarcinoma? Findings Comparable incidence of disease progression and 5-year progression-free survival rates were observed between thermal ablation and partial thyroidectomy. Clinical relevance Thermal ablation, as a minimally invasive procedure, provides a promising alternative to partial thyroidectomy, with comparable clinical outcomes for patients with paratracheal papillary thyroid microcarcinoma.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"4152-4160"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143002525","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Visual rating of brain atrophy in structural MRI: Is its time over?","authors":"Ralph Buchert","doi":"10.1007/s00330-025-11424-4","DOIUrl":"10.1007/s00330-025-11424-4","url":null,"abstract":"","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"4243-4245"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12165996/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143370659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Malignancy risk stratification for pulmonary nodules: comparing a deep learning approach to multiparametric statistical models in different disease groups.","authors":"Lars Piskorski, Manuel Debic, Oyunbileg von Stackelberg, Kai Schlamp, Linn Welzel, Oliver Weinheimer, Alan Arthur Peters, Mark Oliver Wielpütz, Thomas Frauenfelder, Hans-Ulrich Kauczor, Claus Peter Heußel, Jonas Kroschke","doi":"10.1007/s00330-024-11256-8","DOIUrl":"10.1007/s00330-024-11256-8","url":null,"abstract":"<p><strong>Objectives: </strong>Incidentally detected pulmonary nodules present a challenge in clinical routine with demand for reliable support systems for risk classification. We aimed to evaluate the performance of the lung-cancer-prediction-convolutional-neural-network (LCP-CNN), a deep learning-based approach, in comparison to multiparametric statistical methods (Brock model and Lung-RADS®) for risk classification of nodules in cohorts with different risk profiles and underlying pulmonary diseases.</p><p><strong>Materials and methods: </strong>Retrospective analysis was conducted on non-contrast and contrast-enhanced CT scans containing pulmonary nodules measuring 5-30 mm. Ground truth was defined by histology or follow-up stability. The final analysis was performed on 297 patients with 422 eligible nodules, of which 105 nodules were malignant. Classification performance of the LCP-CNN, Brock model, and Lung-RADS® was evaluated in terms of diagnostic accuracy measurements including ROC-analysis for different subcohorts (total, screening, emphysema, and interstitial lung disease).</p><p><strong>Results: </strong>LCP-CNN demonstrated superior performance compared to the Brock model in total and screening cohorts (AUC 0.92 (95% CI: 0.89-0.94) and 0.93 (95% CI: 0.89-0.96)). Superior sensitivity of LCP-CNN was demonstrated compared to the Brock model and Lung-RADS® in total, screening, and emphysema cohorts for a risk threshold of 5%. Superior sensitivity of LCP-CNN was also shown across all disease groups compared to the Brock model at a threshold of 65%, compared to Lung-RADS® sensitivity was better or equal. No significant differences in the performance of LCP-CNN were found between subcohorts.</p><p><strong>Conclusion: </strong>This study offers further evidence of the potential to integrate deep learning-based decision support systems into pulmonary nodule classification workflows, irrespective of the individual patient risk profile and underlying pulmonary disease.</p><p><strong>Key points: </strong>Question Is a deep-learning approach (LCP-CNN) superior to multiparametric models (Brock model, Lung-RADS®) in classifying pulmonary nodule risk across varied patient profiles? Findings LCP-CNN shows superior performance in risk classification of pulmonary nodules compared to multiparametric models with no significant impact on risk profiles and structural pulmonary diseases. Clinical relevance LCP-CNN offers efficiency and accuracy, addressing limitations of traditional models, such as variations in manual measurements or lack of patient data, while producing robust results. Such approaches may therefore impact clinical work by complementing or even replacing current approaches.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"3812-3822"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12165889/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142921035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MRI-specific signature of dementia with Lewy bodies-a step towards improved differential diagnosis of the dementia spectrum.","authors":"Maria Marcella Laganà, Dejan Jakimovski","doi":"10.1007/s00330-025-11534-z","DOIUrl":"10.1007/s00330-025-11534-z","url":null,"abstract":"","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"3750-3752"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143742741","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MRI-based microvascular invasion prediction in mass-forming intrahepatic cholangiocarcinoma: survival and therapeutic benefit.","authors":"Ruofan Sheng, Beixuan Zheng, Yunfei Zhang, Wei Sun, Chun Yang, Jing Han, Mengsu Zeng, Jianjun Zhou","doi":"10.1007/s00330-024-11296-0","DOIUrl":"10.1007/s00330-024-11296-0","url":null,"abstract":"<p><strong>Objectives: </strong>To establish an MRI-based model for microvascular invasion (MVI) prediction in mass-forming intrahepatic cholangiocarcinoma (MF-iCCA) and further evaluate its potential survival and therapeutic benefit.</p><p><strong>Methods: </strong>One hundred and fifty-six pathologically confirmed MF-iCCAs with traditional surgery (121 in training and 35 in validation cohorts), 33 with neoadjuvant treatment and 57 with first-line systemic therapy were retrospectively included. Univariate and multivariate regression analyses were performed to identify the independent predictors for MVI in the traditional surgery group, and an MVI-predictive model was constructed. Survival analyses were conducted and compared between MRI-predicted MVI-positive and MVI-negative MF-iCCAs in different treatment groups.</p><p><strong>Results: </strong>Tumor multinodularity (odds ratio = 4.498, p < 0.001) and peri-tumor diffusion-weighted hyperintensity (odds ratio = 4.163, p < 0.001) were independently significant variables associated with MVI. AUC values for the predictive model were 0.760 [95% CI 0.674, 0.833] in the training cohort and 0.757 [95% CI 0.583, 0.885] in the validation cohort. Recurrence-free survival or progression-free survival of the MRI-predicted MVI-positive patients was significantly shorter than the MVI-negative patients in all three treatment groups (log-rank p < 0.001 to 0.046). The use of neoadjuvant therapy was not associated with improved postoperative recurrence-free survival for high-risk MF-iCCA patients in both MRI-predicted MVI-positive and MVI-negative groups (log-rank p = 0.79 and 0.27). Advanced MF-iCCA patients of the MRI-predicted MVI-positive group had significantly worse objective response rate than the MVI-negative group with systemic therapy (40.91% vs 76.92%, χ² = 5.208, p = 0.022).</p><p><strong>Conclusion: </strong>The MRI-based MVI-predictive model could be a potential biomarker for personalized risk stratification and survival prediction in MF-iCCA patients with varied therapies and may aid in candidate selection for systemic therapy.</p><p><strong>Key points: </strong>Question Identifying intrahepatic cholangiocarcinoma (iCCA) patients at high risk for microvascular invasion (MVI) may inform prognostic risk stratification and guide clinical treatment decision. Findings We established an MRI-based predictive model for MVI in mass-forming-iCCA, integrating imaging features of tumor multinodularity and peri-tumor diffusion-weighted hyperintensity. Clinical relevance The MRI-based MVI-predictive model could be a potential biomarker for personalized risk stratification and survival prediction across varied therapies and may aid in therapeutic candidate selection for systemic therapy.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"4068-4079"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142853601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}