European Radiology最新文献

{"title":"Risk prediction for elderly cognitive impairment by radiomic and morphological quantification analysis based on a cerebral MRA imaging cohort.","authors":"Xian Xu, Yanfeng Zhou, Shasha Sun, Longbiao Cui, Zhiye Chen, Yuanhao Guo, Jiacheng Jiang, Xinjiang Wang, Ting Sun, Qian Yang, Yujia Wang, Yuan Yuan, Li Fan, Ge Yang, Feng Cao","doi":"10.1007/s00330-024-11336-9","DOIUrl":"10.1007/s00330-024-11336-9","url":null,"abstract":"<p><strong>Objective: </strong>To establish morphological and radiomic models for early prediction of cognitive impairment associated with cerebrovascular disease (CI-CVD) in an elderly cohort based on cerebral magnetic resonance angiography (MRA).</p><p><strong>Methods: </strong>One-hundred four patients with CI-CVD and 107 control subjects were retrospectively recruited from the 14-year elderly MRA cohort, and 63 subjects were enrolled for external validation. Automated quantitative analysis was applied to analyse the morphological features, including the stenosis score, length, relative length, twisted angle, and maximum deviation of cerebral arteries. Clinical and morphological risk factors were screened using univariate logistic regression. Radiomic features were extracted via least absolute shrinkage and selection operator (LASSO) regression. The predictive models of CI-CVD were established in the training set and verified in the external testing set.</p><p><strong>Results: </strong>A history of stroke was demonstrated to be a clinical risk factor (OR 2.796, 1.359-5.751). Stenosis ≥ 50% in the right middle cerebral artery (RMCA) and left posterior cerebral artery (LPCA), maximum deviation of the left internal carotid artery (LICA), and twisted angles of the right internal carotid artery (RICA) and LICA were identified as morphological risk factors, with ORs of 4.522 (1.237-16.523), 2.851 (1.438-5.652), 1.373 (1.136-1.661), 0.981 (0.966-0.997) and 0.976 (0.958-0.994), respectively. Overall, 33 radiomic features were screened as risk factors. The clinical-morphological-radiomic model demonstrated optimal performance, with an AUC of 0.883 (0.838-0.928) in the training set and 0.843 (0.743-0.943) in the external testing set.</p><p><strong>Conclusion: </strong>Radiomics features combined with morphological indicators of cerebral arteries were effective indicators for early signs of CI-CVD in elderly individuals.</p><p><strong>Key points: </strong>Question The relationship between morphological features of cerebral arteries and cognitive impairment associated with cerebrovascular disease (CI-CVD) deserves to be explored. Findings The multipredictor model combining with stroke history, vascular morphological indicators and radiomic features of cerebral arteries demonstrated optimal performance for the early warning of CI-CVD. Clinical relevance Stenosis percentage and tortuosity score of the cerebral arteries are important risk factors for cognitive impairment. The radiomic features combined with morphological quantification analysis based on cerebral MRA provide higher predictive performance of CI-CVD.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"4300-4314"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142946820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Implementing an AI algorithm in the clinical setting: a case study for the accuracy paradox.","authors":"John A Scaringi, Ryan A McTaggart, Matthew D Alvin, Michael Atalay, Michael H Bernstein, Mahesh V Jayaraman, Gaurav Jindal, Jonathan S Movson, David W Swenson, Grayson L Baird","doi":"10.1007/s00330-024-11332-z","DOIUrl":"10.1007/s00330-024-11332-z","url":null,"abstract":"<p><strong>Objectives: </strong>We report our experience implementing an algorithm for the detection of large vessel occlusion (LVO) for suspected stroke in the emergency setting, including its performance, and offer an explanation as to why it was poorly received by radiologists.</p><p><strong>Materials and methods: </strong>An algorithm was deployed in the emergency room at a single tertiary care hospital for the detection of LVO on CT angiography (CTA) between September 1st-27th, 2021. A retrospective analysis of the algorithm's accuracy was performed.</p><p><strong>Results: </strong>During the study period, 48 patients underwent CTA examination in the emergency department to evaluate for emergent LVO, with 2 positive cases (60.3 years ± 18.2; 32 women). The LVO algorithm demonstrated a sensitivity and specificity of 100% and 92%, respectively. While the sensitivity of the algorithm at our institution was even higher than the manufacturer's reported values, the false discovery rate was 67%, leading to the perception that the algorithm was inaccurate. In addition, the positive predictive value at our institution was 33% compared with the manufacturer's reported values of 95-98%. This disparity can be attributed to differences in disease prevalence of 4.1% at our institution compared with 45.0-62.2% from the manufacturer's reported values.</p><p><strong>Conclusion: </strong>Despite the LVO algorithm's accuracy performing as advertised, it was perceived as inaccurate due to more false positives than anticipated and was removed from clinical practice. This was likely due to a cognitive bias called the accuracy paradox. To mitigate the accuracy paradox, radiologists should be presented with metrics based on a disease prevalence similar to their practice when evaluating and utilizing artificial intelligence tools.</p><p><strong>Key points: </strong>Question An artificial intelligence algorithm for detecting emergent LVOs was implemented in an emergency department, but it was perceived to be inaccurate. Findings Although the algorithm's accuracy was both high and as advertised, the algorithm demonstrated a high false discovery rate. Clinical relevance The misperception of the algorithm's inaccuracy was likely due to a special case of the base rate fallacy-the accuracy paradox. Equipping radiologists with an algorithm's false discovery rate based on local prevalence will ensure realistic expectations for real-world performance.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"4347-4353"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142909070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spectral CT-based nomogram for evaluation of neoadjuvant chemotherapy response in esophageal squamous cell carcinoma.","authors":"Jing Wang, Yueqiang Zhu, Qian Li, Lining Wang, Haiman Bian, Xiaomei Lu, Zhaoxiang Ye","doi":"10.1007/s00330-024-11294-2","DOIUrl":"10.1007/s00330-024-11294-2","url":null,"abstract":"<p><strong>Objectives: </strong>To establish a spectral CT-based nomogram for predicting the response to neoadjuvant chemotherapy (NAC) in patients with locally advanced esophageal squamous cell carcinoma (ESCC).</p><p><strong>Methods: </strong>This retrospective study included 172 patients with ESCC who underwent spectral CT scans before NAC followed by resection. Based on postoperative tumor regression grades (TRG), 34% (58) of patients were responsive (TRG1) and 66% (114) were non-responsive (TRG2-3). The data was divided into a primary set of 120 and a validation set of 52, maintaining a 7:3 random ratio. Measurements included iodine concentration (IC), normalized iodine concentration (nIC), CT_40kev, CT_70kev, spectral attenuation curve slope (λHU), and effective atomic number (Zeff) during non-contrast and venous phases (VP). Clinicopathologic characteristics were collected. Univariable and multivariable logistic regressions identified independent predictors of NAC response. The model was visualized using nomograms, and its efficacy was assessed via receiver operating characteristic (ROC) curves.</p><p><strong>Results: </strong>Multivariable logistic regression analysis identified the neutrophil-to-lymphocyte ratio (NLR), clinical stage, ZeffVP, and nICVP as independent predictors of NAC response. The nomogram incorporating all four independent predictors, outperformed spectral CT and the clinical model with the highest AUCs of 0.825 (95% CI: 0.746-0.895) for the primary set and 0.794 (95% CI: 0.635-0.918) for the validation set (DeLong test: all p < 0.05).</p><p><strong>Conclusions: </strong>The spectral CT and clinical models were useful in predicting NAC response in ESCC patients. Combining spectral CT imaging parameters and clinicopathologic characteristics in a nomogram improved predictive accuracy.</p><p><strong>Key points: </strong>Question Developing a non-invasive, practical tool to predict ESCC's response to chemotherapy is crucial and has not yet been done. Findings This nomogram, incorporating clinicopathologic characteristics and spectral CT-derived parameters, predicted NAC response in ESCC patients. Clinical relevance This spectral CT-based nomogram is a non-invasive and easily obtainable tool for accurately predicting ESCC response to NAC, aiding clinicians in personalized treatment planning.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"3800-3811"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142893366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Identifying threshold of CT-defined muscle loss after radiotherapy for survival in oral cavity cancer using machine learning.","authors":"Jie Lee, Jhen-Bin Lin, Wan-Chun Lin, Ya-Ting Jan, Yi-Shing Leu, Yu-Jen Chen, Kun-Pin Wu","doi":"10.1007/s00330-024-11303-4","DOIUrl":"10.1007/s00330-024-11303-4","url":null,"abstract":"<p><strong>Objectives: </strong>Muscle loss after radiotherapy is associated with poorer survival in patients with oral cavity squamous cell carcinoma (OCSCC). However, the threshold of muscle loss remains unclear. This study aimed to utilize explainable artificial intelligence to identify the threshold of muscle loss associated with survival in OCSCC.</p><p><strong>Materials and methods: </strong>We enrolled 1087 patients with OCSCC treated with surgery and adjuvant radiotherapy at two tertiary centers (660 in the derivation cohort and 427 in the external validation cohort). Skeletal muscle index (SMI) was measured using pre- and post-radiotherapy computed tomography (CT) at the C3 vertebral level. Random forest (RF), eXtreme Gradient Boosting (XGBoost), and Categorical Boosting (CatBoost) models were developed to predict all-cause mortality, and their performances were evaluated using the area under the curve (AUC). Muscle loss threshold was identified using the SHapley Additive exPlanations (SHAP) method and validated using Cox regression analysis.</p><p><strong>Results: </strong>In the external validation cohort, the RF, XGBoost, and CatBoost models achieved favorable performance in predicting all-cause mortality (AUC: 0.898, 0.859, and 0.842). The SHAP method demonstrated that SMI change after radiotherapy was the most important feature for predicting all-cause mortality and consistently identified SMI loss ≥ 4.2% as the threshold in all three models. In multivariable analysis, SMI loss ≥ 4.2% was independently associated with increased all-cause mortality risk in both cohorts (derivation cohort: hazard ratio: 6.66, p < 0.001; external validation cohort: hazard ratio: 8.46, p < 0.001).</p><p><strong>Conclusion: </strong>This study can assist clinicians in identifying patients with considerable muscle loss after treatment and guide interventions to improve muscle mass.</p><p><strong>Key points: </strong>Question Muscle loss after radiotherapy is associated with poorer survival in patients with oral cavity cancer; however, the threshold of muscle loss remains unclear. Findings Explainable artificial intelligence identified muscle loss ≥ 4.2% as the threshold of increased all-cause mortality risk in both derivation and external validation cohorts. Clinical Relevance Muscle loss ≥ 4.2% may be the optimal threshold for survival in patients who receive adjuvant radiotherapy for oral cavity cancer. This threshold can guide clinicians in improving muscle mass after radiotherapy.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"4289-4299"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142871200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved detection of brain metastases using contrast-enhanced 3D black-blood TSE sequences compared to post-contrast 3D T1 GRE: a comparative study on 1.5-T MRI.","authors":"Zhao Hui Chen Zhou, Elena Salvador Álvarez, Amaya Hilario, Agustín Cárdenas Del Carre, Juan Romero Coronado, Carmen Lechuga, Ana Martínez de Aragón, Ana Ramos González","doi":"10.1007/s00330-025-11363-0","DOIUrl":"10.1007/s00330-025-11363-0","url":null,"abstract":"<p><strong>Objectives: </strong>Brain metastases are the most common intracranial malignancy in adults, and their detection is crucial for treatment planning. Post-contrast 3D T1 gradient-recalled echo (GRE) sequences are commonly used for this purpose, but contrast-enhanced 3D T1 turbo spin-echo (TSE) sequences with motion-sensitized driven-equilibrium (MSDE) technique (\"black blood\") may offer improved detection. This study aimed to compare the effectiveness of contrast-enhanced 3D black blood sequences to standard 3D T1 GRE sequences in detecting brain metastases on a 1.5-T MRI.</p><p><strong>Materials and methods: </strong>A retrospective analysis of 183 patients with suspected or follow-up brain metastases between May 2022 and September 2023 was conducted. Among these patients, 107 were included in the final analysis. Both post-contrast 3D T1 GRE and 3D black blood sequences were acquired on the same scanner with similar acquisition times. Two neuroradiologists independently evaluated the images for the number, size, and location of metastases. Interobserver variability and statistical analysis were performed.</p><p><strong>Results: </strong>Among the 107 patients (mean age 60.8 years ± 13.2 years; 55 males, 52 females), 3D black blood sequences detected a significantly higher number of brain metastases, particularly small lesions (< 5 mm), compared to 3D T1 GRE sequences (p < 0.05). There was no significant difference in detecting large metastases (≥ 5 mm) between the sequences. In addition, the black blood sequences provided better conspicuity of metastases in the majority of patients (85%).</p><p><strong>Conclusion: </strong>Contrast-enhanced 3D T1 TSE with MSDE (\"black blood\") sequences offer improved detection of brain metastases, especially small lesions, on 1.5-T MRI compared to standard 3D T1 GRE sequences.</p><p><strong>Key points: </strong>Question Accurate identification of the number and location of brain metastases using MRI is essential for planning and managing effective treatment. Findings Contrast-enhanced 3D T1 TSE black blood sequences detected significantly more small brain metastases than standard 3D T1 GRE sequences on 1.5-T MRI. Clinical relevance The use of 3D black blood sequences on 1.5-T MRI may have the potential to improve the accuracy of detection of brain metastases, leading to better treatment planning and potentially improved patient outcomes.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"4267-4276"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143002437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Separating dementia with Lewy bodies from Alzheimer's disease dementia using a volumetric MRI classifier.","authors":"Aniek M van Gils, Antti J Tolonen, Hanneke F M Rhodius-Meester, Patrizia Mecocci, Ritva Vanninen, Kristian Steen Frederiksen, Frederik Barkhof, Bas Jasperse, Jyrki Lötjönen, Wiesje M van der Flier, Afina W Lemstra","doi":"10.1007/s00330-024-11257-7","DOIUrl":"10.1007/s00330-024-11257-7","url":null,"abstract":"<p><strong>Objectives: </strong>Distinguishing dementia with Lewy bodies (DLB) from Alzheimer's disease (AD) dementia, particularly in patients with DLB and concomitant AD pathology (DLB/AD+), can be challenging and there is no specific MRI signature for DLB. The aim of this study is to examine the additional value of MRI-based brain volumetry in separating patients with DLB (AD+/-) from patients with AD and controls.</p><p><strong>Methods: </strong>We included 1518 participants from four cohorts (ADC, ADNI, PDBP and PredictND); 147 were patients with DLB (n = 76, DLB/AD+; n = 71, DLB/AD-), 668 patients with AD dementia, and 703 controls. We used an automatic segmentation tool to compute volumes of 70 brain regions, for which age, sex, and head size-dependent z-scores were calculated. We compared individual regions between the diagnostic groups and evaluated whether combining multiple regions improves differentiation. To assess the diagnostic performance, we used the area under the receiver operating characteristic curve (AUC) and sensitivity.</p><p><strong>Results: </strong>The classifier using the combination of 70 volumetric brain regions correctly classified 60% of patients with DLB and 70% of patients with AD dementia. For DLB vs. AD, the classifier produced an AUC of 0.80 (0.77-0.83), which outperformed the best individual region, hippocampus (AUC: 0.73 [0.69-0.76], p < 0.01). For the comparison of DLB/AD+ vs. AD, the classifier increased the AUC to 0.74 (0.68-0.80), which was 0.70 (0.64-0.76) for the hippocampus, p = 0.25.</p><p><strong>Conclusion: </strong>Using a combination of volumetric brain regions improved the classification accuracy, and thus the discrimination, of patients with DLB with and without concomitant AD pathology and AD.</p><p><strong>Key points: </strong>Question No specific MRI signature for dementia with Lewy bodies (DLB) exists, making the differential diagnosis challenging, especially with dementia due to Alzheimer's disease (AD). Findings Volumes of individual brain regions defined by automatic MRI segmentation differed between DLB and AD patients and controls. Clinical relevance Automatic MRI segmentation can contribute to improving the discrimination of patients with DLB and AD, especially in non-specialized memory clinics.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"3753-3767"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142909286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The importance of the radiologist in the pre-therapeutic evaluation and follow-up of advanced ovarian cancer.","authors":"Henrik Leonhardt","doi":"10.1007/s00330-025-11455-x","DOIUrl":"10.1007/s00330-025-11455-x","url":null,"abstract":"","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"4027-4028"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144005149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing the stability of photon-counting CT: insights from a 2-year longitudinal study.","authors":"Leening P Liu, Pouyan Pasyar, Fang Liu, Quy Cao, Olivia F Sandvold, Martin V Rybertt, Pooyan Sahbaee, Russell T Shinohara, Harold I Litt, Peter B Noël","doi":"10.1007/s00330-024-11244-y","DOIUrl":"10.1007/s00330-024-11244-y","url":null,"abstract":"<p><strong>Objective: </strong>Among the advancements in computed tomography (CT) technology, photon-counting computed tomography (PCCT) stands out as a significant innovation, providing superior spectral imaging capabilities while simultaneously reducing radiation exposure. Its long-term stability is important for clinical care, especially longitudinal studies, but is currently unknown. This study sets out to comprehensively analyze the long-term stability of a first-generation clinical PCCT scanner.</p><p><strong>Methods: </strong>Over a 2-year period, from November 2021 to November 2023, we conducted weekly identical experiments utilizing the same multi-energy CT protocol. Throughout this period, notable software and hardware modifications were meticulously recorded. Various tissue-mimicking inserts were scanned weekly to rigorously assess the stability of Hounsfield Units (HU) and image noise in Virtual Monochromatic Images (VMIs) and iodine density maps.</p><p><strong>Results: </strong>Spectral results consistently demonstrated the quantitative stability of PCCT. VMIs exhibited stable HU values, such as variation in relative error for VMI 70 keV measuring 0.11% and 0.30% for single-source and dual-source modes, respectively. Similarly, noise levels remained stable with slight fluctuations linked to software changes for VMI 40 and 70 keV that corresponded to changes of 8 and 1 HU, respectively. Furthermore, iodine density quantification maintained stability and showed significant improvement with software and hardware changes, especially in dual-source mode with nominal errors decreasing from 1.44 to 0.03 mg/mL.</p><p><strong>Conclusion: </strong>This study provides the first long-term reproducibility assessment of quantitative PCCT imaging, highlighting its potential for the clinical arena.</p><p><strong>Key points: </strong>Question Photon-counting CT (PCCT) provides critical spectral imaging for improved diagnostic accuracy, but its long-term quantitative stability over time is still unknown. Findings The clinical PCCT system demonstrated stable Hounsfield Units (HU) and image noise over 2 years, ensuring reliable quantitative imaging and improving diagnostic accuracy. Clinical relevance This study showcased the exceptional value of PCCT in diagnostic radiology, particularly for its application in longitudinal studies.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"3721-3728"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12165871/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142863201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Methodological issues in radiomics: impact on accuracy of MRI for predicting response to neoadjuvant chemotherapy in breast cancer.","authors":"Sofia Netti, Oriana D'Ecclesiis, Federica Corso, Francesca Botta, Daniela Origgi, Filippo Pesapane, Giorgio Maria Agazzi, Anna Rotili, Aurora Gaeta, Elisa Scalco, Giovanna Rizzo, Barbara Alicja Jereczek-Fossa, Enrico Cassano, Giuseppe Curigliano, Sara Gandini, Sara Raimondi","doi":"10.1007/s00330-024-11260-y","DOIUrl":"10.1007/s00330-024-11260-y","url":null,"abstract":"<p><strong>Aim: </strong>To investigate whether methodological aspects may influence the performance of MRI-radiomic models to predict response to neoadjuvant treatment (NAT) in breast cancer (BC) patients.</p><p><strong>Materials and methods: </strong>We conducted a systematic review until March 2023. A random-effects meta-analysis was performed to combine the area under the receiver operating characteristic curve (AUC) values. Publication bias was assessed using Egger's test and heterogeneity was estimated by I². A meta-regression was conducted to investigate the impact of various factors, including scanner, features' number/transformation/type, pixel/voxel scaling, etc. RESULTS: Forty-two studies were included. The summary AUC was 0.77 (95% CI: 0.74-0.81). Substantial heterogeneity was observed (I² = 81%) with no publication bias (p = 0.35). Radiomic model accuracy was influenced by the scanner vendor, with lower AUCs in studies using mixed scanner vendors (AUC; 95% CI: 0.70; 0.61-0.78) compared to studies including images obtained from the same scanner (AUC (95% CI): 0.83 (0.77-0.88), 0.74 (0.67-0.82), 0.83 (0.78-0.89) for three different vendors; vendors 1, 2, and 3, respectively; p-value = 0.03 for comparison with vendor 1). Feature type also seemed to have an impact on the AUC, with higher prediction accuracy observed for studies using 3D than 2D/2.5D images (AUC; 95% CI: 0.81; 0.78-0.85 and 0.73; 0.65-0.81, respectively, p-value = 0.03). Non-significant between-study heterogeneity was observed in the studies including 3D images (I² = 33%) and Vendor 1 scanners (I² = 40%).</p><p><strong>Conclusion: </strong>MRI-radiomics has emerged as a potential method for predicting the response to NAT in BC patients, showing promising outcomes. Nevertheless, it is important to acknowledge the diversity among the methodological choices applied. Further investigations should prioritize achieving standardized protocols, and enhancing methodological rigor in MRI-radiomics.</p><p><strong>Key points: </strong>Question Do methodological aspects influence the performance of MRI-radiomic models in predicting response to NAT in BC patients? Findings Radiomic model accuracy was influenced by the scanner vendor and feature type. Clinical relevance Methodological discrepancies affect the performance of MRI-radiomic models. Developing standardized protocols and enhancing methodological rigor in these studies should be prioritized.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"4325-4334"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142863654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"How useful is contrast-enhanced MRI in the long-term surveillance of glioma? A multicentre retrospective longitudinal cohort study.","authors":"Marcus Cakmak, Sepehr Mohammadian, Vera C W Keil, Joost W Schouten, Philip C de Witt Hamer, Thijs van der Vaart, Rutger K Balvers, Ivar J H G Wamelink, Frederik Barkhof, Martin van den Bent, Mark Vries, Marion Smits","doi":"10.1007/s00330-024-11333-y","DOIUrl":"10.1007/s00330-024-11333-y","url":null,"abstract":"<p><strong>Objective: </strong>To examine whether MRI with routine gadolinium-based contrast agent (GBCA) administration in the long-term surveillance of adult-type diffuse glioma identifies tumour progression earlier than T2-weighted (T2w) and/or T2w fluid-attenuated inversion recovery (FLAIR) MRI only.</p><p><strong>Materials and methods: </strong>In this longitudinal retrospective multicentre cohort study patients with histopathologically confirmed adult-type diffuse glioma and at least two years survival after diagnosis in 2009-2010 were included. Progression was determined by the treating physician or during the multidisciplinary team meeting and defined as the moment a change in treatment or follow-up was required. The primary outcome was the proportion of patients that showed an increase of abnormalities on both contrast-enhanced T1-weighted (CET1w) and T2w/T2w-FLAIR at the time of progression. Chi-square testing was performed to analyse the relationship between the detection of progression on both scan sequences, with calculating the Phi coefficient to determine the degree of association.</p><p><strong>Results: </strong>One hundred eight consecutive patients were included (58 male; 53 grade 2, 21 grade 3, 34 grade 4). Progression was present in 82 patients and was determined on both CET1w and T2w/T2w-FLAIR images in 59 patients (72.0%). In 20 patients (24.4%), progression was determined based solely on T2w/T2w-FLAIR abnormalities. Only three patients showed progression exclusively on CET1w (3.7%). There was a strong positive significant relationship between the detection of progression on both scan types (p < 0.001; Phi = 0.467).</p><p><strong>Conclusion: </strong>An increase in CET1w abnormalities was generally accompanied by an increase in T2w/T2w-FLAIR abnormalities, raising the question of whether routine administration of GBCA is always necessary for long-term survivors of glioma.</p><p><strong>Key points: </strong>Question Long-term survivors with glioma undergo many contrast-enhanced MRI scans, which involve a patient, financial, and environmental burden. Findings In almost all patients, an increase in T2w/T2w-FLAIR abnormalities was present at the time of tumour progression, mostly but not always accompanying contrast-enhancing findings. Clinical relevance T2w/T2-FLAIR MRI seems to detect glioma progression in long-term surviving patients similar to contrast-enhanced T1w MRI, raising the question of whether the routine administration of GBCA is necessary and justified in patients under long-term surveillance of glioma.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":"4257-4266"},"PeriodicalIF":4.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12165967/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143522994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}