Academic Radiology最新文献

{"title":"Quantification of Intratumoral Heterogeneity Based on Habitat Analysis for Preoperative Assessment of Lymphovascular Invasion in Colorectal Cancer.","authors":"Yexin Su, Hongyue Zhao, Zhehao Lyu, Peng Xu, Ziyue Zhang, Huiting Zhang, Mengjiao Wang, Lin Tian, Peng Fu","doi":"10.1016/j.acra.2025.03.014","DOIUrl":"https://doi.org/10.1016/j.acra.2025.03.014","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>Preoperative knowledge of the status of lymphovascular invasion (LVI) status in colorectal cancer (CRC) patients can provide valuable information for choosing appropriate treatment strategies. This study aimed to explore the value of heterogeneity features derived from the habitat analysis of ¹⁸F-fluorodeoxyglucose (FDG) positron emission tomography (PET) images in predicting LVI.</p><p><strong>Materials and methods: </strong>Pretreatment ¹⁸F-FDG PET/computed tomography (CT) images from 177 patients diagnosed with CRC were retrospectively obtained (training cohort, n=106; validation cohort, n=71). Conventional radiomics features and habitat-derived tumor heterogeneity features were extracted from ¹⁸F-FDG PET scans. The output probabilities of the imaging-based random forest model were used to generate a radiomics score (Radscore) and intratumoral heterogeneity score (ITHscore). Multivariate logistic regression analysis was used to determine the independent risk factors for LVI. On this basis, four LVI status classification models were developed using (a) clinical variables (Clinical model), (b) tumor heterogeneity features (ITHscore model), (c) radiomics features (Radscore model), and (d) clinical variables, tumor heterogeneity features, and radiomics features (Combined model). The area under the curve (AUC) and decision curve analysis were used to evaluate model performance.</p><p><strong>Results: </strong>Among all of the variables, the PET/CT-reported lymph node status, ITHscore, and Radscore were retained as predictors related to the risk of LVI in CRC patients (P<0.05). The predictive effect of the ITHscore model (AUC: 0.712) was better than that of the Radscore model (AUC: 0.650) and Clinical model (AUC: 0.652) in the validation cohort. The Combined model achieved better classification effects and clinical usefulness, and the AUCs of the training and validation cohorts were 0.857 and 0.798, respectively. A nomogram of the Combined model was established, and the calibration plot was well fitted (P>0.05). In addition, the results of Spearman's rank correlation tests showed that there was no significant correlation between the ITHscore and Radscore (R=0.044, P=0.655 in the training cohort; R=0.067, P=0.580 in the validation cohort).</p><p><strong>Conclusion: </strong>Our results showed that the ITHscore is a novel and stable quantitative indicator of LVI and is helpful for effectively facilitating the risk stratification of LVI in CRC patients after integrating clinical variables and radiomics features.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143774787","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":"Evaluating CT Dose Variation Across Scanner Technologies: Implications for Compliance with New CMS CT Radiation Dose Measure.","authors":"Madan M Rehani, Maria T Mataac, Xinhua Li","doi":"10.1016/j.acra.2025.03.026","DOIUrl":"https://doi.org/10.1016/j.acra.2025.03.026","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>In 2025, the Centers for Medicare and Medicaid Services introduced a computed tomography (CT) dose measure for pay-for-performance programs. Hospitals employ diverse scanner fleets, but the impact of scanner technologies on dose benchmarking remains unclear. This study evaluates dose variation across scanner models and its benchmarking implications.</p><p><strong>Materials and methods: </strong>A retrospective analysis examined CT exams from January to December 2023 at a quaternary-care hospital, focusing on median-sized adults (water-equivalent diameter: 16-19cm head, 18-22cm neck, 29-33cm torso). Dose indices from seven scanner models across eight adult exams were evaluated. The 50^th and 75^th percentile doses were calculated per exam and scanner model combination, compared to American College of Radiology achievable doses and diagnostic reference levels.</p><p><strong>Results: </strong>Analyzing 34,166 studies, significant dose variations with scanner models emerged. Head without contrast (N=21,654) had median volume CT-dose-index (CTDI_vol) of 36.1-68.3mGy and dose-length-product (DLP) 704-1307.8mGy·cm; 75^th percentiles were 43.1-69.1mGy and 838.2-1378.1mGy·cm. Chest with contrast (N=3065) showed median CTDI_vol of 6.7-16.1mGy and DLP 263.8-579.7mGy·cm; 75^th percentiles were 8.2-19.5mGy and 329-713.7mGy·cm. Abdomen/pelvis with contrast (N=2740) had median CTDI_vol of 8.8-15.2mGy and DLP 429.3-782.1mGy·cm; 75^th percentiles were 10-18.5mGy and 533.4-941.5mGy·cm. While the number of studies was smaller, five other exams also showed large dose variations across scanner models.</p><p><strong>Conclusion: </strong>Single-value dose benchmarks ignoring scanner technology may be inadequate, even for similar-sized patients, potentially requiring scanner removal. Incorporating benchmarks with diverse technologies could prevent increased healthcare costs and patient care disruptions.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143774781","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":"Multiparametric MRI-based Interpretable Machine Learning Radiomics Model for Distinguishing Between Luminal and Non-luminal Tumors in Breast Cancer: A Multicenter Study.","authors":"Yi Zhou, Guihan Lin, Weiyue Chen, Yongjun Chen, Changsheng Shi, Zhiyi Peng, Ling Chen, Shibin Cai, Ying Pan, Minjiang Chen, Chenying Lu, Jiansong Ji, Shuzheng Chen","doi":"10.1016/j.acra.2025.03.010","DOIUrl":"https://doi.org/10.1016/j.acra.2025.03.010","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>To construct and validate an interpretable machine learning (ML) radiomics model derived from multiparametric magnetic resonance imaging (MRI) images to differentiate between luminal and non-luminal breast cancer (BC) subtypes.</p><p><strong>Methods: </strong>This study enrolled 1098 BC participants from four medical centers, categorized into a training cohort (n = 580) and validation cohorts 1-3 (n = 252, 89, and 177, respectively). Multiparametric MRI-based radiomics features, including T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), apparent diffusion coefficient (ADC), and dynamic contrast-enhanced (DCE) imaging, were extracted. Five ML algorithms were applied to develop various radiomics models, from which the best performing model was identified. A ML-based combined model including optimal radiomics features and clinical predictors was constructed, with performance assessed through receiver operating characteristic (ROC) analysis. The Shapley additive explanation (SHAP) method was utilized to assess model interpretability.</p><p><strong>Results: </strong>Tumor size and MR-reported lymph node status were chosen as significant clinical variables. Thirteen radiomics features were identified from multiparametric MRI images. The extreme gradient boosting (XGBoost) radiomics model performed the best, achieving area under the curves (AUCs) of 0.941, 0.903, 0.862, and 0.894 across training and validation cohorts 1-3, respectively. The XGBoost combined model showed favorable discriminative power, with AUCs of 0.956, 0.912, 0.894, and 0.906 in training and validation cohorts 1-3, respectively. The SHAP visualization facilitated global interpretation, identifying \"ADC_wavelet-HLH_glszm_ZoneEntropy\" and \"DCE_wavelet-HLL_gldm_DependenceVariance\" as the most significant features for the model's predictions.</p><p><strong>Conclusion: </strong>The XGBoost combined model derived from multiparametric MRI may proficiently differentiate between luminal and non-luminal BC and aid in treatment decision-making.</p><p><strong>Critical relevance statement: </strong>An interpretable machine learning radiomics model can preoperatively predict luminal and non-luminal subtypes in breast cancer, thereby aiding therapeutic decision-making.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143774786","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":"Generating Synthetic T2*-Weighted Gradient Echo Images of the Knee with an Open-source Deep Learning Model.","authors":"Konstantinos Vrettos, Evangelia E Vassalou, Grigoria Vamvakerou, Apostolos H Karantanas, Michail E Klontzas","doi":"10.1016/j.acra.2025.03.015","DOIUrl":"https://doi.org/10.1016/j.acra.2025.03.015","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>Routine knee MRI protocols for 1.5 T and 3 T scanners, do not include T2*-w gradient echo (T2*W) images, which are useful in several clinical scenarios such as the assessment of cartilage, synovial blooming (deposition of hemosiderin), chondrocalcinosis and the evaluation of the physis in pediatric patients. Herein, we aimed to develop an open-source deep learning model that creates synthetic T2*W images of the knee using fat-suppressed intermediate-weighted images.</p><p><strong>Materials and methods: </strong>A cycleGAN model was trained with 12,118 sagittal knee MR images and tested on an independent set of 2996 images. Diagnostic interchangeability of synthetic T2*W images was assessed against a series of findings. Voxel intensity of four tissues was evaluated with Bland-Altman plots. Image quality was assessed with the use of root mean squared error (NRMSE), structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR). Code, model and a standalone executable file are provided on github.</p><p><strong>Results: </strong>The model achieved a median NRMSE, PSNR and SSIM of 0.5, 17.4, and 0.5, respectively. Images were found interchangeable with an intraclass correlation coefficient >0.95 for all findings. Mean voxel intensity was equal between synthetic and conventional images. Four types of artifacts were identified: geometrical distortion (86/163 cases), object insertion/omission (11/163 cases), a wrap-around-like (26/163 cases) and an incomplete fat-suppression artifact (120/163 cases), which had a median 0 impact (no impact) on the diagnosis.</p><p><strong>Conclusion: </strong>In conclusion, the developed open-source GAN model creates synthetic T2*W images of the knee of high diagnostic value and quality. The identified artifacts had no or minor effect on the diagnostic value of the images.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143774783","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":"Thermal Ablation for Low-risk Papillary Thyroid Carcinoma: Comparing Outcomes in T1N0M0 and T2N0M0 PTC.","authors":"Yu-Tong Liu, Ying Wei, Zhen-Long Zhao, Jie Wu, Shi-Liang Cao, Na Yu, Yan Li, Li-Li Peng, Ming-An Yu","doi":"10.1016/j.acra.2025.03.019","DOIUrl":"https://doi.org/10.1016/j.acra.2025.03.019","url":null,"abstract":"<p><strong>Background: </strong>Thermal ablation (TA) has demonstrated promising treatment efficacy and safety in T1N0M0 papillary thyroid carcinoma (PTC). However, the efficacy and safety of TA for T2N0M0 PTC still lack sufficient evidence.</p><p><strong>Purpose: </strong>To compare the technical effectiveness, disease progression, and complications of TA in the treatment of solitary T1N0M0 versus solitary T2N0M0 PTC.</p><p><strong>Materials and methods: </strong>In this retrospective study, 1159 patients with PTC treated with TA from January 2015 to June 2024 were included and divided into two groups according to tumor stage. Propensity score matching (PSM) was used to control for confounding factors. Kaplan-Meier curves were used to analyze the disease progression.</p><p><strong>Results: </strong>After PSM (1:4), 41 patients (median age 35 years [IQR 30-49]; 30 women) were included in the T2 group, and 164 patients (median age 34 years [IQR 29-43]; 108 women) were included in the T1 group. The median follow-up durations were 26 months (IQR 13-49) for the T2 group and 25 months (IQR 12.3-43) for the T1 group. The technical success rates were 100% in the two groups. Statistical analysis showed no significant differences in disease progression between the T1 and T2 groups (0.6% vs. 4.9%, P=0.103), nor in disease progression-free survival rates (98.2% vs. 88.6%, log-rank P=0.052). The incidence of major complications was higher in the T2 group than that in the T1 group (1.8% vs. 17.1%, P=0.001). No permanent hoarseness was observed in the two groups.</p><p><strong>Conclusion: </strong>TA could be a safe and effective option in the treatment of solitary T2N0M0 PTC. No significant difference was observed in disease progression between T1N0M0 and T2N0M0 PTC.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143765787","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":"Integrating Deep Learning in Breast MRI: Technical Advances and Clinical Promise.","authors":"Yuki Arita, Noam Nissan","doi":"10.1016/j.acra.2025.03.047","DOIUrl":"https://doi.org/10.1016/j.acra.2025.03.047","url":null,"abstract":"","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143765780","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 2024 Association of Academic Radiologists and Industry Think Tank: Unmet Clinical Needs and Collaborative Resourcing.","authors":"Kara Gaetke-Udager, Christopher Hess, Mary Mahoney, Jeffrey G Jarvik, Pablo R Ros","doi":"10.1016/j.acra.2025.03.016","DOIUrl":"https://doi.org/10.1016/j.acra.2025.03.016","url":null,"abstract":"","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143765784","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":"Lateralized Amplitude Low-frequency Fluctuation Alterations in Mild Cognitive Impairment as a Biomarker for Early Alzheimer's Disease Detection.","authors":"Lichang Yao, Zhilin Zhang","doi":"10.1016/j.acra.2025.03.035","DOIUrl":"https://doi.org/10.1016/j.acra.2025.03.035","url":null,"abstract":"","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143765782","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":"Performance of Magnetic Resonance Imaging and Ultrasound for Identifying the Different Degrees of Hepatic Steatosis: A Systematic Review and Meta-analysis.","authors":"Shuzhen Wu, Junhan Pan, Mengchen Song, Yan-Ci Zhao, Wuyue Chen, Huizhen Huang, Yanyan Zhu, Feng Chen","doi":"10.1016/j.acra.2025.03.008","DOIUrl":"https://doi.org/10.1016/j.acra.2025.03.008","url":null,"abstract":"<p><strong>Background: </strong>MRI proton density fat fraction (MRI-PDFF), controlled attenuation parameters (CAP), and attenuation coefficients (AC) are capable of steatosis characterization and may be useful as noninvasive alternatives for diagnosing hepatic steatosis.</p><p><strong>Purpose: </strong>This meta-analysis aimed to evaluate the performance of MRI-PDFF, CAP, and AC in grading hepatic steatosis, using histology as the reference standard.</p><p><strong>Methods: </strong>We conducted a comprehensive search of the PubMed, Cochrane Library, Embase, and Web of Science databases until June 2024. The quality of eligible studies was assessed. Pooled sensitivity, specificity, and area under receiver operating characteristic (AUC) curves were calculated using a bivariate random-effects model. Meta-regression analysis, subgroup analysis, and Deeks' test were performed to explore heterogeneity and assess publication bias.</p><p><strong>Results: </strong>This meta-analysis included 38 studies with 5056 patients with metabolic dysfunction-associated steatotic liver disease. The AUC values for grading steatosis ≥S1, ≥S2, and ≥S3 were 0.99, 0.89, and 0.90 for MRI-PDFF, 0.95, 0.84, and 0.77 for CAP, and 0.97, 0.90, and 0.89 for AC, respectively. CAP demonstrated lower accuracy for detecting steatosis grades ≥S2 and ≥S3 compared to MRI-PDFF (0.89 vs. 0.84, p<0.001; 0.90 vs. 0.77, p<0.001) and AC (0.90 vs. 0.84, p<0.001; 0.89 vs. 0.77, p<0.001). Subgroup analyses revealed that MRI-PDFF and CAP exhibited superior diagnostic performance in diagnosing ≥S2 and ≥S3 steatosis among individuals in Asia, with a body mass index ≤30 kg/m², and age <51 years.</p><p><strong>Conclusion: </strong>A direct comparison with CAP showed greater accuracy for MRI-PDFF and AC in diagnosing moderate and severe steatosis, and similar diagnostic performance for MRI-PDFF and AC. For patients with steatosis, AC should be incorporated into routine ultrasound screening.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755813","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":"Deep Learning and Radiomics Discrimination of Coronary Chronic Total Occlusion and Subtotal Occlusion using CTA.","authors":"Zhen Zhou, Kairui Bo, Yifeng Gao, Weiwei Zhang, Hongkai Zhang, Yan Chen, Yanchun Chen, Hui Wang, Nan Zhang, Yimin Huang, Xinsheng Mao, Zhifan Gao, Heye Zhang, Lei Xu","doi":"10.1016/j.acra.2025.03.011","DOIUrl":"https://doi.org/10.1016/j.acra.2025.03.011","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>Coronary chronic total occlusion (CTO) and subtotal occlusion (STO) pose diagnostic challenges, differing in treatment strategies. Artificial intelligence and radiomics are promising tools for accurate discrimination. This study aimed to develop deep learning (DL) and radiomics models using coronary computed tomography angiography (CCTA) to differentiate CTO from STO lesions and compare their performance with that of the conventional method.</p><p><strong>Materials and methods: </strong>CTO and STO were identified retrospectively from a tertiary hospital and served as training and validation sets for developing and validating the DL and radiomics models to distinguish CTO from STO. An external test cohort was recruited from two additional tertiary hospitals with identical eligibility criteria. All participants underwent CCTA within 1 month before invasive coronary angiography.</p><p><strong>Results: </strong>A total of 581 participants (mean age, 50 years ± 11 [SD]; 474 [81.6%] men) with 600 lesions were enrolled, including 403 CTO and 197 STO lesions. The DL and radiomics models exhibited better discrimination performance than the conventional method, with areas under the curve of 0.908 and 0.860, respectively, vs. 0.794 in the validation set (all p＜0.05), and 0.893 and 0.827, respectively, vs. 0.746 in the external test set (all p＜0.05).</p><p><strong>Conclusions: </strong>The proposed CCTA-based DL and radiomics models achieved efficient and accurate discrimination of coronary CTO and STO.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755751","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}