Pub Date : 2025-11-22DOI: 10.1016/j.ejrad.2025.112565
Ali Rastegarpour
Purpose
This study attempts to review the depiction of imaging modalities in feature length films, including documentaries.
Methods
The IMDb website was searched for feature films containing keywords related to multiple radiology modalities (including mammography, CT, MRI, radiography, fluoroscopy, angiography, and ultrasound) used in the “plot” summary and the use of imaging was reviewed as it related to the film or its plot. Common themes were identified and presented.
Results
A total of 67 titles were retrieved, which after removal of duplicate entries and irrelevant entries resulted in 51 individual titles. Common themes that may have a negative connotation included imaging portrayed as harmful (17.6%) or revealing a harmful process (23.5%). A harmful finding (unfavorable diagnosis or supernatural process) is demonstrated more often than normal findings on imaging, 12 out of 13 times (92.3%). Anti-mammography documentaries accounted for 4 out of 6 movies about mammography (66.7%). MRI is frequently depicted as a technological marvel and, along with CT,as a source of discovery, although often the target of science-fiction and science-fiction-adjacent depictions as a harmful technology. Ultrasound is commonly used as a symbol representing pregnancy and future or current children.
Conclusions
Recognizing how imaging modalities are depicted in film may help identify targets to address in health marketing campaigns and how to rectify certain attitudes and beliefs regarding imaging.
{"title":"The representation of imaging modalities in film","authors":"Ali Rastegarpour","doi":"10.1016/j.ejrad.2025.112565","DOIUrl":"10.1016/j.ejrad.2025.112565","url":null,"abstract":"<div><h3>Purpose</h3><div>This study attempts to review the depiction of imaging modalities in feature length films, including documentaries.</div></div><div><h3>Methods</h3><div>The IMDb website was searched for feature films containing keywords related to multiple radiology modalities (including mammography, CT, MRI, radiography, fluoroscopy, angiography, and ultrasound) used in the “plot” summary and the use of imaging was reviewed as it related to the film or its plot. Common themes were identified and presented.</div></div><div><h3>Results</h3><div>A total of 67 titles were retrieved, which after removal of duplicate entries and irrelevant entries resulted in 51 individual titles. Common themes that may have a negative connotation included imaging portrayed as harmful (17.6%) or revealing a harmful process (23.5%). A harmful finding (unfavorable diagnosis or supernatural process) is demonstrated more often than normal findings on imaging, 12 out of 13 times (92.3%). Anti-mammography documentaries accounted for 4 out of 6 movies about mammography (66.7%). MRI is frequently depicted as a technological marvel and, along with CT,as a source of discovery, although often the target of science-fiction and science-fiction-adjacent depictions as a harmful technology. Ultrasound is commonly used as a symbol representing pregnancy and future or current children.</div></div><div><h3>Conclusions</h3><div>Recognizing how imaging modalities are depicted in film may help identify targets to address in health marketing campaigns and how to rectify certain attitudes and beliefs regarding imaging.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"195 ","pages":"Article 112565"},"PeriodicalIF":3.3,"publicationDate":"2025-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145603348","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 : 2025-11-22DOI: 10.1016/j.ejrad.2025.112568
Xiaowen Ma , YunYi Wang , Feixiang Hu , Li Chen , Yan Huang , Weijun Peng , Qin Xiao , Yajia Gu
Purpose
Reactive cutaneous capillary endothelial proliferation (RCCEP) is a common immune-related adverse event (irAE) associated with camrelizumab. We aimed to explore and describe benign vascular proliferative lesions occurring within breast tissue of triple-negative breast cancer (TNBC) patients undergoing neoadjuvant chemoimmunotherapy (NACI) with camrelizumab.
Methods
We conducted a retrospective single-center analysis of 106 TNBC patients treated between March 2021 and August 2023 (mean age 48.1 ± 11.2 years). The cohort included 60 patients receiving neoadjuvant chemotherapy (NAC) and 46 patients who underwent NACI with camrelizumab. Clinical data, pathological characteristics, and MRI findings at baseline and during each treatment cycle were analyzed for all participants. Post-treatment newly identified abnormal lesions within breast tissue were detected and characterized.
Results
Abnormal enhancement was observed in 30 patients (3 NAC vs. 27 NACI, P < 0.001). In the NACI group, abnormal enhancement included 3 cases of ring enhancement (3/27, 11.1 %), 2 cases of linear enhancement (2/27, 7.4 %), and 22 cases of mass enhancement (22/27, 81.5 %). These lesions typically emerged after the second treatment cycle, with few appearing after the fourth or sixth cycle. Most lesions (26/27, 96.3 %) regressed with continued treatment. In the NACI group, the development of new enhancement lesions was correlated with younger age (P = 0.007), premenopausal status (P = 0.014), a lack of peritumoral edema on baseline MRI (P = 0.007), and the presence of mass enhancements (P = 0.012).
Conclusion
TNBC patients treated with camrelizumab frequently develop benign vascular proliferative lesions in the breast tissue, primarily manifesting as mass enhancements on MRI that typically regress with continued treatment without requiring therapy discontinuation.
目的：反应性皮肤毛细血管内皮增生（RCCEP）是与camrelizumab相关的常见免疫相关不良事件（irAE）。我们的目的是探索和描述三阴性乳腺癌（TNBC）患者在接受camrelizumab新辅助化疗免疫治疗（NACI）时乳房组织内发生的良性血管增生性病变。方法对2021年3月至2023年8月期间接受治疗的106例TNBC患者（平均年龄48.1±11.2岁）进行回顾性单中心分析。该队列包括60名接受新辅助化疗（NAC）的患者和46名接受camrelizumab辅助化疗的患者。对所有参与者在基线和每个治疗周期的临床资料、病理特征和MRI结果进行分析。治疗后新发现的乳腺组织异常病变被检测和表征。结果30例患者出现异常强化（3例NAC vs. 27例NACI， P < 0.001）。NACI组异常强化包括3例环状强化（3/ 27,11.1%），2例线状强化（2/ 27,7.4%），22例团块强化（22/ 27,81.5%）。这些病变通常在第二个治疗周期后出现，很少在第四个或第六个治疗周期后出现。大多数病变（26/27,96.3%）在持续治疗后消退。在NACI组中，新强化病灶的发生与年龄较小（P = 0.007）、绝经前状态（P = 0.014）、基线MRI检查有无肿瘤周围水肿（P = 0.007）和肿块增强（P = 0.012）相关。结论：camrelizumab治疗的tnbc患者经常在乳腺组织中出现良性血管增生性病变，主要表现为MRI肿块增强，通常在持续治疗后不需要停药即可消退。
{"title":"Intramammary benign vascular proliferative lesions on MRI during neoadjuvant chemoimmunotherapy with camrelizumab in TNBC patients","authors":"Xiaowen Ma , YunYi Wang , Feixiang Hu , Li Chen , Yan Huang , Weijun Peng , Qin Xiao , Yajia Gu","doi":"10.1016/j.ejrad.2025.112568","DOIUrl":"10.1016/j.ejrad.2025.112568","url":null,"abstract":"<div><h3>Purpose</h3><div>Reactive cutaneous capillary endothelial proliferation (RCCEP) is a common immune-related adverse event (irAE) associated with camrelizumab. We aimed to explore and describe benign vascular proliferative lesions occurring within breast tissue of triple-negative breast cancer (TNBC) patients undergoing neoadjuvant chemoimmunotherapy (NACI) with camrelizumab.</div></div><div><h3>Methods</h3><div>We conducted a retrospective single-center analysis of 106 TNBC patients treated between March 2021 and August 2023 (mean age 48.1 ± 11.2 years). The cohort included 60 patients receiving neoadjuvant chemotherapy (NAC) and 46 patients who underwent NACI with camrelizumab. Clinical data, pathological characteristics, and MRI findings at baseline and during each treatment cycle were analyzed for all participants. Post-treatment newly identified abnormal lesions within breast tissue were detected and characterized.</div></div><div><h3>Results</h3><div>Abnormal enhancement was observed in 30 patients (3 NAC vs. 27 NACI, <em>P</em> < 0.001). In the NACI group, abnormal enhancement included 3 cases of ring enhancement (3/27, 11.1 %), 2 cases of linear enhancement (2/27, 7.4 %), and 22 cases of mass enhancement (22/27, 81.5 %). These lesions typically emerged after the second treatment cycle, with few appearing after the fourth or sixth cycle. Most lesions (26/27, 96.3 %) regressed with continued treatment. In the NACI group, the development of new enhancement lesions was correlated with younger age (<em>P</em> = 0.007), premenopausal status (<em>P</em> = 0.014), a lack of peritumoral edema on baseline MRI (<em>P</em> = 0.007), and the presence of mass enhancements (<em>P</em> = 0.012).</div></div><div><h3>Conclusion</h3><div>TNBC patients treated with camrelizumab frequently develop benign vascular proliferative lesions in the breast tissue, primarily manifesting as mass enhancements on MRI that typically regress with continued treatment without requiring therapy discontinuation.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"195 ","pages":"Article 112568"},"PeriodicalIF":3.3,"publicationDate":"2025-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145622217","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 : 2025-11-22DOI: 10.1016/j.ejrad.2025.112567
Anna Colarieti , Elizaveta Vologina , Anna Carmen Leonetti , Serena Carriero , Leon Groenhoff , Carolina Lanza , Gianpaolo Carafiello , Alessandro Carriero
Purpose
Radiology residency in Italy is a structured four-year program that emphasizes both clinical practice and didactic education. Despite its pivotal role in shaping future radiologists, resident satisfaction remains an underexplored topic. This study aims to assess radiology residents’ satisfaction with their training, focusing on theoretical education, practical preparedness, mentorship, and overall professional development.
Methods
Starting from September 25, 2023, and finished on January 31, 2024, a cross-sectional survey was developed and distributed across 35 Italian radiology postgraduate schools. The questionnaire covered key areas: lecture quality, clinical training, mentorship, educational resources, and perceived readiness for independent practice. Descriptive statistics and cross-tabulations were conducted. Associations were analysed using chi-square tests and Cramer’s V.
Results
A total of 199 residents completed the survey. The sample was balanced by gender (54% female, 45% male) and represented all training years. Satisfaction with theoretical training and mentorship increased with residency seniority. Fourth-year residents reported the highest perceived preparedness (15.9% “very adequate”), while early-year residents expressed uncertainty. A strong association was found between satisfaction with didactic instruction and perceived autonomy. Gender-based differences revealed that male residents more often rated teaching and mentorship positively.
Conclusion
This study highlights generally positive satisfaction among radiology residents. Satisfaction increased with seniority and was closely linked to the perceived quality of theoretical instruction. Gender-related differences and mid-training challenges also emerged, underscoring areas for targeted improvement. These findings offer valuable guidance for optimizing radiology training programs through enhanced curriculum design, mentorship, and resident support.
{"title":"Voices of the future: insights from a survey on radiology training experiences and needs","authors":"Anna Colarieti , Elizaveta Vologina , Anna Carmen Leonetti , Serena Carriero , Leon Groenhoff , Carolina Lanza , Gianpaolo Carafiello , Alessandro Carriero","doi":"10.1016/j.ejrad.2025.112567","DOIUrl":"10.1016/j.ejrad.2025.112567","url":null,"abstract":"<div><h3>Purpose</h3><div>Radiology residency in Italy is a structured four-year program that emphasizes both clinical practice and didactic education. Despite its pivotal role in shaping future radiologists, resident satisfaction remains an underexplored topic. This study aims to assess radiology residents’ satisfaction with their training, focusing on theoretical education, practical preparedness, mentorship, and overall professional development.</div></div><div><h3>Methods</h3><div>Starting from September 25, 2023, and finished on January 31, 2024, a cross-sectional survey was developed and distributed across 35 Italian radiology postgraduate schools. The questionnaire covered key areas: lecture quality, clinical training, mentorship, educational resources, and perceived readiness for independent practice. Descriptive statistics and cross-tabulations were conducted. Associations were analysed using chi-square tests and Cramer’s V.</div></div><div><h3>Results</h3><div>A total of 199 residents completed the survey. The sample was balanced by gender (54% female, 45% male) and represented all training years. Satisfaction with theoretical training and mentorship increased with residency seniority. Fourth-year residents reported the highest perceived preparedness (15.9% “very adequate”), while early-year residents expressed uncertainty. A strong association was found between satisfaction with didactic instruction and perceived autonomy. Gender-based differences revealed that male residents more often rated teaching and mentorship positively.</div></div><div><h3>Conclusion</h3><div>This study highlights generally positive satisfaction among radiology residents. Satisfaction increased with seniority and was closely linked to the perceived quality of theoretical instruction. Gender-related differences and mid-training challenges also emerged, underscoring areas for targeted improvement. These findings offer valuable guidance for optimizing radiology training programs through enhanced curriculum design, mentorship, and resident support.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"195 ","pages":"Article 112567"},"PeriodicalIF":3.3,"publicationDate":"2025-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145622727","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 : 2025-11-20DOI: 10.1016/j.ejrad.2025.112521
Siang Shen , Bitian Liu , Yutong Li , Yiying Zeng , Shanshan Ren , Rui Yin , Han Ma , Shen Pan
Rationale and objectives
Androgen deprivation therapy (ADT) efficacy exhibits significant interindividual heterogeneity in advanced prostate cancer (PCa). This study aim to develop and validate a machine learning model based on multiparametric MRI (mpMRI) to predict the risk of Castration-Resistant Prostate Cancer (CRPC) progression in advanced PCa.
Materials and methods
In this retrospective study, 180 advanced PCa patients who underwent mpMRI before ADT were collected from two hospitals between January 2014 and October 2024. Radiomic features were selected by using variance threshold, Least Absolute Shrinkage and Selection Operator and recursive feature elimination. Random forest and logistic regression model selected clinical features. We developed eight machine learning classifiers, a stacking ensemble model by integrating the optimally performing classifier. Model performance was evaluated using confusion matrices, accuracy, precision, recall, F1-score, and area under curve (AUC). SHapley Additive exPlanations was employed for both global and local model interpretability. Intergroup differences were analyzed using one-way Analysis of Variance or Kruskal-Wallis tests.
Results
180 patients (mean age 72, range 51–90 years) were stratified by the time to CRPC into groups: very high-risk (<1 year, n = 49), high-risk (1–4 years, n = 65) and low-risk (>4 years, n = 66). The mpMRI-clinical combined model performed better than mpMRI-alone model (AUC:0.84;95 %CI:0.73, 0.92).The stacking model further enhanced CRPC prediction, internal test set (AUC: 0.89; 95 %CI:0.81, 0.93) and external test set (0.82; 95 %CI:0.72, 0.89). In low-risk group, stacking model demonstrated the strongest discriminative capability AUC (0.89;95 %CI:0.77, 0.97).
Conclusion
The Stacking model demonstrated favorable predictive capability for CRPC progression risk in advanced Pca, facilitating clinically actionable risk-stratified interventions.
{"title":"mpMRI-based interpretable machine learning model for predicting castration-resistant prostate cancer risk","authors":"Siang Shen , Bitian Liu , Yutong Li , Yiying Zeng , Shanshan Ren , Rui Yin , Han Ma , Shen Pan","doi":"10.1016/j.ejrad.2025.112521","DOIUrl":"10.1016/j.ejrad.2025.112521","url":null,"abstract":"<div><h3>Rationale and objectives</h3><div>Androgen deprivation therapy (ADT) efficacy exhibits significant interindividual heterogeneity in advanced prostate cancer (PCa). This study aim to develop and validate a machine learning model based on multiparametric MRI (mpMRI) to predict the risk of Castration-Resistant Prostate Cancer (CRPC) progression in advanced PCa.</div></div><div><h3>Materials and methods</h3><div>In this retrospective study, 180 advanced PCa patients who underwent mpMRI before ADT were collected from two hospitals between January 2014 and October 2024. Radiomic features were selected by using variance threshold, Least Absolute Shrinkage and Selection Operator and recursive feature elimination. Random forest and logistic regression model selected clinical features. We developed eight machine learning classifiers, a stacking ensemble model by integrating the optimally performing classifier. Model performance was evaluated using confusion matrices, accuracy, precision, recall, F1-score, and area under curve (AUC). SHapley Additive exPlanations was employed for both global and local model interpretability. Intergroup differences were analyzed using one-way Analysis of Variance or Kruskal-Wallis tests.</div></div><div><h3>Results</h3><div>180 patients (mean age 72, range 51–90 years) were stratified by the time to CRPC into groups: very high-risk (<1 year, n = 49), high-risk (1–4 years, n = 65) and low-risk (>4 years, n = 66). The mpMRI-clinical combined model performed better than mpMRI-alone model (AUC:0.84;95 %CI:0.73, 0.92).The stacking model further enhanced CRPC prediction, internal test set (AUC: 0.89; 95 %CI:0.81, 0.93) and external test set (0.82; 95 %CI:0.72, 0.89). In low-risk group, stacking model demonstrated the strongest discriminative capability AUC (0.89;95 %CI:0.77, 0.97).</div></div><div><h3>Conclusion</h3><div>The Stacking model demonstrated favorable predictive capability for CRPC progression risk in advanced Pca, facilitating clinically actionable risk-stratified interventions.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"195 ","pages":"Article 112521"},"PeriodicalIF":3.3,"publicationDate":"2025-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145603343","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 : 2025-11-19DOI: 10.1016/j.ejrad.2025.112554
Jing-Juan Liu , Chen Lin , Wei Liu , Liang Zhu , Chen-Xue Ma , Xuan Wang , Jia Xu , Yi-Tong Lu , Yi-Fei Zhang , Bo Jiang , Wei-Bin Wang , Feng Feng
Objective
To evaluate the performance of a non-contrast rapid magnetic resonance imaging (MRI) protocol with deep learning reconstruction (DLR) for identifying complicated appendicitis in patients with acute appendicitis, compared to conventional MRI without DLR (non-DLR) and non-contrast computed tomography (NC-CT).
Methods
Sixty-two eligible patients were enrolled, of which 55 had a final diagnosis of acute appendicitis and were included for further analysis of complications. Among them, 51 underwent both NC-CT and MRI, while 4 pregnant patients underwent MRI only. The MRI protocol included T2-weighted imaging (with and without fat suppression), T1-weighted imaging, and diffusion-weighted imaging (DWI). Two abdominal radiologists independently evaluated the subjective and objective image quality of DLR and non-DLR images using a 5-point Likert scale to assess diagnostic confidence for complicated appendicitis. Interobserver agreement (kappa statistics) and receiver operating characteristic (ROC) analysis were performed.
Results
MRI with DLR demonstrated significantly better objective and subjective image quality than non-DLR MRI, with improved appendix delineation and reduced noise (p < 0.01). With a mean acquisition time of 9.5 min, both MRI protocols outperformed NC-CT in the diagnosis of complicated appendicitis (p = 0.035 and p = 0.001, respectively). MRI-DLR achieved higher sensitivity (97.06 % vs. 88.24 %) and negative predictive value (95.45 % vs. 84.00 %) for complicated appendicitis than MRI-non-DLR. The detection rates of appendiceal wall discontinuity and peri-appendiceal abscesses were significantly higher with MRI-DLR (p < 0.05).
Conclusion
Rapid MRI with DLR improves image quality and diagnostic accuracy for complicated appendicitis compared to non-DLR MRI and NC-CT, offering a valuable alternative for radiation-sensitive patients.
{"title":"Rapid MR examination with deep learning reconstruction improves diagnosis of complicated acute appendicitis","authors":"Jing-Juan Liu , Chen Lin , Wei Liu , Liang Zhu , Chen-Xue Ma , Xuan Wang , Jia Xu , Yi-Tong Lu , Yi-Fei Zhang , Bo Jiang , Wei-Bin Wang , Feng Feng","doi":"10.1016/j.ejrad.2025.112554","DOIUrl":"10.1016/j.ejrad.2025.112554","url":null,"abstract":"<div><h3>Objective</h3><div>To evaluate the performance of a non-contrast rapid magnetic resonance imaging (MRI) protocol with deep learning reconstruction (DLR) for identifying complicated appendicitis in patients with acute appendicitis, compared to conventional MRI without DLR (non-DLR) and non-contrast computed tomography (NC-CT).</div></div><div><h3>Methods</h3><div>Sixty-two eligible patients were enrolled, of which 55 had a final diagnosis of acute appendicitis and were included for further analysis of complications. Among them, 51 underwent both NC-CT and MRI, while 4 pregnant patients underwent MRI only. The MRI protocol included T2-weighted imaging (with and without fat suppression), T1-weighted imaging, and diffusion-weighted imaging (DWI). Two abdominal radiologists independently evaluated the subjective and objective image quality of DLR and non-DLR images using a 5-point Likert scale to assess diagnostic confidence for complicated appendicitis. Interobserver agreement (kappa statistics) and receiver operating characteristic (ROC) analysis were performed.</div></div><div><h3>Results</h3><div>MRI with DLR demonstrated significantly better objective and subjective image quality than non-DLR MRI, with improved appendix delineation and reduced noise (<em>p</em> < 0.01). With a mean acquisition time of 9.5 min, both MRI protocols outperformed NC-CT in the diagnosis of complicated appendicitis (<em>p</em> = 0.035 and<!--> <em>p</em> = 0.001, respectively). MRI-DLR achieved higher sensitivity (97.06 % vs. 88.24 %) and negative predictive value (95.45 % vs. 84.00 %) for complicated appendicitis than MRI-non-DLR. The detection rates of appendiceal wall discontinuity and <em>peri</em>-appendiceal abscesses were significantly higher with MRI-DLR (<em>p</em> < 0.05).</div></div><div><h3>Conclusion</h3><div>Rapid MRI with DLR improves image quality and diagnostic accuracy for complicated appendicitis compared to non-DLR MRI and NC-CT, offering a valuable alternative for radiation-sensitive patients.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"195 ","pages":"Article 112554"},"PeriodicalIF":3.3,"publicationDate":"2025-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145603275","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 : 2025-11-19DOI: 10.1016/j.ejrad.2025.112559
Shurong Li , Zhiqiang Zhang , Yubing Zhang , Yulong Chen , Jian Ling , Qingfen Hong , Xuanling Wu , Fufu Zheng , Cheng Luo
Purpose
Intraoperative hemodynamic instability (HDI) might lead to severe complications for pheochromocytoma and paraganglioma (PPGL) patients. This study aims to construct a machine learning (ML) model to predict HDI based on intratumoral and peritumoral CT radiomics.
Materials and methods
Totally, 223 patients diagnosed with PPGL from two centers were retrospectively included and analyzed. Intratumoral and peritumoral radiomic features were derived from preoperative computed tomography (CT) imaging and then selected through least absolute shrinkage and selection operator (LASSO) algorithm. Three predictive models including intratumoral, peritumoral and fusion radiomic models were constructed by applying eight ML methods. The performance of predictive models were evaluated by receiver operating characteristic curve (ROC) with area under the curve (AUC), calibration and decision curves. Furthermore, SHapley Additive exPlanations (SHAP) analysis was used for the interpretability of the optimal model by ranking features importance.
Results
Enrolled patients were randomly divided into training cohort (n = 156) and testing cohort (n = 67). By the feature screening process, eight, fourteen and eighteen features were selected for intratumoral, peritumoral and fusion radiomic models, respectively. The fusion radiomic models exerted the best performance for predicting HDI with the AUC values of 0.840 (95 %CI: 0.779–0.901) and 0.800 (95 %CI: 0.693–0.907) in the training and testing cohort. Calibration curve indicated a high level of agreement between the predictive probabilities and observed outcomes, and further DCA showed the best clinical benefits among the three models.
Conclusion
The fusion radiomic model including intratumoral and peritumoral features is promising nonivasive tool for predicting intraoperative HDI for PPGL patients, which might facilitate individualized evaluation and management in clinical practice.
{"title":"Development and validation of an interpretable machine learning model for predicting intraoperative HDI in PPGL based on intratumoral and peritumoral CT radiomics","authors":"Shurong Li , Zhiqiang Zhang , Yubing Zhang , Yulong Chen , Jian Ling , Qingfen Hong , Xuanling Wu , Fufu Zheng , Cheng Luo","doi":"10.1016/j.ejrad.2025.112559","DOIUrl":"10.1016/j.ejrad.2025.112559","url":null,"abstract":"<div><h3>Purpose</h3><div>Intraoperative hemodynamic instability (HDI) might lead to severe complications for pheochromocytoma and paraganglioma (PPGL) patients. This study aims to construct a machine learning (ML) model to predict HDI based on intratumoral and peritumoral CT radiomics.</div></div><div><h3>Materials and methods</h3><div>Totally, 223 patients diagnosed with PPGL from two centers were retrospectively included and analyzed. Intratumoral and peritumoral radiomic features were derived from preoperative computed tomography (CT) imaging and then selected through least absolute shrinkage and selection operator (LASSO) algorithm. Three predictive models including intratumoral, peritumoral and fusion radiomic models were constructed by applying eight ML methods. The performance of predictive models were evaluated by receiver operating characteristic curve (ROC) with area under the curve (AUC), calibration and decision curves. Furthermore, SHapley Additive exPlanations (SHAP) analysis was used for the interpretability of the optimal model by ranking features importance.</div></div><div><h3>Results</h3><div>Enrolled patients were randomly divided into training cohort (n = 156) and testing cohort (n = 67). By the feature screening process, eight, fourteen and eighteen features were selected for intratumoral, peritumoral and fusion radiomic models, respectively. The fusion radiomic models exerted the best performance for predicting HDI with the AUC values of 0.840 (95 %CI: 0.779–0.901) and 0.800 (95 %CI: 0.693–0.907) in the training and testing cohort. Calibration curve indicated a high level of agreement between the predictive probabilities and observed outcomes, and further DCA showed the best clinical benefits among the three models.</div></div><div><h3>Conclusion</h3><div>The fusion radiomic model including intratumoral and peritumoral features is promising nonivasive tool for predicting intraoperative HDI for PPGL patients, which might facilitate individualized evaluation and management in clinical practice.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"195 ","pages":"Article 112559"},"PeriodicalIF":3.3,"publicationDate":"2025-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145687399","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Comment on “ Analysis of clinical and imaging characteristics of pseudocirrhosis in breast cancer liver metastasis”","authors":"Antonio Manenti , Stefania Caramaschi , Luca Reggiani Bonetti , Gianrocco Manco","doi":"10.1016/j.ejrad.2025.112563","DOIUrl":"10.1016/j.ejrad.2025.112563","url":null,"abstract":"","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"195 ","pages":"Article 112563"},"PeriodicalIF":3.3,"publicationDate":"2025-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145578560","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 : 2025-11-19DOI: 10.1016/j.ejrad.2025.112542
George Markousis-Mavrogenis , Alessia Pepe , Brittany N. Weber , Anne Hui Sze Kwong , Vassiliki Vartela , Monica Mukherjee , Juerg Schwitter , Sophie I. Mavrogeni
Myocardial fibrosis constitutes an important pathophysiologic and maladaptive process in the vast majority of cardiac diseases. Contemporary cardiologists are permitted a very nuanced glimpse of myocardial fibrosis by means of cardiovascular magnetic resonance imaging (CMR), and specifically late gadolinium enhancement (LGE) methods. These allow the evaluation of the presence, extent, and distribution of myocardial replacement fibrosis. An increasing amount of scientific evidence has demonstrated a significant role for LGE in the elucidation of cardiac pathophysiologic substrates in patients with autoimmune rheumatic diseases (ARDs) and cardiac involvement. However, whether existing methods for the evaluation of myocardial fibrosis can uniformly be extrapolated for use in patients with ARDs in their present form remains an important question. In this opinion paper, we provide a brief overview of the basic principles underlying LGE imaging, as well as the current status and challenges regarding its use in patients with and without ARDs.
{"title":"Late gadolinium enhancement in patients with and without autoimmune rheumatic diseases: “walking, we create the way”","authors":"George Markousis-Mavrogenis , Alessia Pepe , Brittany N. Weber , Anne Hui Sze Kwong , Vassiliki Vartela , Monica Mukherjee , Juerg Schwitter , Sophie I. Mavrogeni","doi":"10.1016/j.ejrad.2025.112542","DOIUrl":"10.1016/j.ejrad.2025.112542","url":null,"abstract":"<div><div>Myocardial fibrosis constitutes an important pathophysiologic and maladaptive process in the vast majority of cardiac diseases. Contemporary cardiologists are permitted a very nuanced glimpse of myocardial fibrosis by means of cardiovascular magnetic resonance imaging (CMR), and specifically late gadolinium enhancement (LGE) methods. These allow the evaluation of the presence, extent, and distribution of myocardial replacement fibrosis. An increasing amount of scientific evidence has demonstrated a significant role for LGE in the elucidation of cardiac pathophysiologic substrates in patients with autoimmune rheumatic diseases (ARDs) and cardiac involvement. However, whether existing methods for the evaluation of myocardial fibrosis can uniformly be extrapolated for use in patients with ARDs in their present form remains an important question. In this opinion paper, we provide a brief overview of the basic principles underlying LGE imaging, as well as the current status and challenges regarding its use in patients with and without ARDs.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"195 ","pages":"Article 112542"},"PeriodicalIF":3.3,"publicationDate":"2025-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145603333","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 : 2025-11-19DOI: 10.1016/j.ejrad.2025.112562
Wen Li , Renfei Zong , Jianjun Wu , Miao Wei , Wenqin Zhou , Jiayi Pu , Minghao Wu , William Lu , Fajin Lv
Purpose
To evaluate the predictive performance of areal bone mineral density (aBMD), volumetric bone mineral density (vBMD), and intermuscular adipose tissue (IMAT) for hip fracture risk using an automatic phantom-less quantitative computed tomography (PL-QCT) system.
Methods
This retrospective study included 550 patients who underwent hip or pelvic CT: 283 patients with low-energy hip fractures and 267 without fractures. Hip aBMD, vBMD, and IMAT were measured using the automatic PL-QCT system. Propensity score matching was applied to match age, sex, and body mass index between groups. The Mann–Whitney U test was used to compare parameter differences, binary logistic regression to identify independent predictors, and receiver operating characteristic (ROC) curve analysis to evaluate predictive performance.
Results
IMAT was significantly higher in the fracture group, whereas aBMD and vBMD were lower (p < 0.001). Multivariate analysis revealed vBMD as a protective factor (OR < 1, p < 0.05) and IMAT as a risk factor (OR > 1, p < 0.05). IMAT outperformed aBMD and vBMD in predicting fracture risk (AUC: 0.896, 0.768, and 0.815). The combination of IMAT and vBMD achieved the highest predictive value (AUC = 0.927).
Conclusion
Automatic PL-QCT multiparameter measurements, particularly IMAT, outperform aBMD and vBMD alone in predicting hip fracture risk and can better inform orthopedic decision-making.
目的利用自动无影定量计算机断层扫描（PL-QCT）系统评估面骨矿物质密度（aBMD）、体积骨矿物质密度（vBMD）和肌间脂肪组织（IMAT）对髋部骨折风险的预测能力。方法回顾性研究纳入550例髋部或骨盆CT患者：283例髋部低能量骨折，267例无骨折。采用全自动PL-QCT系统测量髋关节aBMD、vBMD和IMAT。采用倾向评分匹配来匹配组间年龄、性别和体重指数。采用Mann-Whitney U检验比较参数差异，采用二元logistic回归识别独立预测因子，采用受试者工作特征（ROC）曲线分析评价预测效果。结果骨折组simat显著增高，aBMD、vBMD显著降低（p < 0.001）。多因素分析显示vBMD为保护因素（OR > 1, p < 0.05）， IMAT为危险因素（OR > 1, p < 0.05）。IMAT在预测骨折风险方面优于aBMD和vBMD （AUC分别为0.896、0.768和0.815）。IMAT与vBMD联合应用的预测值最高（AUC = 0.927）。结论自动PL-QCT多参数测量，特别是IMAT，在预测髋部骨折风险方面优于aBMD和vBMD，可以更好地为骨科决策提供信息。
{"title":"Automatic phantom-less QCT predicts hip fracture risk: Bone and muscle parameters comparison","authors":"Wen Li , Renfei Zong , Jianjun Wu , Miao Wei , Wenqin Zhou , Jiayi Pu , Minghao Wu , William Lu , Fajin Lv","doi":"10.1016/j.ejrad.2025.112562","DOIUrl":"10.1016/j.ejrad.2025.112562","url":null,"abstract":"<div><h3>Purpose</h3><div>To evaluate the predictive performance of areal bone mineral density (aBMD), volumetric bone mineral density (vBMD), and intermuscular adipose tissue (IMAT) for hip fracture risk using an automatic phantom-less quantitative computed tomography (PL-QCT) system.</div></div><div><h3>Methods</h3><div>This retrospective study included 550 patients who underwent hip or pelvic CT: 283 patients with low-energy hip fractures and 267 without fractures. Hip aBMD, vBMD, and IMAT were measured using the automatic PL-QCT system. Propensity score matching was applied to match age, sex, and body mass index between groups. The Mann–Whitney <em>U</em> test was used to compare parameter differences, binary logistic regression to identify independent predictors, and receiver operating characteristic (ROC) curve analysis to evaluate predictive performance.</div></div><div><h3>Results</h3><div>IMAT was significantly higher in the fracture group, whereas aBMD and vBMD were lower (<em>p</em> < 0.001). Multivariate analysis revealed vBMD as a protective factor (OR < 1, <em>p</em> < 0.05) and IMAT as a risk factor (OR > 1, <em>p</em> < 0.05). IMAT outperformed aBMD and vBMD in predicting fracture risk (AUC: 0.896, 0.768, and 0.815). The combination of IMAT and vBMD achieved the highest predictive value (AUC = 0.927).</div></div><div><h3>Conclusion</h3><div>Automatic PL-QCT multiparameter measurements, particularly IMAT, outperform aBMD and vBMD alone in predicting hip fracture risk and can better inform orthopedic decision-making.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"195 ","pages":"Article 112562"},"PeriodicalIF":3.3,"publicationDate":"2025-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145622655","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 : 2025-11-19DOI: 10.1016/j.ejrad.2025.112556
Milán Vecsey-Nagy , Muhammad Taha Hagar , U.Joseph Schoepf , Jose Osoria-Velasquez , James Ira Griggers , Andrew J. Matuskowitz , Ava Wenderoth , Tilman Emrich , Akos Varga-Szemes
Purpose
The feasibility of CT angiography (CTA)-based fractional flow reserve (CT-FFR) has been documented in acute chest pain (ACP). The present study aimed to evaluate the impact of CT-FFR on clinical outcomes and costs in the emergency department (ED).
Methods
ACP patients with intermediate (30 − 90 %) stenosis on coronary or triple rule-out CTA were prospectively enrolled. Treatment decisions were made once the off-site CT-FFR results were available. ED length of stay (LOS), downstream test utilization (stress echocardiography, single-photon emission CT, invasive coronary angiography [ICA]), and revascularization efficiency (percutaneous coronary interventions per ICAs) were documented. Costs of care were collected for a 90-day period. The prospective cohort was compared to a control group without CT-FFR analysis matched for sex, age, and Coronary Artery Disease-Reporting and Data System category.
Results
A total of 100 patients (age: 66.2 ± 10.2 years) were enrolled and matched to 100 retrospective patients (age: 67.8 ± 10.6 years), with 39.0 % women in both groups. LOS was higher in the CT-FFR group (9.0 [6.0 − 28.0] vs. 8.0 [6.0 − 12.0] hours, p = 0.02), without differences in the rate of downstream test utilization (all p > 0.05). CT-FFR led to a higher revascularization efficiency (32.5 % [13/40] vs. 12.2 % [5/41]; p = 0.03). CT-FFR resulted in an increase in aggregate expenditures (2069.0 [1757.0 − 5135.0] vs. 879.0 [306.0 − 3684.0] $, p < 0.001) after 90 days.
Conclusions
While the utilization of CT-FFR in ACP does increase ED LOS and associated healthcare costs, the selection of patients who may benefit from subsequent ICA may prove more efficacious.
{"title":"CT Angiography-derived fractional flow reserve in the emergency department: Insights from a matched cohort analysis","authors":"Milán Vecsey-Nagy , Muhammad Taha Hagar , U.Joseph Schoepf , Jose Osoria-Velasquez , James Ira Griggers , Andrew J. Matuskowitz , Ava Wenderoth , Tilman Emrich , Akos Varga-Szemes","doi":"10.1016/j.ejrad.2025.112556","DOIUrl":"10.1016/j.ejrad.2025.112556","url":null,"abstract":"<div><h3>Purpose</h3><div>The feasibility of CT angiography (CTA)-based fractional flow reserve (CT-FFR) has been documented in acute chest pain (ACP). The present study aimed to evaluate the impact of CT-FFR on clinical outcomes and costs in the emergency department (ED).</div></div><div><h3>Methods</h3><div>ACP patients with intermediate (30 − 90 %) stenosis on coronary or triple rule-out CTA were prospectively enrolled. Treatment decisions were made once the off-site CT-FFR results were available. ED length of stay (LOS), downstream test utilization (stress echocardiography, single-photon emission CT, invasive coronary angiography [ICA]), and revascularization efficiency (percutaneous coronary interventions per ICAs) were documented. Costs of care were collected for a 90-day period. The prospective cohort was compared to a control group without CT-FFR analysis matched for sex, age, and Coronary Artery Disease-Reporting and Data System category.</div></div><div><h3>Results</h3><div>A total of 100 patients (age: 66.2 ± 10.2 years) were enrolled and matched to 100 retrospective patients (age: 67.8 ± 10.6 years), with 39.0 % women in both groups. LOS was higher in the CT-FFR group (9.0 [6.0 − 28.0] vs. 8.0 [6.0 − 12.0] hours, <em>p</em> = 0.02), without differences in the rate of downstream test utilization (all <em>p</em> > 0.05). CT-FFR led to a higher revascularization efficiency (32.5 % [13/40] vs. 12.2 % [5/41]; <em>p</em> = 0.03). CT-FFR resulted in an increase in aggregate expenditures (2069.0 [1757.0 − 5135.0] vs. 879.0 [306.0 − 3684.0] $, <em>p</em> < 0.001) after 90 days.</div></div><div><h3>Conclusions</h3><div>While the utilization of CT-FFR in ACP does increase ED LOS and associated healthcare costs, the selection of patients who may benefit from subsequent ICA may prove more efficacious.</div><div>Abbreviations: ACP, acute chest pain; CAD-RADS, Coronary Artery Disease-Reporting and Data System; CCTA, coronary CT angiography; CTA, CT angiography; CT-FFR, coronary CT angiography-derived fractional flow reserve; ED, emergency department; ICA, invasive coronary angiography; LOS, length of stay; PCI, percutaneous coronary intervention; SPECT, single-photon emission CT; TRO, triple rule-out.</div></div>","PeriodicalId":12063,"journal":{"name":"European Journal of Radiology","volume":"195 ","pages":"Article 112556"},"PeriodicalIF":3.3,"publicationDate":"2025-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145586489","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号