British Journal of Radiology最新文献

{"title":"Harnessing Intrinsic Cardiac Motion vs. External Mechanical Vibrations: A Comparison of MRI Cine-Tagging and MR Elastography for Liver Fibrosis Assessment.","authors":"Thierry L Lefebvre, Anton Volniansky, Léonie Petitclerc, Emmanuel Montagnon, Giada Sebastiani, Jeanne-Marie Giard, Marie-Pierre Sylvestre, Bich Ngoc Nguyen, Guillaume Gilbert, Guy Cloutier, An Tang","doi":"10.1093/bjr/tqaf256","DOIUrl":"https://doi.org/10.1093/bjr/tqaf256","url":null,"abstract":"<p><strong>Objective: </strong>This study aims to assess and compare the diagnostic accuracy of MRI cine-tagging and magnetic resonance elastography (MRE) for staging histologically confirmed liver fibrosis in patients with chronic liver disease.</p><p><strong>Methods: </strong>MRI cine-tagging evaluates liver strain as the deformation induced by intrinsic cardiac motion on the left liver lobe, whereas MRE captures liver stiffness in response to externally applied vibrations from a mechanical driver. A head-to-head comparison of MRI cine-tagging and MRE was performed in 76 participants with biopsy-proven chronic liver disease. Spearman's rank correlation coefficients and areas under the receiver operating characteristic curve (AUC) were assessed. AUCs were compared using the Delong method.</p><p><strong>Results: </strong>MRE-derived shear modulus increased, while strain obtained from tagged cine MRI decreased with higher fibrosis stages (ρ = 0.73 and ρ=-0.67, respectively; P < 0.0001). Both shear modulus and strain values exhibited significant differences across fibrosis stages (P < 0.0001) and correlated with each other (ρ=-0.44, P < 0.0001). MRE provided higher AUCs than MRI cine-tagging only for distinguishing stages ≤F3 vs. F4 (0.91 vs. 0.87, P = 0.043). There were no significant differences in AUCs for differentiating other dichotomized fibrosis stages, including stages F0 vs. ≥F1 (0.87 vs. 0.81, P = 0.083), ≤F1 vs. ≥F2 (0.84 vs. 0.84, P = 0.889), and ≤F2 vs. ≥F3 (0.89 vs. 0.86, P = 0.116).</p><p><strong>Conclusion: </strong>MRI cine-tagging provided a similar diagnostic performance compared to MRE for staging liver fibrosis, except for the diagnosis of cirrhosis (F4). It is possible to assess liver strain as part of abdominal MRI screening, offering additional insight into the left lobe without the need for additional equipment.</p><p><strong>Advances in knowledge: </strong>A head-to-head comparison of magnetic resonance elastography (MRE), the most accurate technique for the noninvasive staging of liver fibrosis, and MRI cine-tagging has not been performed yet. We found that MRI cine-tagging, having the advantage of not requiring any additional hardware, provides a similar diagnostic performance compared to MRE for staging liver fibrosis, except for the diagnosis of cirrhosis in patients with chronic liver disease.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145279011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnostic ability of spectral CT-based vertebral hydroxyapatite concentration for bone mineral density assessment in patients with liver cirrhosis: evaluating in unenhanced, arterial, and portal venous phase after intravenous contrast administration.","authors":"Xiaoyue Cheng, Qiang Ma, Xinmeng Hou, Chenglin Zhao, Yuanyuan Yan, Jianying Li, Zhenghan Yang","doi":"10.1093/bjr/tqaf250","DOIUrl":"https://doi.org/10.1093/bjr/tqaf250","url":null,"abstract":"<p><strong>Objectives: </strong>To access the impact of intravenous contrast on the diagnostic efficacy of abdominal spectral CT-based vertebral hydroxyapatite (HAP) concentration measurement for bone mineral density (BMD) assessment in menopausal women, women undergoing menopausal transition, and men older than 50 years with liver cirrhosis.</p><p><strong>Methods: </strong>172 patients (mean age, 63.78 ± 7.20 years; range, 51-82 years) with liver cirrhosis enrolled in the study. These individuals underwent comprehensive abdominal spectral abdominal spectral CT scans, which included both unenhanced and contrast-enhanced arterial phase (AP) and portal venous phase (VP). Vertebral HAP concentration was quantified in the medullary compartment of vertebral body (L1-L3) using HAP-based material decomposition images. The receiver operating characteristic (ROC) curves were adapted to investigate the diagnostic efficacy of using unenhanced, AP and VP HAP concentrations for evaluating BMD validated by T-scores on dual-energy x-ray absorptiometry.</p><p><strong>Results: </strong>HAP values were significantly different among the three scan phases (all P < 0.05). By adjusting thresholds, high accuracies were obtained for detecting low bone mass (osteoporosis or osteopenia) with HAP measurements in all scan phases (all areas-under-ROC > 0.9). The data did not reveal a statistically significant disparity between the unenhanced and AP (P = 0.055) to detect low bone mass. The efficacies for detecting low bone mass had statistically significant reduction with HAP concentrations in VP (P = 0.012).</p><p><strong>Conclusions: </strong>Vertebral HAP concentrations increased in AP and VP compared to unenhanced phase.</p><p><strong>Advances in knowledge: </strong>Adjusting thresholds higher in contrast-enhanced phases may maintain high detection efficacies for low bone mass.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145278983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Relationship between radiation exposure and indicators of vascular resistance, arterial remodeling, and atherosclerosis.","authors":"Nobuo Sasaki, Yoshitaka Ueno, Seiko Hirota, Shinji Kishimoto, Ryoji Ozono, Yukiko Nakano, Shinji Yoshinaga, Yukihito Higashi","doi":"10.1093/bjr/tqaf252","DOIUrl":"https://doi.org/10.1093/bjr/tqaf252","url":null,"abstract":"<p><strong>Objectives: </strong>The diameter, resistance index (RI), and plaque formation in the common carotid artery (CCA) are indicators of arterial remodeling, vascular resistance, and atherosclerosis, respectively. This study used CCA parameters to investigate the longitudinal relationship between radiation exposure and vascular damage.</p><p><strong>Methods: </strong>This retrospective cohort analysis included 806 atomic bomb survivors with estimated radiation doses from the Hiroshima atomic bomb survivor study database, who underwent carotid artery ultrasonography between April 2003 and December 2021. Participants were divided into three groups based on their radiation doses: <0.3 Gy, 0.3-3 Gy, and >3 Gy. The highest quartile of each index was defined as having a large CCA diameter, a high RI, increased plaque number, and a greater maximum plaque thickness.</p><p><strong>Results: </strong>The median time between radiation exposure and carotid artery ultrasonography was 68.3 years. In the <0.3 and >3 Gy groups, the proportions of large CCA diameter were 24.2% and 50.0%, and the proportions of high RI were 23.5% and 54.6%, respectively. In multivariate analysis, the >3 Gy group had significantly larger CCA diameter (odds ratio [OR]: 4.36, 95% confidence interval [CI]: 1.30-14.7) and higher RI (OR: 4.04, 95% CI: 1.14-14.3) than the <0.3 Gy group. The plaque number or maximum plaque thickness did not differ significantly among the three-radiation dose groups.</p><p><strong>Conclusions: </strong>Radiation exposure may affect vascular resistance and remodeling.</p><p><strong>Advances in knowledge: </strong>To assess the risk of cardiovascular disease in radiation-exposed individuals, it appears necessary to investigate the effects of vascular damage other than atherosclerosis.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145273828","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Arterial embolization using cyanoacrylates in renal haemorrhage with no coagulopathy: What can do more can do less!","authors":"Romaric Loffroy","doi":"10.1093/bjr/tqaf251","DOIUrl":"https://doi.org/10.1093/bjr/tqaf251","url":null,"abstract":"","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145273836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Characterizing chronic obstructive pulmonary disease using quantitative MRI biomarkers.","authors":"Daniel Genkin, Kalysta Makimoto, Miranda Kirby","doi":"10.1093/bjr/tqaf249","DOIUrl":"https://doi.org/10.1093/bjr/tqaf249","url":null,"abstract":"<p><p>Chronic obstructive pulmonary disease (COPD) is a heterogeneous lung disease that occurs due to structural changes to the parenchyma, airways and pulmonary vasculature, and consequent functional impairments to ventilation and perfusion. Although computed tomography (CT) imaging is the standard for assessing structural lung changes in COPD, it requires ionizing radiation and is unable to provide functional information without contrast agents. Conversely, there have been numerous developments for magnetic resonance imaging (MRI) of the lungs in the last several decades, allowing for the quantification of structural and functional abnormalities without ionizing radiation. Various quantitative MR (qMR) imaging biomarkers have been developed that describe parenchymal and airway structure as well as ventilation and perfusion within the lungs. These qMR imaging biomarkers have been investigated in individuals with COPD, reporting both cross-sectional and longitudinal associations with important outcomes. Therefore, the aim of this article is to briefly review some commonly used MRI techniques that have been investigated for lung imaging and discuss commonly implemented qMR imaging biomarkers and their application in COPD. Additionally, this review will focus on gaps in the literature that should be addressed to allow for future widespread implementation of qMR imaging biomarkers in COPD-related research.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145273811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Radiomics-based explainable artificial intelligence to predict treatment response following lung stereotactic body radiation therapy.","authors":"Savino Cilla, Carmela Romano, Gabriella Macchia, Donato Pezzulla, Elisabetta Lepre, Milly Buwenge, Costanza Maria Donati, Erika Galietta, Alessio Giuseppe Morganti, Francesco Deodato","doi":"10.1093/bjr/tqaf043","DOIUrl":"https://doi.org/10.1093/bjr/tqaf043","url":null,"abstract":"<p><strong>Objective: </strong>To develop and validate a CT-based radiomic-clinical-dosimetric model to assess the treatment response of lung metastasis following stereotactic body radiation therapy (SBRT).</p><p><strong>Methods: </strong>80 lung metastases treated with SBRT curative intent in a single institution were analyzed. The treatment responses of lung lesions were categorized as a complete responding (CR) group vs. a non-complete responding (NCR) group according to RECIST criteria. For each lesion, 107 features were extracted from the CT planning images. The least absolute shrinkage and selection operator (LASSO) was used for features selection. An eXtreme Gradient Boosting (XGBoost) model was trained and validated. SHAP analysis was used to provide insights into the impact of each variable on the model's predictions.</p><p><strong>Results: </strong>Eight radiomic features, one dosimetric variable and no clinical variables were identified by LASSO and used to build the XGBoost model. The model yielded AUCs of 0.897 (95%CI 0.860-0.935) and 0.864 (95%CI 0.803-0.924) in the training cohort and validation cohort, respectively. Skewness, surface-volume ratio, sphericity and BED10 were the most significant variables in predicting CR. The SHAP plots illustrated the feature's global and local impact to the model, explaining the model output in a clinician-friendly way.</p><p><strong>Conclusion: </strong>The integration of the XGBoost model with the SHAP strategy was able to assess lung lesions CR following SBRT, with the potential to assist clinicians in directing personalized SBRT strategies in an understandable manner.</p><p><strong>Advances in knowledge: </strong>The explanaible radiomics model we propose can better predict the treatment response of lung metastasis after SBRT and provide further guidance for clinical practice.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145273889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Non-invasive prediction of Central lymph node metastasis in papillary thyroid microcarcinoma with machine learning-based CT radiomics: a multicenter study.","authors":"Feng Cheng, Guihan Lin, Weiyue Chen, Yongjun Chen, Rongzhen Zhou, Jing Yang, Bin Zhou, Minjiang Chen, Jiansong Ji","doi":"10.1093/bjr/tqaf247","DOIUrl":"https://doi.org/10.1093/bjr/tqaf247","url":null,"abstract":"<p><strong>Objectives: </strong>This study aimed to develop and validate a machine learning-based computed tomography (CT) radiomics method to preoperatively predict the presence of central lymph node metastasis (CLNM) in patients with papillary thyroid microcarcinoma (PTMC).</p><p><strong>Methods: </strong>A total of 921 patients with histopathologically proven PTMC from three medical centers were included in this retrospective study and divided into training, internal validation, external test 1, and external test 2 sets. Radiomics features of thyroid tumors were extracted from CT images and selected for dimensional reduction. Five machine learning classifiers were applied, and the best classifier was selected to calculate radiomics scores (rad-scores). Then, the rad-scores and clinical factors were combined to construct a nomogram model.</p><p><strong>Results: </strong>In the four sets, 35.18% (324/921) patients were CLNM+. The XGBoost classifier showed the best performance, with the highest average area under the curve (AUC) of 0.756 in the validation set. The nomogram model incorporating XGBoost-based rad-scores with age and sex showed better performance than the clinical model in the training [AUC: 0.847(0.809-0.879) vs. 0.706(0.660-0.748)], internal validation [AUC: 0.773(0.682-0.847) vs. 0.671(0.575-0.758)], external test 1 [AUC: 0.807(0.757-0.852) vs. 0.639(0.580-0.695)], and external test 2 [AUC: 0.746(0.645-0.830) vs. 0.608(0.502-0.707)] sets. Furthermore, the nomogram showed better clinical benefit than the clinical and radiomics models.</p><p><strong>Conclusions: </strong>The nomogram model based on the XGBoost classifier exhibited favorable performance. This model provides a potential approach for the non-invasive diagnosis of CLNM in patients with PTMC.</p><p><strong>Advances in knowledge: </strong>This study developed a potential surrogate of preoperative accurate evaluation of CLNM status, which is non-invasive and easy-to-use.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145249855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-parametric MRI Radiomics models for preoperative assessment of lymph vascular space invasion status in early-stage cervical cancer: A two-center retrospective study.","authors":"Lei Deng, Rui Zhang, Huabing Lv, Feng Li, Lin Li, Xiaomin Qin, Jiang Yang, Tao Ai, Chencui Huang, Xingzhi Chen, Hui Xing, Feng Wu","doi":"10.1093/bjr/tqaf248","DOIUrl":"https://doi.org/10.1093/bjr/tqaf248","url":null,"abstract":"<p><strong>Objective: </strong>To preoperatively predict lymphovascular space invasion (LVSI) in early-stage cervical cancer (CC) using multi-parametric MRI (mpMRI) radiomics models.</p><p><strong>Methods: </strong>This dual-center study included 196 early-stage CC patients (Center A: 142, Dec2020-Apr2023; Center B: 54, May-Oct2023). Center A was partitioned into training (n = 99) and internal validation (n = 43) cohorts; Center B served as external validation. Radiomics features were extracted from T2WI, DWI, and CE-MRI sequences. Feature stability was assessed via intra-class correlation and Dice coefficient, with selection through linear correlation and F-tests. Seven radiomics models (single/combined sequences) were built using the top-performing algorithm among eleven machine learning methods. A combination model (CMIC) integrated the optimal mpMRI model's rad-score with clinical factors. Performance was evaluated by ROC, calibration curves, and DCA across all cohorts.</p><p><strong>Results: </strong>The AdaBoost-based mpMRI model (CE-MRI+DWI+T2WI) utilized 12 selected features. It achieved AUCs of 0.953 (95% CI : 0.916-0.989) in training, 0.868 (0.755-0.981) in internal validation, and 0.797 (0.677-0.916) externally. The CMIC model showed comparable performance (training: 0.957; validation: 0.864; external: 0.847), with no significant differences versus the mpMRI model (p > 0.05 all cohorts).</p><p><strong>Conclusion: </strong>The AdaBoost-driven mpMRI radiomics model effectively predicts LVSI in early-stage CC. Both mpMRI and CMIC models demonstrate robust preoperative predictive capability.</p><p><strong>Advances in knowledge: </strong>This mpMRI radiomics approach using AdaBoost outperforms single-sequence models for LVSI prediction, enabling personalized treatment strategies for early-stage CC.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145243781","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correlation between Clinical Diagnosis of Pelvic Organ Prolapse via Pelvic Floor Ultrasound and Quantitative Staging Method: A Clinical Study.","authors":"Xiaoming Li, Juan Yan","doi":"10.1093/bjr/tqaf246","DOIUrl":"https://doi.org/10.1093/bjr/tqaf246","url":null,"abstract":"<p><strong>Objectives: </strong>To validate the diagnostic accuracy of pelvic floor ultrasound (PFUS) for pelvic organ prolapse (POP) and its correlation with the Pelvic Organ Prolapse Quantification (POP-Q) staging system by performing a rigorous quantitative comparison of anatomical measurements between women with POP and asymptomatic controls.</p><p><strong>Methods: </strong>In this prospective observational study, 80 women with clinically confirmed POP and 60 asymptomatic controls underwent standardized PFUS and POP-Q examinations. PFUS was utilized to measure bladder, uterine, and rectal positions during maximal Valsalva maneuver. POP-Q staging was conducted by two blinded urogynecologists (inter-rater reliability κ = 0.87). Statistical analyses included Spearman's correlation (ρ), diagnostic performance metrics (sensitivity, specificity, accuracy), and group comparisons using t-tests or chi-square tests.</p><p><strong>Results: </strong>The POP group exhibited significant organ descent versus controls, including mean bladder descent (4.5 ± 1.2 cm vs. 1.8 ± 0.3 cm; P = 0.004) and uterine descent (5.2 ± 1.4 cm vs. 2.05 ± 0.40 cm; P = 0.012). PFUS measurements demonstrated strong correlation with POP-Q stages (compartment-specific ρ = 0.87-0.91). Overall agreement was 90.0% (ρ = 0.92, P < 0.001), with high diagnostic accuracy (93.5%), sensitivity (>90%), and specificity (>96%).</p><p><strong>Conclusions: </strong>PFUS is a reliable, non-invasive method to quantify pelvic organ displacement, showing excellent agreement with the clinical standard POP-Q system. Its high diagnostic performance supports its integration into clinical practice for objective diagnosis, severity grading, and comprehensive anatomical characterization of POP.</p><p><strong>Advances in knowledge: </strong>This study provides robust evidence validating PFUS as a reproducible objective tool for POP assessment.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145243802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Differentiation of malignant from benign focal liver lesions in triphase-enhanced CT using machine-learning-based radiomics.","authors":"Lingyun Wang, Zhihan Xu, Lu Zhang, Keke Zhao, Hongcheng Sun, Zhijie Pan, Qingyao Li, Yaping Zhang, Xueqian Xie","doi":"10.1093/bjr/tqaf138","DOIUrl":"10.1093/bjr/tqaf138","url":null,"abstract":"<p><strong>Objectives: </strong>Triphasic enhanced CT provides more information about blood supply. The aim was to establish a radiomics model of triphasic-enhanced CT to differentiate malignant from benign focal liver lesions (FLLs).</p><p><strong>Methods: </strong>Patients with FLLs who underwent triphasic enhanced CT with histopathological results were retrospectively included. We extracted the radiomic features of each lesion in arterial phase (AP), portal vein phase (PVP), delayed phase (DP), slope of AP to PVP, and slope of PVP to DP. The features that best discriminated malignant from benign FLLs were selected using the Boruta algorithm and random forest algorithm and combined to create a radiomic signature. Three radiologists independently graded the Liver Imaging Reporting and Data System category.</p><p><strong>Results: </strong>Of the 322 FLLs, the training, validation and test cohorts consisted of 160 (122 malignant, 76.3%), 83 (63 malignant, 75.9%), and 79 (63 malignant, 79.7%) lesions. The three observers classified 235, 169, and 220 as malignant, respectively. In the test cohort, the area under the curve of the radiomic signature in identifying malignant FLLs was 0.896 (0.850-0.973), lower than 0.935 (0.873-0.996) (P = .463) of the senior radiologist, but higher than 0.812 (0.713-0.910) (P = .228) and 0.747 (0.667-0.827) (P = .016) of the two less-experienced radiologists.</p><p><strong>Conclusions: </strong>The radiomics-based model for triphasic enhanced CT images performed well in differentiating malignant from benign FLLs and may be a potential tool to screen for positive cases and avoid false negatives.</p><p><strong>Advances in knowledge: </strong>The radiomics-based model for triphasic enhanced CT achieved high performance in differentiating malignant from benign FLLs and may help to screen for positive cases and avoid false negatives.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":"1623-1631"},"PeriodicalIF":3.4,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144526503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}