Pub Date : 2026-01-28DOI: 10.1016/j.ejrad.2026.112706
Rosa Alba Pugliesi, Roberto Cannella, Federica Vernuccio, Marika Triscari Barberi, Giovanni Roccella, Giuseppe Brancatelli, Giuseppe Lo Re
Pelvic floor dysfunction encompasses a spectrum of disorders characterized by organ descent, muscular weakness, and impaired coordination across the anterior, middle, and posterior compartments. MRI defecography has become an established non-invasive technique for comprehensive assessment of both static anatomy and dynamic function of the pelvic floor. This review describes the MRI defecography technique, protocol components, and quantitative parameters that provide an objective evaluation of pelvic floor dysfunction. Standard MRI defecography protocol incorporates resting, contraction, straining, and evacuation phases, with single-shot fast spin-echo and real-time sequences enabling visualization of pelvic structures throughout motion. Quantitative parameters, including the anorectal angle, pubococcygeal line, H and M lines, minimal prolapse level, and levator plate angle, allow for objective evaluation of pelvic floor dysfunction. MRI defecography is particularly valuable in complex and postoperative scenarios, allowing detection of cystoceles, rectoceles, enteroceles, uterine or vaginal prolapse, intussusception, and post-surgical complications. In addition, MRI-defecography highlights the importance of stabilizing structures such as the urogenital diaphragm, endopelvic fascia, and levator ani complex. By integrating anatomic and functional findings, MRI defecography supports individualized therapeutic planning, guides surgical decision-making, and improves long-term outcomes. MRI defecography has thus emerged as a cornerstone in the multidisciplinary management of pelvic floor dysfunction.
{"title":"Pelvic floor dysfunction: Anatomical characterization and functional imaging with MRI defecography.","authors":"Rosa Alba Pugliesi, Roberto Cannella, Federica Vernuccio, Marika Triscari Barberi, Giovanni Roccella, Giuseppe Brancatelli, Giuseppe Lo Re","doi":"10.1016/j.ejrad.2026.112706","DOIUrl":"https://doi.org/10.1016/j.ejrad.2026.112706","url":null,"abstract":"<p><p>Pelvic floor dysfunction encompasses a spectrum of disorders characterized by organ descent, muscular weakness, and impaired coordination across the anterior, middle, and posterior compartments. MRI defecography has become an established non-invasive technique for comprehensive assessment of both static anatomy and dynamic function of the pelvic floor. This review describes the MRI defecography technique, protocol components, and quantitative parameters that provide an objective evaluation of pelvic floor dysfunction. Standard MRI defecography protocol incorporates resting, contraction, straining, and evacuation phases, with single-shot fast spin-echo and real-time sequences enabling visualization of pelvic structures throughout motion. Quantitative parameters, including the anorectal angle, pubococcygeal line, H and M lines, minimal prolapse level, and levator plate angle, allow for objective evaluation of pelvic floor dysfunction. MRI defecography is particularly valuable in complex and postoperative scenarios, allowing detection of cystoceles, rectoceles, enteroceles, uterine or vaginal prolapse, intussusception, and post-surgical complications. In addition, MRI-defecography highlights the importance of stabilizing structures such as the urogenital diaphragm, endopelvic fascia, and levator ani complex. By integrating anatomic and functional findings, MRI defecography supports individualized therapeutic planning, guides surgical decision-making, and improves long-term outcomes. MRI defecography has thus emerged as a cornerstone in the multidisciplinary management of pelvic floor dysfunction.</p>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"112706"},"PeriodicalIF":3.3,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146118375","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}
Pub Date : 2026-01-28DOI: 10.1016/j.ejrad.2026.112702
Yixuan Hu , Jinxia Wang , Lingzhi Meng , Jinzhen Song , Zongli Yang
Background
The SRU consensus on pelvic ultrasound proposed standardized augmented ultrasound, but its validity and indirect signs’ role require validation. This study will explore the application value of this consensus in deep endometriosis.
Method
This prospective study enrolled patients with clinically suspected endometriosis at Qingdao University Affiliated Hospital from May 2024 to April 2025. TVUS findings were compared with surgical findings. The diagnostic performance of TVUS for endometriosis was calculated, and multivariable logistic regression was applied to analyze associations between indirect sonographic signs and lesion locations.
Results
Included were 288 patients with clinical suspicion of DE. For DE detection, TVUS showed an overall accuracy of 84.4% (sensitivity 87.4%, specificity 76.8%). Fixed uterine retroflexion was significantly associated with bowel (OR 2.07, 95% CI 1.16–3.71), RVS (OR 2.83, 95% CI 1.34–6.32), and uterine serosal involvement (OR 2.38, 95% CI 1.19–4.88). Bowel tethering predicted bowel (OR 6.45, 95% CI 3.69–11.53), RVS (OR 4.53, 95% CI 2.24–9.62), uterine serosal (OR 2.15, 95% CI 1.12–4.18), and vaginal lesions (OR 3.83, 95% CI 1.85–8.25). Ipsilateral ovarian fixation or abnormal position was indicative of ipsilateral ovarian endometriosis (right: OR 16.9, 95% CI 9.15–32.96; left: OR 14.54, 95% CI 8.02–27.63) and USL involvement (right: OR 4.38, 95% CI 2.40–8.29, left: OR 2.23, 95%CI 1.3–3.91).
Conclusion
SRU-based ultrasound demonstrates high diagnostic accuracy for DE. Indirect signs effectively localize endometriotic lesions, enhancing surgical planning.
SRU关于骨盆超声的共识提出了标准化增强超声,但其有效性和间接标志的作用有待验证。本研究将探讨该共识在深部子宫内膜异位症中的应用价值。方法本前瞻性研究纳入2024年5月至2025年4月青岛大学附属医院临床疑似子宫内膜异位症患者。将TVUS结果与手术结果进行比较。计算TVUS对子宫内膜异位症的诊断效果,并应用多变量logistic回归分析间接超声征象与病变部位的相关性。结果入选288例临床疑似DE患者,TVUS检测DE的总准确率为84.4%(敏感性87.4%,特异性76.8%)。固定子宫后倾与肠道(OR 2.07, 95% CI 1.16-3.71)、RVS (OR 2.83, 95% CI 1.34-6.32)和子宫浆膜受累(OR 2.38, 95% CI 1.19-4.88)显著相关。肠栓术预测肠道(OR 6.45, 95% CI 3.69-11.53)、RVS (OR 4.53, 95% CI 2.24-9.62)、子宫浆膜(OR 2.15, 95% CI 1.12-4.18)和阴道病变(OR 3.83, 95% CI 1.85-8.25)。同侧卵巢固定或位置异常提示同侧卵巢子宫内膜异位症(右侧:or 16.9, 95%CI 9.15-32.96;左侧:or 14.54, 95%CI 8.02-27.63)和USL受累(右侧:or 4.38, 95%CI 2.40-8.29,左侧:or 2.23, 95%CI 1.3-3.91)。结论超声超声对DE的诊断准确率高,间接征象能有效定位子宫内膜异位症病变,提高手术计划。
{"title":"Transvaginal ultrasound for deep endometriosis: Prospective validation of SRU criteria and diagnostic value of indirect signs","authors":"Yixuan Hu , Jinxia Wang , Lingzhi Meng , Jinzhen Song , Zongli Yang","doi":"10.1016/j.ejrad.2026.112702","DOIUrl":"10.1016/j.ejrad.2026.112702","url":null,"abstract":"<div><h3>Background</h3><div>The SRU consensus on pelvic ultrasound proposed standardized augmented ultrasound, but its validity and indirect signs’ role require validation. This study will explore the application value of this consensus in deep endometriosis.</div></div><div><h3>Method</h3><div>This prospective study enrolled patients with clinically suspected endometriosis at Qingdao University Affiliated Hospital from May 2024 to April 2025. TVUS findings were compared with surgical findings. The diagnostic performance of TVUS for endometriosis was calculated, and multivariable logistic regression was applied to analyze associations between indirect sonographic signs and lesion locations.</div></div><div><h3>Results</h3><div>Included were 288 patients with clinical suspicion of DE. For DE detection, TVUS showed an overall accuracy of 84.4% (sensitivity 87.4%, specificity 76.8%). Fixed uterine retroflexion was significantly associated with bowel (OR 2.07, 95% CI 1.16–3.71), RVS (OR 2.83, 95% CI 1.34–6.32), and uterine serosal involvement (OR 2.38, 95% CI 1.19–4.88). Bowel tethering predicted bowel (OR 6.45, 95% CI 3.69–11.53), RVS (OR 4.53, 95% CI 2.24–9.62), uterine serosal (OR 2.15, 95% CI 1.12–4.18), and vaginal lesions (OR 3.83, 95% CI 1.85–8.25). Ipsilateral ovarian fixation or abnormal position was indicative of ipsilateral ovarian endometriosis (right: OR 16.9, 95% CI 9.15–32.96; left: OR 14.54, 95% CI 8.02–27.63) and USL involvement (right: OR 4.38, 95% CI 2.40–8.29, left: OR 2.23, 95%CI 1.3–3.91).</div></div><div><h3>Conclusion</h3><div>SRU-based ultrasound demonstrates high diagnostic accuracy for DE. Indirect signs effectively localize endometriotic lesions, enhancing surgical planning.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"Article 112702"},"PeriodicalIF":3.3,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146074524","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}
Pub Date : 2026-01-28DOI: 10.1016/j.ejrad.2026.112705
Langlang Tang , Kaiqian Que , Yanfen Lan , Yimin Li , Bin Wang , Zhuting Fang
Purpose
To develop and validate a prognostic model integrating pretreatment MRI features and clinical characteristics for hepatocellular carcinoma (HCC) patients undergoing transarterial chemoembolization (TACE) and hepatic arterial infusion chemotherapy (HAIC) combined targeted immunotherapy (TII). A weighted scoring system was developed to improve the model’s clinical utility.
Methods
We retrospectively recruited 141 patients with HCC from multiple centers, with 98 in the training cohort and 43 in the validation cohort. The independent predictors were identified using univariate and multivariate Cox regression analyses and developed a clinical nomogram. We constructed an 10-point weighted scoring system incorporating imaging features. Model performance was evaluated using AUC, decision curve analysis (DCA), and calibration curves assessed via bootstrapping.
Results
Logistic regression identified four risk factors for objective response (OR): irregular tumor border, absent of Intratumoral artery, albumin-bilirubin (ALBI) score ≥ -2.352, number ≥ 2, and tumor histopathological enhancement (THPE). The AUC was 0.804 in the training cohort and 0.580 in the validation cohort. The Akaike Information Criterion (AIC) for the scoring model was lower than the other model for predicting OR, progression-free survival (PFS), and overall survival (OS). Patients with a scoring model value > 5.5 points were classified as high-risk. The Kaplan-Meier (K-M) curves of the scoring model showed the better discriminative ability for PFS and OS.
Conclusion
The functional imaging-liver function synergy model demonstrates superior prognostic accuracy over conventional tumor burden parameters in hepatocellular carcinoma patients receiving quadruple therapy. Furthermore, the derived 10-point scoring system enables clinically actionable risk stratification.
目的建立并验证肝细胞癌(HCC)经动脉化疗栓塞(TACE)和肝动脉灌注化疗(HAIC)联合靶向免疫治疗(TII)的预后模型。开发了加权评分系统以提高模型的临床实用性。方法我们回顾性地从多个中心招募了141例HCC患者,其中98例为培训组,43例为验证组。使用单变量和多变量Cox回归分析确定独立预测因子,并制定临床nomogram。我们构建了一个包含影像特征的10分加权评分系统。采用AUC、决策曲线分析(DCA)和自举校准曲线评估模型性能。结果logistic回归分析确定了4个客观反应(OR)的危险因素:肿瘤边界不规则、瘤内动脉缺失、白蛋白-胆红素(ALBI)评分≥-2.352、数量≥2、肿瘤组织病理学增强(THPE)。训练组和验证组的AUC分别为0.804和0.580。评分模型的赤池信息标准(Akaike Information Criterion, AIC)在预测OR、无进展生存期(PFS)和总生存期(OS)方面低于其他模型。评分模型值为>; 5.5分的患者为高危患者。评分模型的Kaplan-Meier (K-M)曲线对PFS和OS有较好的判别能力。结论功能影像学-肝功能协同模型对肝细胞癌四联治疗患者预后的准确性优于常规肿瘤负荷参数。此外,衍生的10分评分系统使临床可操作的风险分层。
{"title":"Prognostic value of functional MRI and liver function synergy in hepatocellular carcinoma patients receiving combined locoregional-systemic therapy: A multicenter scoring model","authors":"Langlang Tang , Kaiqian Que , Yanfen Lan , Yimin Li , Bin Wang , Zhuting Fang","doi":"10.1016/j.ejrad.2026.112705","DOIUrl":"10.1016/j.ejrad.2026.112705","url":null,"abstract":"<div><h3>Purpose</h3><div>To develop and validate a prognostic model integrating pretreatment MRI features and clinical characteristics for hepatocellular carcinoma (HCC) patients undergoing transarterial chemoembolization (TACE) and hepatic arterial infusion chemotherapy (HAIC) combined targeted immunotherapy (TII). A weighted scoring system was developed to improve the model’s clinical utility.</div></div><div><h3>Methods</h3><div>We retrospectively recruited 141 patients with HCC from multiple centers, with 98 in the training cohort and 43 in the validation cohort. The independent predictors were identified using univariate and multivariate Cox regression analyses and developed a clinical nomogram. We constructed an 10-point weighted scoring system incorporating imaging features. Model performance was evaluated using AUC, decision curve analysis (DCA), and calibration curves assessed via bootstrapping.</div></div><div><h3>Results</h3><div>Logistic regression identified four risk factors for objective response (OR): irregular tumor border, absent of Intratumoral artery, albumin-bilirubin (ALBI) score ≥ -2.352, number ≥ 2, and tumor histopathological enhancement (THPE). The AUC was 0.804 in the training cohort and 0.580 in the validation cohort. The Akaike Information Criterion (AIC) for the scoring model was lower than the other model for predicting OR, progression-free survival (PFS), and overall survival (OS). Patients with a scoring model value > 5.5 points were classified as high-risk. The Kaplan-Meier (K-M) curves of the scoring model showed the better discriminative ability for PFS and OS.</div></div><div><h3>Conclusion</h3><div>The functional imaging-liver function synergy model demonstrates superior prognostic accuracy over conventional tumor burden parameters in hepatocellular carcinoma patients receiving quadruple therapy. Furthermore, the derived 10-point scoring system enables clinically actionable risk stratification.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"Article 112705"},"PeriodicalIF":3.3,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146074617","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}
Pub Date : 2026-01-28DOI: 10.1016/j.ejrad.2026.112704
Qian Zhang, Cuilian Mao, Fengyun Lu, Yunjuan Wu, Yao Ke, Rui Liu
Objective: Bone erosion is a hallmark of progressive joint damage and poor prognosis in psoriatic arthritis (PsA). Early identification of high-risk patients is critical for implementing aggressive interventions that can mitigate inflammation and prevent irreversible structural joint damage. This study aimed to identify clinical and ultrasonographic features associated with bone erosion in patients with early PsA.
Methods: A total of 82 patients with early PsA with articular and/or the entheseal involvement of less than 6-month duration were prospectively enrolled from the Rheumatology Department of the First Affiliated Hospital with Nanjing Medical University between March 2022 and January 2025 and followed for 24 months. Data about demographic and clinical characteristics, clinical enthesitis and dactylitis, and medication were collected. Musculoskeletal ultrasound was performed at baseline and the 2-year visit.Inflammatory and structural changes were scored with the modified MAdrid Sonographic Enthesitis Index (MASEI) and Novel and reliable DACTylitis glObal Sonographic (DACTOS) score. Erosions were defined by two radiology experts based on at least two imaging techniques. Logistic regression analysis was performed to identify variables associated with bone erosion occurring within 2 years of initial diagnosis. This trial has been registered on ClinicalTrials.gov under identifier NCT06730334.
Results: Early PsA patients with bone erosion had later onset of the disease (40.70 ± 13.35 vs 32.33 ± 13.98, p = 0.008), higher proportion with metabolic syndrome (p = 0.043), a greater number of swollen joints at baseline (p = 0.029), and higher DACTOS scores (p = 0.026). Over the 24-month follow-up, a higher proportion of patients without bone erosion received IL-17 inhibitor therapy (p = 0.034). Multivariate analysis identified older age at symptom onset (OR 1.049, p = 0.012) and higher DACTOS score (OR 1.082, p = 0.036) as independent predictors of bone erosion.
Conclusion: Our findings establish that an older age at symptom onset and a higher ultrasonographic dactylitis burden, quantified by the DACTOS score, are independent risk factors for bone erosion in early PsA. This supports the integration of ultrasound into early risk stratification to identify patients at greater risk for structural damage.
目的:骨侵蚀是银屑病关节炎(PsA)进行性关节损伤和预后不良的标志。早期识别高风险患者对于实施积极的干预措施至关重要,这些干预措施可以减轻炎症并防止不可逆的结构性关节损伤。本研究旨在确定与早期PsA患者骨侵蚀相关的临床和超声特征。方法:前瞻性入选南京医科大学第一附属医院风湿病科于2022年3月至2025年1月期间,伴有关节和/或肺泡受累的早期PsA患者共82例,持续时间小于6个月,随访24个月。收集了人口学和临床特征、临床鼻炎和指突炎以及用药情况的资料。在基线和2年随访时进行肌肉骨骼超声检查。采用改良的马德里超声胸炎指数(MASEI)和新颖可靠的DACTylitis全球超声(DACTOS)评分对炎症和结构变化进行评分。侵蚀由两名放射学专家根据至少两种成像技术确定。进行Logistic回归分析以确定与首次诊断2年内发生骨侵蚀相关的变量。该试验已在ClinicalTrials.gov注册,识别码为NCT06730334。结果:骨质侵蚀的早期PsA患者发病较晚(40.70±13.35 vs 32.33±13.98,p = 0.008),代谢综合征比例较高(p = 0.043),基线时关节肿胀较多(p = 0.029), DACTOS评分较高(p = 0.026)。在24个月的随访中,接受IL-17抑制剂治疗的无骨侵蚀患者比例较高(p = 0.034)。多因素分析发现,出现症状时年龄较大(OR 1.049, p = 0.012)和DACTOS评分较高(OR 1.082, p = 0.036)是骨侵蚀的独立预测因素。结论:我们的研究结果表明,症状发作时年龄较大和超声指炎负担较高(通过DACTOS评分量化)是早期PsA骨侵蚀的独立危险因素。这支持将超声整合到早期风险分层中,以识别结构损伤风险较大的患者。
{"title":"Ultrasound dactylitis predicts bone erosion in early psoriatic arthritis: A longitudinal cohort study.","authors":"Qian Zhang, Cuilian Mao, Fengyun Lu, Yunjuan Wu, Yao Ke, Rui Liu","doi":"10.1016/j.ejrad.2026.112704","DOIUrl":"https://doi.org/10.1016/j.ejrad.2026.112704","url":null,"abstract":"<p><strong>Objective: </strong>Bone erosion is a hallmark of progressive joint damage and poor prognosis in psoriatic arthritis (PsA). Early identification of high-risk patients is critical for implementing aggressive interventions that can mitigate inflammation and prevent irreversible structural joint damage. This study aimed to identify clinical and ultrasonographic features associated with bone erosion in patients with early PsA.</p><p><strong>Methods: </strong>A total of 82 patients with early PsA with articular and/or the entheseal involvement of less than 6-month duration were prospectively enrolled from the Rheumatology Department of the First Affiliated Hospital with Nanjing Medical University between March 2022 and January 2025 and followed for 24 months. Data about demographic and clinical characteristics, clinical enthesitis and dactylitis, and medication were collected. Musculoskeletal ultrasound was performed at baseline and the 2-year visit.Inflammatory and structural changes were scored with the modified MAdrid Sonographic Enthesitis Index (MASEI) and Novel and reliable DACTylitis glObal Sonographic (DACTOS) score. Erosions were defined by two radiology experts based on at least two imaging techniques. Logistic regression analysis was performed to identify variables associated with bone erosion occurring within 2 years of initial diagnosis. This trial has been registered on ClinicalTrials.gov under identifier NCT06730334.</p><p><strong>Results: </strong>Early PsA patients with bone erosion had later onset of the disease (40.70 ± 13.35 vs 32.33 ± 13.98, p = 0.008), higher proportion with metabolic syndrome (p = 0.043), a greater number of swollen joints at baseline (p = 0.029), and higher DACTOS scores (p = 0.026). Over the 24-month follow-up, a higher proportion of patients without bone erosion received IL-17 inhibitor therapy (p = 0.034). Multivariate analysis identified older age at symptom onset (OR 1.049, p = 0.012) and higher DACTOS score (OR 1.082, p = 0.036) as independent predictors of bone erosion.</p><p><strong>Conclusion: </strong>Our findings establish that an older age at symptom onset and a higher ultrasonographic dactylitis burden, quantified by the DACTOS score, are independent risk factors for bone erosion in early PsA. This supports the integration of ultrasound into early risk stratification to identify patients at greater risk for structural damage.</p>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"112704"},"PeriodicalIF":3.3,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146100086","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}
Pub Date : 2026-01-28DOI: 10.1016/j.ejrad.2026.112710
Mathis Rombaut, Nicolas Coquelet, Roberto Casale, Ayoub Mokhtari, Maria Antonietta Bali, Kevin Brou Boni, Felix Nensa, René Hosch, Katarzyna Borys, Riccardo De Angelis
Introduction: High-grade soft tissue sarcomas (STShg) of the extremities are rare cancers with a poor prognosis. Accurate staging at initial evaluation is crucial for determining optimal treatment. Current guidelines recommend systematic chest computed tomography (CT) scans during initial assessment. Recent advances in artificial intelligence (AI)-based imaging software now enable automatic, rapid volumetric assessment of body composition from CT scans. Our study aims to evaluate the predictive role of body composition features, obtained using a dedicated AI program, on overall survival (OS) and disease-free survival (DFS), using staging chest CT scans from patients diagnosed with extremity STShg.
Materials and methods: We conducted a single-center retrospective study at the Jules Bordet Institute, including patients diagnosed with extremity STShg between January 2010 and January 2023 who underwent CT scans covering the thoracic region. Using dedicated software, we performed automated 3D quantitative analysis of various anatomical compartments, including intramuscular adipose tissue (IMAT), pericardial adipose tissue (PAT), epicardial adipose tissue (EAT), and visceral adipose tissue (VAT). We assessed the association between body composition metrics and OS, DFS, local recurrence-free survival, and metastatic recurrence-free survival.
Results: Higher volumes of IMAT and PAT were associated with shorter OS, DFS, and local recurrence-free survival. Increased EAT volume correlated with reduced OS, while higher VAT volume was linked to worse OS and DFS.
Conclusion: Our study suggests a potential predictive role of specific body composition features, particularly IMAT, PAT, EAT, and VAT volumes, in the prognosis of extremity STShg.
{"title":"Automated 3D body composition analysis on chest CT scans for survival prediction in high-grade extremity soft tissue sarcomas.","authors":"Mathis Rombaut, Nicolas Coquelet, Roberto Casale, Ayoub Mokhtari, Maria Antonietta Bali, Kevin Brou Boni, Felix Nensa, René Hosch, Katarzyna Borys, Riccardo De Angelis","doi":"10.1016/j.ejrad.2026.112710","DOIUrl":"https://doi.org/10.1016/j.ejrad.2026.112710","url":null,"abstract":"<p><strong>Introduction: </strong>High-grade soft tissue sarcomas (STShg) of the extremities are rare cancers with a poor prognosis. Accurate staging at initial evaluation is crucial for determining optimal treatment. Current guidelines recommend systematic chest computed tomography (CT) scans during initial assessment. Recent advances in artificial intelligence (AI)-based imaging software now enable automatic, rapid volumetric assessment of body composition from CT scans. Our study aims to evaluate the predictive role of body composition features, obtained using a dedicated AI program, on overall survival (OS) and disease-free survival (DFS), using staging chest CT scans from patients diagnosed with extremity STShg.</p><p><strong>Materials and methods: </strong>We conducted a single-center retrospective study at the Jules Bordet Institute, including patients diagnosed with extremity STShg between January 2010 and January 2023 who underwent CT scans covering the thoracic region. Using dedicated software, we performed automated 3D quantitative analysis of various anatomical compartments, including intramuscular adipose tissue (IMAT), pericardial adipose tissue (PAT), epicardial adipose tissue (EAT), and visceral adipose tissue (VAT). We assessed the association between body composition metrics and OS, DFS, local recurrence-free survival, and metastatic recurrence-free survival.</p><p><strong>Results: </strong>Higher volumes of IMAT and PAT were associated with shorter OS, DFS, and local recurrence-free survival. Increased EAT volume correlated with reduced OS, while higher VAT volume was linked to worse OS and DFS.</p><p><strong>Conclusion: </strong>Our study suggests a potential predictive role of specific body composition features, particularly IMAT, PAT, EAT, and VAT volumes, in the prognosis of extremity STShg.</p>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"112710"},"PeriodicalIF":3.3,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146112725","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}
Pub Date : 2026-01-26DOI: 10.1016/j.ejrad.2026.112694
Yangyang Yin , Qiuxia Wang , Zhihan Xu , Xudong Ai , Huan Liu , Haoyue Shao , Linhan Zhai , Shen Gui , Zhiwen Yang , Yu Chen , Baoyi Wang , Jing Zhang
Background
The lenticulostriate arteries (LSAs) are critical perforating vessels, but conventional CTA poorly depicts them. Dual-Energy CT offers Virtual Monochromatic Imaging and kernel adjustment, yet the optimal strategy for LSAs visualization remains unclear.
Materials and Methods
This retrospective study included 556 patients (59 [46–72] years; 310 males [55.8%]) who underwent DE-CTA between May 2023 to July 2024. Images were reconstructed Virtual Monochromatic Imaging at 40–90 KeV and multiple convolution kernels (Qr40, Hv36, Hv40, Hv44, and Hv49). Step 1 compared image quality across KeV levels, and Step 2 optimized kernels on the basis of the best KeV and compared these optimized reconstructions again. Quantitative metrics included CT value, SNR, CNR, edge rise distance, and edge rise slope; qualitative assessment and visible LSAs branch counts were performed.
Results
Step 1 demonstrated significant differences in CT value, and CNR across KeV levels (all p < 0.001), with 40 KeV yielding the highest CT value and CNR and the best subjective scores for artery branches visualization. Step 2 showed that sharper kernels significantly improved ERS and reduced ERD, with Hv49-40 KeV achieving the greatest edge sharpness (ERS, 10374.4 [7407.0–13341.9]; ERD, 0.10 [0.08–0.13]) and the highest number of visible LSAs branches (6.5 [2.5–10.5]; all adjusted p < . 001).
Conclusion
Hv49-40KeV on DE‑CTA of the head and neck substantially improves the visualization of arteries across different calibers, with a marked enhancement in the depiction of the LSAs, providing a solid technical foundation for the evaluation of LSAs with DE‑CT.
Relevance statement
This optimized Dual Energy-CT angiography reconstruction increases the utility of head and neck CTA by improving lenticulostriate artery visualization, thereby supporting routine evaluation of both large and small cerebral vessels in clinical practice.
{"title":"Dual-energy computed tomography angiography for lenticulostriate arteries: Stepwise optimization of virtual monochromatic imaging and kernel setting","authors":"Yangyang Yin , Qiuxia Wang , Zhihan Xu , Xudong Ai , Huan Liu , Haoyue Shao , Linhan Zhai , Shen Gui , Zhiwen Yang , Yu Chen , Baoyi Wang , Jing Zhang","doi":"10.1016/j.ejrad.2026.112694","DOIUrl":"10.1016/j.ejrad.2026.112694","url":null,"abstract":"<div><h3>Background</h3><div>The lenticulostriate arteries (LSAs) are critical perforating vessels, but conventional CTA poorly depicts them. Dual-Energy CT offers Virtual Monochromatic Imaging and kernel adjustment, yet the optimal strategy for LSAs visualization remains unclear.</div></div><div><h3>Materials and Methods</h3><div>This retrospective study included 556 patients (59 [46–72] years; 310 males [55.8%]) who underwent DE-CTA between May 2023 to July 2024. Images were reconstructed Virtual Monochromatic Imaging at 40–90 KeV and multiple convolution kernels (Qr40, Hv36, Hv40, Hv44, and Hv49). Step 1 compared image quality across KeV levels, and Step 2 optimized kernels on the basis of the best KeV and compared these optimized reconstructions again. Quantitative metrics included CT value, SNR, CNR, edge rise distance, and edge rise slope; qualitative assessment and visible LSAs branch counts were performed.</div></div><div><h3>Results</h3><div>Step 1 demonstrated significant differences in CT value, and CNR across KeV levels (all <em>p</em> < 0.001), with 40 KeV yielding the highest CT value and CNR and the best subjective scores for artery branches visualization. Step 2 showed that sharper kernels significantly improved ERS and reduced ERD, with Hv49-40 KeV achieving the greatest edge sharpness (ERS, 10374.4 [7407.0–13341.9]; ERD, 0.10 [0.08–0.13]) and the highest number of visible LSAs branches (6.5 [2.5–10.5]; all adjusted <em>p</em> < . 001).</div></div><div><h3>Conclusion</h3><div>Hv49-40KeV on DE‑CTA of the head and neck substantially improves the visualization of arteries across different calibers, with a marked enhancement in the depiction of the LSAs, providing a solid technical foundation for the evaluation of LSAs with DE‑CT.</div></div><div><h3>Relevance statement</h3><div>This optimized Dual Energy-CT angiography reconstruction increases the utility of head and neck CTA by improving lenticulostriate artery visualization, thereby supporting routine evaluation of both large and small cerebral vessels in clinical practice.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"Article 112694"},"PeriodicalIF":3.3,"publicationDate":"2026-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146074525","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}
Pub Date : 2026-01-25DOI: 10.1016/j.ejrad.2026.112701
Sari Luthfiyah, Triwiyanto Triwiyanto, Luthfi Rusyadi, Mohammed Ismath
We comment on Ba-Ssalamah et al.'s study comparing MRI-derived and biopsy-confirmed liver iron concentration in chronic liver disease. The strong agreement between two R2*-based methods supports the robustness of relaxometry-based LIC estimation in the low-mild iron range. We discuss physics-related considerations, including R2* nonlinearity, spatial sampling, signal modeling, and calibration dependence, and outline future directions toward volumetric mapping and cross-platform harmonization for quantitative liver MRI.
{"title":"Letter to Editor: Correlation between MRI-derived and biopsy-confirmed liver iron concentration in patients with chronic liver disease.","authors":"Sari Luthfiyah, Triwiyanto Triwiyanto, Luthfi Rusyadi, Mohammed Ismath","doi":"10.1016/j.ejrad.2026.112701","DOIUrl":"https://doi.org/10.1016/j.ejrad.2026.112701","url":null,"abstract":"<p><p>We comment on Ba-Ssalamah et al.'s study comparing MRI-derived and biopsy-confirmed liver iron concentration in chronic liver disease. The strong agreement between two R2*-based methods supports the robustness of relaxometry-based LIC estimation in the low-mild iron range. We discuss physics-related considerations, including R2* nonlinearity, spatial sampling, signal modeling, and calibration dependence, and outline future directions toward volumetric mapping and cross-platform harmonization for quantitative liver MRI.</p>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"112701"},"PeriodicalIF":3.3,"publicationDate":"2026-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146099918","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}
Pub Date : 2026-01-25DOI: 10.1016/j.ejrad.2026.112699
Hangzhi Liu , Yingzhu Zhao , Jing Li , Xiaoxia Qu , Tianying Ma , Chen Zhang , Thorsten Feiweier , Xinyan Wang , Junfang Xian
Background
Preoperative discrimination between orbital B-cell lymphoma and inflammatory lesions remains a significant challenge using conventional imaging. This study evaluates the potential of time-dependent diffusion MRI (td-dMRI) alongside diffusion-weighted imaging (DWI) to improve differential diagnosis.
Methods
Patients with suspected orbital tumors were prospectively enrolled between October 2023 and November 2024. All participants underwent td-dMRI using oscillating gradient spin-echo (OGSE) and pulsed gradient spin-echo (PGSE) sequences on a 3 T scanner. Microstructural parameters—including cell diameter (d), cellularity, extracellular diffusivity (Dex), and intracellular volume fraction (Vin)—were derived. Correlations between apparent diffusion coefficient (ADC), d, cellularity, and histopathological metrics were assessed through quantitative morphometric analysis. Diagnostic performance was evaluated using receiver operating characteristic (ROC) analysis.
Results
Forty-eight patients were enrolled (20 orbital MALT lymphoma, 28 inflammatory lesions). All parameters showed excellent interobserver agreement (ICCs: 0.82–0.93). Strong correlations were observed between histological cell diameter and d (r = 0.75), and between histological cellularity and both td-dMRI-derived cellularity (r = 0.71) and ADC (r = -0.74) (all p < 0.001). Lymphomas exhibited significantly lower ADC, d, and Dex, and higher Vin and cellularity compared to inflammatory lesions (all p < 0.01). Cellularity demonstrated the highest discriminative power (AUC = 0.87), followed by Vin (AUC = 0.82), while ADC showed moderate performance (AUC = 0.74). No significant differences in diagnostic efficacy were observed among the parameters.
Conclusions
The td-dMRI provides highly reproducible, histologically correlated biomarkers that effectively differentiate orbital lymphoma from inflammatory lesions, thereby enabling orbital lesion risk-stratification and providing valuable non-invasive characterization to complement conventional ADC-based assessment for preoperative diagnosis of orbital lesions.
{"title":"Discriminating orbital lymphoma from inflammation and correlating with histopathology using microstructure-based time-dependent diffusion MRI","authors":"Hangzhi Liu , Yingzhu Zhao , Jing Li , Xiaoxia Qu , Tianying Ma , Chen Zhang , Thorsten Feiweier , Xinyan Wang , Junfang Xian","doi":"10.1016/j.ejrad.2026.112699","DOIUrl":"10.1016/j.ejrad.2026.112699","url":null,"abstract":"<div><h3>Background</h3><div>Preoperative discrimination between orbital B-cell lymphoma and inflammatory lesions remains a significant challenge using conventional imaging. This study evaluates the potential of time-dependent diffusion MRI (td-dMRI) alongside diffusion-weighted imaging (DWI) to improve differential diagnosis.</div></div><div><h3>Methods</h3><div>Patients with suspected orbital tumors were prospectively enrolled between October 2023 and November 2024. All participants underwent td-dMRI using oscillating gradient spin-echo (OGSE) and pulsed gradient spin-echo (PGSE) sequences on a 3 T scanner. Microstructural parameters—including cell diameter (d), cellularity, extracellular diffusivity (Dex), and intracellular volume fraction (Vin)—were derived. Correlations between apparent diffusion coefficient (ADC), d, cellularity, and histopathological metrics were assessed through quantitative morphometric analysis. Diagnostic performance was evaluated using receiver operating characteristic (ROC) analysis.</div></div><div><h3>Results</h3><div>Forty-eight patients were enrolled (20 orbital MALT lymphoma, 28 inflammatory lesions). All parameters showed excellent interobserver agreement (ICCs: 0.82–0.93). Strong correlations were observed between histological cell diameter and d (r = 0.75), and between histological cellularity and both td-dMRI-derived cellularity (r = 0.71) and ADC (r = -0.74) (all p < 0.001). Lymphomas exhibited significantly lower ADC, d, and Dex, and higher Vin and cellularity compared to inflammatory lesions (all p < 0.01). Cellularity demonstrated the highest discriminative power (AUC = 0.87), followed by Vin (AUC = 0.82), while ADC showed moderate performance (AUC = 0.74). No significant differences in diagnostic efficacy were observed among the parameters.</div></div><div><h3>Conclusions</h3><div>The td-dMRI provides highly reproducible, histologically correlated biomarkers that effectively differentiate orbital lymphoma from inflammatory lesions, thereby enabling orbital lesion risk-stratification and providing valuable non-invasive characterization to complement conventional ADC-based assessment for preoperative diagnosis of orbital lesions.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"Article 112699"},"PeriodicalIF":3.3,"publicationDate":"2026-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146074549","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}
Pub Date : 2026-01-25DOI: 10.1016/j.ejrad.2026.112697
Jia Xu , Liang Zhu , Wei Liu , Wenjing Liu , Yitong Lu , Jingjuan Liu , Chenxue Ma , Yifei Zhang , Xuan Wang , Feng Feng
Purpose
To evaluate the image quality and clinical utility of DLR-enhanced single-shot fast spin-echo (SSFSE) T2-weighted imaging (T2WI) for diagnosing acute abdominal conditions, compared to standard SSFSE and Periodically Rotated Overlapping Parallel Lines with Enhanced Reconstruction (PROPELLER) T2WI sequences.
Methods
This prospective single-institutional study enrolled 70 participants (35 healthy volunteers and 35 patients with acute abdominal pain). Abdominopelvic MRI were performed, including SSFSE and PROPELLER sequences. SSFSE images were reconstructed with and without deep-learning algorithm. Three radiologists independently evaluated image quality and target organ conditions. The Friedman test was used to compare image quality across sequences. The diagnostic performance for identifying disorders (e.g., cholecystitis, appendicitis, etc.) was assessed using the area under receiver operating characteristic curves (AUCs) and compared using the Delong method. Three pregnant women and one elderly patient who underwent SSFSE protocols only were also analyzed.
Results
SSFSE-DLR demonstrated significantly higher image quality and lower noise than SSFSE and PROPELLER across all imaging planes (p < 0.05). It exhibited fewer motion artifacts and superior clarity of the appendix, gallbladder, and common bile duct compared to PROPELLER (p < 0.05). SSFSE-DLR achieved higher diagnostic accuracy for common acute abdominopelvic disorders (AUCs: 0.977–1.0), compared to SSFSE and PROPELLER (AUCs: 0.887–1.00 and 0.585–0.953, respectively, p < 0.05). In vulnerable patients with fast protocol, SSFSE-DLR identified one appendicitis missed by ultrasound, enabling timely surgery.
Conclusion
SSFSE-DLR significantly improves image quality and diagnostic accuracy in healthy volunteers and patients with acute abdomen.
{"title":"Feasibility study of fast T2-weighted imaging with deep-learning reconstruction in volunteers and emergency patients with acute abdomen","authors":"Jia Xu , Liang Zhu , Wei Liu , Wenjing Liu , Yitong Lu , Jingjuan Liu , Chenxue Ma , Yifei Zhang , Xuan Wang , Feng Feng","doi":"10.1016/j.ejrad.2026.112697","DOIUrl":"10.1016/j.ejrad.2026.112697","url":null,"abstract":"<div><h3>Purpose</h3><div>To evaluate the image quality and clinical utility of DLR-enhanced single-shot fast spin-echo (SSFSE) T2-weighted imaging (T2WI) for diagnosing acute abdominal conditions, compared to standard SSFSE and Periodically Rotated Overlapping Parallel Lines with Enhanced Reconstruction (PROPELLER) T2WI sequences.</div></div><div><h3>Methods</h3><div>This prospective single-institutional study enrolled 70 participants (35 healthy volunteers and 35 patients with acute abdominal pain). Abdominopelvic MRI were performed, including SSFSE and PROPELLER sequences. SSFSE images were reconstructed with and without deep-learning algorithm. Three radiologists independently evaluated image quality and target organ conditions. The Friedman test was used to compare image quality across sequences. The diagnostic performance for identifying disorders (e.g., cholecystitis, appendicitis, etc.) was assessed using the area under receiver operating characteristic curves (AUCs) and compared using the Delong method. Three pregnant women and one elderly patient who underwent SSFSE protocols only were also analyzed.</div></div><div><h3>Results</h3><div>SSFSE-DLR demonstrated significantly higher image quality and lower noise than SSFSE and PROPELLER across all imaging planes (<em>p</em> < 0.05). It exhibited fewer motion artifacts and superior clarity of the appendix, gallbladder, and common bile duct compared to PROPELLER (<em>p</em> < 0.05). SSFSE-DLR achieved higher diagnostic accuracy for common acute abdominopelvic disorders (AUCs: 0.977–1.0), compared to SSFSE and PROPELLER (AUCs: 0.887–1.00 and 0.585–0.953, respectively, <em>p</em> < 0.05). In vulnerable patients with fast protocol, SSFSE-DLR identified one appendicitis missed by ultrasound, enabling timely surgery.</div></div><div><h3>Conclusion</h3><div>SSFSE-DLR significantly improves image quality and diagnostic accuracy in healthy volunteers and patients with acute abdomen.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"Article 112697"},"PeriodicalIF":3.3,"publicationDate":"2026-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146074526","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}
Pub Date : 2026-01-25DOI: 10.1016/j.ejrad.2026.112700
Yuchen Wang , Xiaoxia Qu , Zheng Li , Dinggang Shen , Junfang Xian
Objective
Differentiating sinonasal small round cell malignant tumors (SRCMTs) from non-SRCMTs is challenging due to overlapping MRI features. This study aimed to compare the diagnostic performance of deep learning and radiomics models for preoperative MRI-based classification.
Methods
We retrospectively analyzed 325 patients with pathologically confirmed sinonasal malignancies (163 SRCMTs and 162 non-SRCMTs). Each patient underwent T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and contrast-enhanced T1-weighted imaging (CE-T1WI). Tumors were manually segmented. Five convolutional neural networks (CNNs)—ResNet-18, ResNet-34, ResNet-50, VGG13, and VGG16—were trained on each sequence. For radiomics, 1200 features were extracted per sequence, and multiple machine learning classifiers were trained. Model performance was assessed by area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). The DeLong test was used to compare AUCs between models, with statistical significance set at P < 0.05.
Results
The CE-T1WI-based ResNet-34 model achieved the best performance, with an average AUC of 0.830, the accuracy of 0.755, sensitivity of 0.918, specificity of 0.592, PPV of 0.692, and NPV of 0.879. The corresponding CE-T1WI-based radiomics model using a support vector machine yielded an AUC of 0.758 (accuracy = 0.755, sensitivity = 0.840, specificity = 0.667, PPV = 0.724, NPV = 0.800). On the independent test cohort, ResNet-34 showed numerically higher discriminative performance than the radiomics model, although this difference did not reach statistical significance. For T1WI and T2WI, deep learning and radiomics models demonstrated broadly comparable performance.
Conclusions
A CE-T1WI-based ResNet-34 network provided high diagnostic efficacy, and in our cohort deep learning models achieved numerically higher comparable performance to MRI-based radiomics models for differentiating SRCMTs from non-SRCMTs.
{"title":"Deep learning outperformed radiomics based on MRI in the differentiation of sinonasal small round cell and non-small round cell malignant tumors","authors":"Yuchen Wang , Xiaoxia Qu , Zheng Li , Dinggang Shen , Junfang Xian","doi":"10.1016/j.ejrad.2026.112700","DOIUrl":"10.1016/j.ejrad.2026.112700","url":null,"abstract":"<div><h3>Objective</h3><div>Differentiating sinonasal small round cell malignant tumors (SRCMTs) from non-SRCMTs is challenging due to overlapping MRI features. This study aimed to compare the diagnostic performance of deep learning and radiomics models for preoperative MRI-based classification.</div></div><div><h3>Methods</h3><div>We retrospectively analyzed 325 patients with pathologically confirmed sinonasal malignancies (163 SRCMTs and 162 non-SRCMTs). Each patient underwent T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and contrast-enhanced T1-weighted imaging (CE-T1WI). Tumors were manually segmented. Five convolutional neural networks (CNNs)—ResNet-18, ResNet-34, ResNet-50, VGG13, and VGG16—were trained on each sequence. For radiomics, 1200 features were extracted per sequence, and multiple machine learning classifiers were trained. Model performance was assessed by area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). The DeLong test was used to compare AUCs between models, with statistical significance set at P < 0.05.</div></div><div><h3>Results</h3><div>The CE-T1WI-based ResNet-34 model achieved the best performance, with an average AUC of 0.830, the accuracy of 0.755, sensitivity of 0.918, specificity of 0.592, PPV of 0.692, and NPV of 0.879. The corresponding CE-T1WI-based radiomics model using a support vector machine yielded an AUC of 0.758 (accuracy = 0.755, sensitivity = 0.840, specificity = 0.667, PPV = 0.724, NPV = 0.800). On the independent test cohort, ResNet-34 showed numerically higher discriminative performance than the radiomics model, although this difference did not reach statistical significance. For T1WI and T2WI, deep learning and radiomics models demonstrated broadly comparable performance.</div></div><div><h3>Conclusions</h3><div>A CE-T1WI-based ResNet-34 network provided high diagnostic efficacy, and in our cohort deep learning models achieved numerically higher comparable performance to MRI-based radiomics models for differentiating SRCMTs from non-SRCMTs.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"196 ","pages":"Article 112700"},"PeriodicalIF":3.3,"publicationDate":"2026-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146074551","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}