European Radiology最新文献

{"title":"Quantitative spectral computed tomography detects different patterns of airway wall thickening and contrast enhancement in infective lung disease: a feasibility study.","authors":"Philip Konietzke, Johanna Thomä, Oliver Weinheimer, Thuy D Do, Willi L Wagner, Arndt L Bodenberger, Wolfram Stiller, Tim F Weber, Claus P Heußel, Hans-Ulrich Kauczor, Mark O Wielpütz","doi":"10.1007/s00330-025-11752-5","DOIUrl":"https://doi.org/10.1007/s00330-025-11752-5","url":null,"abstract":"<p><strong>Objectives: </strong>We aimed to show that spectral computed tomography (CT) can identify different patterns of airway wall thickening and contrast enhancement in lung-healthy controls, coronavirus disease 2019 (COVID-19), and non-COVID-19 pneumonia patients, reflecting airway inflammation in both pneumonia subtypes and airway neovascularization in COVID-19.</p><p><strong>Materials and methods: </strong>331 subjects (age 58.9 ± 17.2 years) with 218 arterial and 113 venous phase spectral CT acquisitions were retrospectively recruited: 119 lung-healthy controls, 45 with COVID-19 and 167 with non-COVID-19 pneumonia. Scientific software was used for segmenting the airway tree. Wall thickness (WT_5-10) and the difference in median maximum airway wall attenuation (slope of the spectral attenuation curve) between 40 keV and 100 keV display energy were calculated and aggregated for subsegmental airway generations 5-10 (λHU_5-10). Descriptive statistics, correlations, t-tests, and ANOVA analyses were performed.</p><p><strong>Results: </strong>Arterial phase WT_5-10 was similarly increased in COVID-19 (1.70 ± 0.44 mm) and non-COVID-19 (1.64 ± 0.53 mm) pneumonia compared to controls (1.18 ± 0.34 mm, p < 0.001). Arterial phase λHU_5-10 was significantly higher in patients with COVID-19 pneumonia (3.09 ± 2.27 HU/keV) than in non-COVID-19 pneumonia (2.18 ± 1.54 HU/keV, p < 0.01) and lung-healthy controls (2.06 ± 1.11 HU/keV, p < 0.01).</p><p><strong>Conclusion: </strong>Spectral CT shows significant differences in segmental wall thickness and airway contrast enhancement between COVID-19 and non-COVID-19 pneumonia and lung-healthy controls. Airway contrast enhancement may be a feasible measure to detect airway inflammation in pneumonia and neovascularization in COVID-19 pneumonia.</p><p><strong>Key points: </strong>Question Is spectral CT airway contrast enhancement a feasible quantitative method to detect airway inflammation or neovascularisation? Findings Spectral CT shows significant differences in segmental wall thickness and airway contrast enhancement between COVID-19 and non-COVID-19 pneumonia, and lung-healthy controls. Clinical relevance Spectral CT can be used to assess inflammatory airway diseases such as cystic fibrosis, COPD, asthma and bronchiectasis.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144324846","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":"Concordance between single-slice abdominal computed tomography-based and bioelectrical impedance-based analysis of body composition in a prospective study.","authors":"Uli Fehrenbach, Clarissa Hosse, William Wienbrandt, Thula Walter-Rittel, Johannes Kolck, Timo Alexander Auer, Elisabeth Blüthner, Frank Tacke, Nick Lasse Beetz, Dominik Geisel","doi":"10.1007/s00330-025-11746-3","DOIUrl":"https://doi.org/10.1007/s00330-025-11746-3","url":null,"abstract":"<p><strong>Objectives: </strong>Body composition analysis (BCA) is a recognized indicator of patient frailty. Apart from the established bioelectrical impedance analysis (BIA), computed tomography (CT)-derived BCA is being increasingly explored. The aim of this prospective study was to directly compare BCA obtained from BIA and CT.</p><p><strong>Materials and methods: </strong>A total of 210 consecutive patients scheduled for CT, including a high proportion of cancer patients, were prospectively enrolled. Immediately prior to the CT scan, all patients underwent BIA. CT-based BCA was performed using a single-slice AI tool for automated detection and segmentation at the level of the third lumbar vertebra (L3). BIA-based parameters, body fat mass (BFM_BIA) and skeletal muscle mass (SMM_BIA), CT-based parameters, subcutaneous and visceral adipose tissue area (SATA_CT and VATA_CT) and total abdominal muscle area (TAMA_CT) were determined. Indices were calculated by normalizing the BIA and CT parameters to patient's weight (body fat percentage (BFP_BIA) and body fat index (BFI_CT)) or height (skeletal muscle index (SMI_BIA) and lumbar skeletal muscle index (LSMI_CT)).</p><p><strong>Results: </strong>Parameters representing fat, BFM_BIA and SATA_CT + VATA_CT, and parameters representing muscle tissue, SMM_BIA and TAMA_CT, showed strong correlations in female (fat: r = 0.95; muscle: r = 0.72; p < 0.001) and male (fat: r = 0.91; muscle: r = 0.71; p < 0.001) patients. Linear regression analysis was statistically significant (fat: R² = 0.73 (female) and 0.74 (male); muscle: R² = 0.56 (female) and 0.56 (male); p < 0.001), showing that BFI_CT and LSMI_CT allowed prediction of BFP_BIA and SMI_BIA for both sexes.</p><p><strong>Conclusion: </strong>CT-based BCA strongly correlates with BIA results and yields quantitative results for BFP and SMI comparable to the existing gold standard.</p><p><strong>Key points: </strong>Question CT-based body composition analysis (BCA) is moving more and more into clinical focus, but validation against established methods is lacking. Findings Fully automated CT-based BCA correlates very strongly with guideline-accepted bioelectrical impedance analysis (BIA). Clinical relevance BCA is currently moving further into clinical focus to improve assessment of patient frailty and individualize therapies accordingly. Comparability with established BIA strengthens the value of CT-based BCA and supports its translation into clinical routine.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144324839","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":"Development and validation of an AI-driven radiomics model using non-enhanced CT for automated severity grading in chronic pancreatitis.","authors":"Chengwei Chen, Jian Zhou, Shaojia Mo, Jing Li, Xu Fang, Fang Liu, Tiegong Wang, Li Wang, Jianping Lu, Chengwei Shao, Yun Bian","doi":"10.1007/s00330-025-11776-x","DOIUrl":"https://doi.org/10.1007/s00330-025-11776-x","url":null,"abstract":"<p><strong>Objective: </strong>To develop and validate the chronic pancreatitis CT severity model (CATS), an artificial intelligence (AI)-based tool leveraging automated 3D segmentation and radiomics analysis of non-enhanced CT scans for objective severity stratification in chronic pancreatitis (CP).</p><p><strong>Materials and methods: </strong>This retrospective study encompassed patients with recurrent acute pancreatitis (RAP) and CP from June 2016 to May 2020. A 3D convolutional neural network segmented non-enhanced CT scans, extracting 1843 radiomic features to calculate the radiomics score (Rad-score). The CATS was formulated using multivariable logistic regression and validated in a subsequent cohort from June 2020 to April 2023.</p><p><strong>Results: </strong>Overall, 2054 patients with RAP and CP were included in the training (n = 927), validation set (n = 616), and external test (n = 511) sets. CP grade I and II patients accounted for 300 (14.61%) and 1754 (85.39%), respectively. The Rad-score significantly correlated with the acinus-to-stroma ratio (p = 0.023; OR, -2.44). The CATS model demonstrated high discriminatory performance in differentiating CP severity grades, achieving an area under the curve (AUC) of 0.96 (95% CI: 0.94-0.98) and 0.88 (95% CI: 0.81-0.90) in the validation and test cohorts. CATS-predicted grades correlated with exocrine insufficiency (all p < 0.05) and showed significant prognostic differences (all p < 0.05). CATS outperformed radiologists in detecting calcifications, identifying all minute calcifications missed by radiologists.</p><p><strong>Conclusion: </strong>The CATS, developed using non-enhanced CT and AI, accurately predicts CP severity, reflects disease morphology, and forecasts short- to medium-term prognosis, offering a significant advancement in CP management.</p><p><strong>Key points: </strong>Question Existing CP severity assessments rely on semi-quantitative CT evaluations and multi-modality imaging, leading to inconsistency and inaccuracy in early diagnosis and prognosis prediction. Findings The AI-driven CATS model, using non-enhanced CT, achieved high accuracy in grading CP severity, and correlated with histopathological fibrosis markers. Clinical relevance CATS provides a cost-effective, widely accessible tool for precise CP severity stratification, enabling early intervention, personalized management, and improved outcomes without contrast agents or invasive biopsies.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144324842","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":"Contrast-enhanced CT-based prediction models for early intervention efficacy and in-hospital mortality risk in acute necrotizing pancreatitis with persistent organ failure.","authors":"Minchun Bu, Yun Zhang, Faxi Chen, Xiaochun Xie, Kaiming Li, Bo Ye, Lu Ke, Zhihui Tong, Weiqin Li, Gang Li","doi":"10.1007/s00330-025-11766-z","DOIUrl":"https://doi.org/10.1007/s00330-025-11766-z","url":null,"abstract":"<p><strong>Objective: </strong>To develop contrast-enhanced CT-based nomograms for predicting early intervention efficacy and in-hospital mortality in acute necrotizing pancreatitis (ANP) with persistent organ failure (POF).</p><p><strong>Materials and methods: </strong>This retrospective study analyzed 164 ANP patients with POF (110 in the training cohort, 54 in the validation cohort). The Sequential Organ Failure Assessment (SOFA) score was used to evaluate organ dysfunction severity. Contrast-enhanced CT parameters included mean and range CT numbers (HU) of acute necrotic collections (ANC) across anatomical regions, as well as pancreatic necrosis volume (PNV). LASSO regression identified predictors for early intervention efficacy and mortality. Nomograms were assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis.</p><p><strong>Results: </strong>Early intervention efficacy predictors included intra-abdominal pressure, cardiovascular hemodynamic changes, and PNV increase. The model demonstrated good predictive performance, with an area under the ROC curve (AUC) of 0.848 (95% CI: 0.769-0.927) in the training cohort and 0.796 (95% CI: 0.644-0.947) in the validation cohort. In-hospital mortality predictors were SOFA score, cardiovascular hemodynamic changes, mean CT number of ANC at the right anterior pararenal space, and CT number range at the left paracolic gutter. The model showed AUCs of 0.918 (training cohort, 95% CI: 0.864-0.971) and 0.860 (validation cohort, 95% CI: 0.801-0.919).</p><p><strong>Conclusion: </strong>ANP patients with intra-abdominal hypertension or significant PNV increase who maintain cardiovascular hemodynamic stability are more likely to benefit from early intervention. An elevated SOFA score, persistent cardiovascular failure, and ANC with poor homogeneity or drainage difficulty are risk factors for in-hospital mortality.</p><p><strong>Key points: </strong>Question The optimal timing for early invasive intervention remains controversial in ANP with POF. Findings Nomogram models integrating organ dysfunction severity and contrast-enhanced CT imaging features can predict treatment response and clinical outcomes in ANP patients with POF. Clinical relevance Our prediction models can identify patients who may benefit from early invasive intervention and assess in-hospital mortality risk for the entire cohort, providing a practical tool to guide clinical decision-making.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144324840","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":"CT-derived extracellular volume fraction as a predictive marker for postoperative recurrence in pStage II-III gastric cancer.","authors":"Nishimuta Yusuke, Tsurumaru Daisuke, Fujuta Nobuhiro, Kai Satohiro, Maehara Junki, Ushijima Yasuhiro, Oki Eiji, Ishigami Kousei","doi":"10.1007/s00330-025-11765-0","DOIUrl":"https://doi.org/10.1007/s00330-025-11765-0","url":null,"abstract":"<p><strong>Objective: </strong>This study assessed the prognostic value of CT-derived extracellular volume fraction (CT-ECV) in predicting postoperative recurrence in patients with pathological stage (pStage) II-III gastric cancer (GC).</p><p><strong>Materials and methods: </strong>A retrospective analysis was conducted on 112 patients with pathologically confirmed pStage II-III gastric adenocarcinoma who underwent preoperative triphasic contrast-enhanced CT and curative gastrectomy without neoadjuvant therapy. The relationship between preoperative CT-ECV and recurrence risk was evaluated using comprehensive imaging and clinicopathological data. The optimal CT-ECV threshold for recurrence prediction was determined using receiver operating characteristic (ROC) curve analysis. Disease-free survival (DFS) was assessed using Kaplan-Meier and Cox regression analyses.</p><p><strong>Results: </strong>The mean CT-ECV was 56.4 ± 16.7%. Patients with recurrence (n = 28) had significantly higher CT-ECV values than those without recurrence (n = 84) (65.3 ± 14.3% vs 53.5 ± 16.5%; p < 0.001). The optimal CT-ECV cutoff for recurrence prediction was ≥ 56.9%, with an area under the curve of 0.71 (sensitivity 82.1%, specificity 61.9%). Multivariate analysis revealed that high CT-ECV was independently associated with worse DFS (HR: 5.93; 95% CI: 1.77-19.86; p = 0.004). Patients with high CT-ECV had significantly lower DFS rates compared to those with low CT-ECV (5-year DFS rate: 49.9% vs 93.7%; p < 0.001).</p><p><strong>Conclusion: </strong>High CT-ECV values correlate with increased recurrence risk and shorter DFS in pStage II-III GC, highlighting its potential as a predictive imaging biomarker for preoperative risk stratification.</p><p><strong>Key points: </strong>Question Identifying prognostic markers is crucial for improving outcomes in stage II-III GC with high recurrence rates post-treatment. Findings High preoperative CT-ECV values are independently associated with increased recurrence risk and reduced DFS in pStage II-III GC. Clinical relevance CT-ECV can facilitate personalised treatment strategies and potentially improve patient management and outcomes.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144324841","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":"Predictors of early complete nodule shrinkage in symptomatic benign thyroid nodules treated with radiofrequency ablation with or without sclerotherapy: a retrospective study.","authors":"Yuxuan Qiu, Ting Lin, Min Feng, Minjie Shi, Lingyun Bao, Jianhua Fang","doi":"10.1007/s00330-025-11767-y","DOIUrl":"https://doi.org/10.1007/s00330-025-11767-y","url":null,"abstract":"<p><strong>Objectives: </strong>To identify factors influencing the early complete shrinkage of symptomatic benign thyroid nodules following radiofrequency ablation (RFA) with or without sclerotherapy and to predict complete nodule resolution within 2 years, thereby alleviating concerns regarding long-term follow-up outcomes.</p><p><strong>Materials and methods: </strong>Patients with symptomatic benign thyroid nodules who underwent RFA were retrospectively enrolled. The patients were grouped according to whether their nodules had completely shrunk within 2 years. Logistic regression analyses were conducted to identify independent prognostic factors associated with early complete shrinkage. These factors were subsequently integrated into predictive nomograms.</p><p><strong>Results: </strong>A total of 118 patients were included with a mean follow-up of 50.5 months. The complete nodule shrinkage rate at 2 years was 27% (32/118). Independent predictors for complete nodule shrinkage within 2 years included a smaller initial nodule volume (odds ratio (OR), 2.471; 95% confidence interval (CI), 1.516-4.027; p < 0.001), absence of posterior echogenicity enhancement (OR, 10.771; 95% CI, 1.521-76.27; p = 0.017), and reduced perinodular vascularity (OR, 8.912; 95% CI, 2.909-27.303; p < 0.001). The predictive nomogram demonstrated a high predictive value with an area under the curve of 0.9655. Furthermore, in patients receiving lauromacrogol sclerotherapy, a smaller initial nodule volume and reduced use of lauromacrogol were independent predictors.</p><p><strong>Conclusion: </strong>This study demonstrated the efficacy of RFA in treating symptomatic thyroid nodules and suggested the use of predictive factors and a nomogram to assess early shrinkage, which would facilitate personalized follow-up for patients.</p><p><strong>Key points: </strong>Question What factors predict early complete shrinkage of symptomatic benign thyroid nodules after radiofrequency ablation. Findings A smaller initial volume, the absence of posterior echogenic enhancement, and reduced perinodular vascularity on ultrasound were predictive of complete shrinkage within 2 years. Clinical relevance This study enabled physicians to better address patients' concerns regarding the pace of nodule shrinkage and the persistence of nodules even after extended periods. This understanding helps alleviate anxiety for both us and patients when determining the follow-up endpoint.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144324844","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":"From pilot to policy: what Korea's LDCT program teaches us about National Lung Cancer Screening.","authors":"Lisa Jungblut","doi":"10.1007/s00330-025-11758-z","DOIUrl":"https://doi.org/10.1007/s00330-025-11758-z","url":null,"abstract":"","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144324843","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":"Impact of the clinical role of interventional radiologists: results of the CLINTERVENTIONAL randomized controlled trial.","authors":"Pedro Blas García Jurado, Juan José Espejo Herrero, María Sagrario Lombardo Galera, María Eugenia Pérez Montilla, Sara Barranco Acosta, José García-Revillo García, Pilar Font Ugalde, Marina Álvarez Benito","doi":"10.1007/s00330-025-11757-0","DOIUrl":"https://doi.org/10.1007/s00330-025-11757-0","url":null,"abstract":"<p><strong>Objectives: </strong>To assess the impact of preprocedural consultations with interventional radiologists and explanatory videos of interventional radiology (IR) procedures on patients' knowledge, satisfaction with information and communication, and anxiety regarding the procedure.</p><p><strong>Materials and methods: </strong>A randomized, controlled, single-center trial (ClinicalTrials.gov: NCT05461482) was conducted between August 2022 and April 2024. Patients scheduled for certain IR procedures were included. They were randomly assigned to a control group (standard information from the ordering physician) or experimental group (additional consultation with an interventional radiologist and access to explanatory videos about the procedures). Knowledge of the procedures (measured via multiple-choice questionnaires), satisfaction with the information and communication (Likert scales), and anxiety (Likert scale and State-Trait Anxiety Inventory) were assessed. Statistical analyses included Student's t-test, the chi-square test, and mixed analysis of variance.</p><p><strong>Results: </strong>Four hundred thirty patients (mean age, 62 years (13); 267 men) were included. The experimental group (n = 214), compared to the control group (n = 216), showed greater understanding of the procedures (10.5 (1.9) vs 5.1 (3.2); p < 0.001) and greater satisfaction with the information (8.9 (1.5) vs 6.5 (3.3); p < 0.001) and communication (8.7 (1.7) vs 6.4 (2.8); p < 0.001). Anxiety was lower in the experimental group according to the State-Trait Anxiety Inventory (42.9 (12.7) vs 45.7 (12.4); p = 0.02). 99.5% (207/208) of patients in the experimental group felt the video helped them understand the intervention.</p><p><strong>Conclusions: </strong>Preprocedural consultations by interventional radiologists improve patients' understanding of the procedure, increase their satisfaction with information and communication, and reduce anxiety during the procedure.</p><p><strong>Key points: </strong>Question Technical advances in IR lack parallel clinical role development, possibly limiting preprocedural information. This study evaluates preprocedural consultations and videos to address this gap. Findings Preprocedural consultations with interventional radiologists and explanatory videos enhance patient knowledge, improve satisfaction with information and communication, and reduce procedure-related anxiety. Clinical relevance Structured preprocedural communication, including consultations with radiologists and explanatory videos, optimizes patients' understanding, satisfaction with information and communication, and emotional well-being, reinforcing the importance of patient-centered care in IR.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144316218","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":"Risk factors and prognostic indicators for progressive fibrosing interstitial lung disease: a deep learning-based CT quantification approach.","authors":"Kanghwi Lee, Jong Hyuk Lee, Seok Young Koh, Hyungin Park, Jin Mo Goo","doi":"10.1007/s00330-025-11714-x","DOIUrl":"https://doi.org/10.1007/s00330-025-11714-x","url":null,"abstract":"<p><strong>Objectives: </strong>To investigate the value of deep learning-based quantitative CT (QCT) in predicting progressive fibrosing interstitial lung disease (PF-ILD) and assessing prognosis.</p><p><strong>Materials and methods: </strong>This single-center retrospective study included ILD patients with CT examinations between January 2015 and June 2021. Each ILD finding (ground-glass opacity (GGO), reticular opacity (RO), honeycombing) and fibrosis (sum of RO and honeycombing) was quantified from baseline and follow-up CTs. Logistic regression was performed to identify predictors of PF-ILD, defined as radiologic progression along with forced vital capacity (FVC) decline ≥ 5% predicted. Cox proportional hazard regression was used to assess mortality. The added value of incorporating QCT into FVC was evaluated using C-index.</p><p><strong>Results: </strong>Among 465 ILD patients (median age [IQR], 65 [58-71] years; 238 men), 148 had PF-ILD. After adjusting for clinico-radiological variables, baseline RO (OR: 1.096, 95% CI: 1.042, 1.152, p < 0.001) and fibrosis extent (OR: 1.035, 95% CI: 1.004, 1.067, p = 0.025) were PF-ILD predictors. Baseline RO (HR: 1.063, 95% CI: 1.013, 1.115, p = 0.013), honeycombing (HR: 1.074, 95% CI: 1.034, 1.116, p < 0.001), and fibrosis extent (HR: 1.067, 95% CI: 1.043, 1.093, p < 0.001) predicted poor prognosis. The Cox models combining baseline percent predicted FVC with QCT (each ILD finding, C-index: 0.714, 95% CI: 0.660, 0.764; fibrosis, C-index: 0.703, 95% CI: 0.649, 0.752; both p-values < 0.001) outperformed the model without QCT (C-index: 0.545, 95% CI: 0.500, 0.599).</p><p><strong>Conclusion: </strong>Deep learning-based QCT for ILD findings is useful for predicting PF-ILD and its prognosis.</p><p><strong>Key points: </strong>Question Does deep learning-based CT quantification of interstitial lung disease (ILD) findings have value in predicting progressive fibrosing ILD (PF-ILD) and improving prognostication? Findings Deep learning-based CT quantification of baseline reticular opacity and fibrosis predicted the development of PF-ILD. In addition, CT quantification demonstrated value in predicting all-cause mortality. Clinical relevance Deep learning-based CT quantification of ILD findings is useful for predicting PF-ILD and its prognosis. Identifying patients at high risk of PF-ILD through CT quantification enables closer monitoring and earlier treatment initiation, which may lead to improved clinical outcomes.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144316219","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":"Effects of patient and imaging factors on small bowel motility scores derived from deep learning-based segmentation of cine MRI.","authors":"Subin Heo, Jihye Yun, Dong Wook Kim, Seo Young Park, Sang Hyun Choi, Kyuwon Kim, Kee Wook Jung, Seung-Jae Myung, Seong Ho Park","doi":"10.1007/s00330-025-11737-4","DOIUrl":"https://doi.org/10.1007/s00330-025-11737-4","url":null,"abstract":"<p><strong>Objectives: </strong>Small bowel motility can be quantified using cine MRI, but the influence of patient and imaging factors on motility scores remains unclear. This study evaluated whether patient and imaging factors affect motility scores derived from deep learning-based segmentation of cine MRI.</p><p><strong>Materials and methods: </strong>Fifty-four patients (mean age 53.6 ± 16.4 years; 34 women) with chronic constipation or suspected colonic pseudo-obstruction who underwent cine MRI covering the entire small bowel between 2022 and 2023 were included. A deep learning algorithm was developed to segment small bowel regions, and motility was quantified with an optical flow-based algorithm, producing a motility score for each slice. Associations of motility scores with patient factors (age, sex, body mass index, symptoms, and bowel distension) and MRI slice-related factors (anatomical location, bowel area, and anteroposterior position) were analyzed using linear mixed models.</p><p><strong>Results: </strong>Deep learning-based small bowel segmentation achieved a mean volumetric Dice similarity coefficient of 75.4 ± 18.9%, with a manual correction time of 26.5 ± 13.5 s. Median motility scores per patient ranged from 26.4 to 64.4, with an interquartile range of 3.1-26.6. Multivariable analysis revealed that MRI slice-related factors, including anatomical location with mixed ileum and jejunum (β = -4.9; p = 0.01, compared with ileum dominant), bowel area (first order β = -0.2, p < 0.001; second order β = 5.7 × 10^-4, p < 0.001), and anteroposterior position (first order β = -51.5, p < 0.001; second order β = 28.8, p = 0.004) were significantly associated with motility scores. Patient factors showed no association with motility scores.</p><p><strong>Conclusion: </strong>Small bowel motility scores were significantly associated with MRI slice-related factors. Determining global motility without adjusting for these factors may be limited.</p><p><strong>Key points: </strong>Question Global small bowel motility can be quantified from cine MRI; however, the confounding factors affecting motility scores remain unclear. Findings Motility scores were significantly influenced by MRI slice-related factors, including anatomical location, bowel area, and anteroposterior position. Clinical relevance Adjusting for slice-related factors is essential for accurate interpretation of small bowel motility scores on cine MRI.</p>","PeriodicalId":12076,"journal":{"name":"European Radiology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144316216","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}