{"title":"Explainable Fusion Model for Predicting Postoperative Early Recurrence in Hepatocellular Carcinoma Using Gadoxetic Acid-Enhanced MRI Habitat Imaging.","authors":"Yanjin Qin, Lie-Guang Zhang, Xiaoqi Zhou, Chenyu Song, Yuxin Wu, Mimi Tang, Zhoukun Ling, Jifei Wang, Huasong Cai, Zhenpeng Peng, Shi-Ting Feng","doi":"10.1016/j.acra.2025.04.018","DOIUrl":"https://doi.org/10.1016/j.acra.2025.04.018","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>To develop an explainable fusion model that combines clinical, radiomic, and habitat features to predict postoperative early recurrence in hepatocellular carcinoma (HCC).</p><p><strong>Methods: </strong>The bicentric retrospective study included 370 patients with surgically confirmed early-stage HCC who underwent gadoxetic acid-enhanced MRI. The patients were stratified into a training cohort (n=296) and an external validation cohort (n=74). From the hepatobiliary phase images, habitat and radiomics features were extracted across the entire tumor and used to construct radiomics and habitat models. Additionally, a clinical model was established utilizing relevant clinical features. Subsequently, all previously mentioned features were merged to construct the fusion model (HabRad_FB). Diagnostic performance of these models was assessed and compared using the area under the receiver operating characteristic curve (AUC), net reclassification index (NRI), and integrated discrimination improvement (IDI). The fusion model was then interpreted using SHapley Additive exPlanations (SHAP) analysis.</p><p><strong>Results: </strong>Tumor recurrence was observed in 73 out of 370 patients (19.7%; 55.2±11.3 years; male=333). Among all study cohorts, the HabRad_FB model showed the highest AUC (0.820-0.959), outperforming the clinical (0.517-0.729), radiomics (0.707-0.815), and habitat (0.729-0.861) models. The HabRad_FB model also demonstrated significant improvement in IDI in the training cohort and NRI in the validation cohort. SHAP force plots provided valuable insights into the interpretation of HabRad_FB model's predictions for early recurrence.</p><p><strong>Conclusion: </strong>The HabRad_FB, an explainable fusion model, aids clinicians in accurately and non-invasively predicting the early recurrence of HCC preoperatively. This model might provide great potential in prognostic prediction and clinical management.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144086945","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 Affirmative Action Ruling on Diversity in Radiology.","authors":"Ajay Malhotra, Dheeman Futela","doi":"10.1016/j.acra.2025.04.066","DOIUrl":"https://doi.org/10.1016/j.acra.2025.04.066","url":null,"abstract":"","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144081876","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}
Zi Hao Ni, Tian Ying Xing, Wei Hong Hou, Xin Yu Zhao, Yun Lu Tao, Fu Bo Zhou, Ying Qi Xing
{"title":"Development and Validation of Ultrasound Hemodynamic-based Prediction Models for Acute Kidney Injury After Renal Transplantation.","authors":"Zi Hao Ni, Tian Ying Xing, Wei Hong Hou, Xin Yu Zhao, Yun Lu Tao, Fu Bo Zhou, Ying Qi Xing","doi":"10.1016/j.acra.2025.04.058","DOIUrl":"https://doi.org/10.1016/j.acra.2025.04.058","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>Acute kidney injury (AKI) post-renal transplantation often has a poor prognosis. This study aimed to identify patients with elevated risks of AKI after kidney transplantation.</p><p><strong>Materials and methods: </strong>A retrospective analysis was conducted on 422 patients who underwent kidney transplants from January 2020 to April 2023. Participants from 2020 to 2022 were randomized to training group (n=261) and validation group 1 (n=113), and those in 2023, as validation group 2 (n=48). Risk factors were determined by employing logistic regression analysis alongside the least absolute shrinkage and selection operator, making use of ultrasound hemodynamic, clinical, and laboratory information. Models for prediction were developed using logistic regression analysis and six machine-learning techniques. The evaluation of the logistic regression model encompassed its discrimination, calibration, and applicability in clinical settings, and a nomogram was created to illustrate the model. SHapley Additive exPlanations were used to explain and visualize the best of the six machine learning models.</p><p><strong>Results: </strong>The least absolute shrinkage and selection operator combined with logistic regression identified and incorporated five risk factors into the predictive model. The logistic regression model (AUC=0.927 in the validation set 1; AUC=0.968 in the validation set 2) and the random forest model (AUC=0.946 in the validation set 1;AUC=0.996 in the validation set 2) showed good performance post-validation, with no significant difference in their predictive accuracy.</p><p><strong>Conclusion: </strong>These findings can assist clinicians in the early identification of patients at high risk for AKI, allowing for timely interventions and potentially enhancing the prognosis following kidney transplantation.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144081873","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":"Re: \"Factors Influencing Medical Students' Choice of Radiology as a Future Career: A Cross-sectional Study From Saudi Arabia\".","authors":"Isobel Saoirse Kelsh","doi":"10.1016/j.acra.2025.04.065","DOIUrl":"https://doi.org/10.1016/j.acra.2025.04.065","url":null,"abstract":"","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144081883","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-Guided Lung Biopsy with Needle Embolization Using Gelatin Sponge Slurry to Prevent Pneumothorax and Pulmonary Hemorrhage: A Propensity Score Matching Controlled Study.","authors":"Xiao-Hui Zhao, Shi-Bo Zhu, Xin Li, Cheng-Min Yang, Jia-Xin Liu, Fang Liu, Wen-Ge Xing, Yong Li","doi":"10.1016/j.acra.2025.04.055","DOIUrl":"https://doi.org/10.1016/j.acra.2025.04.055","url":null,"abstract":"<p><strong>Rationale and objective: </strong>To investigate whether using gelatin sponge slurry to seal the needle tract during computed tomography (CT)-guided lung biopsy can reduce the incidence of pneumothorax (PTX) and pulmonary hemorrhage (PH).</p><p><strong>Materials and methods: </strong>This retrospective, large-sample, controlled study was conducted in the Interventional Therapy Department of Medical University Cancer Institute and Hospital from December 2022 to January 2023. A total of 1126 patients were included. There were 844 patients in the non-gelatin sponge slurry group (Group A) and 282 patients in the gelatin sponge slurry group (Group B). Group B patients were preoperatively considered to be at higher risk for PTX and/or PH. CT-guided biopsies were performed using a coaxial technique, injecting 1-3 ml of gelatin sponge slurry while withdrawing the needle. Chi-square tests compared the PTX rate, PH rate, chest tube placement rate, and significant pulmonary hemorrhage rate between Group A and Group B. Univariate and multivariate logistic regression analyses identified risk factors for PTX and PH in the entire cohort and within each group. Factors included demographics, lesion characteristics, and biopsy technical parameters. Propensity Score Matching (PSM) adjusted for selection bias between the two groups.</p><p><strong>Results: </strong>The incidence of pneumothorax was 26.1% in Group A and 6.4% in Group B. In Group A, 28 patients required chest tube placement, compared to 3 patients in Group B. Using gelatin sponge slurry significantly reduced the incidence of PTX (P<0.05). Multivariate logistic regression analysis in the entire cohort showed that emphysema, smaller tumor size, greater puncture depth, traversing the interlobar fissure, and not using gelatin sponge slurry were significantly associated with increased PTX risk. Within-group multivariate analysis indicated that emphysema, tumor size, puncture depth, and traversing the interlobar fissure were PTX risk factors in Group A. Puncture depth was the sole risk factor in Group B. The incidence of PH was 37.6% in Group A and 38.3% in Group B (P=0.825). Significant pulmonary hemorrhage rates were 14.8% in Group A and 10.6% in Group B (P=0.078). Only one patient in Group A required hemostatic intervention under digital subtraction angiography (DSA). Multivariate logistic regression analysis for the entire cohort identified tumor size and puncture depth as independent prognostic factors for PH. Similar results were observed in within-group analyses. Subgroup analysis revealed that using gelatin sponge slurry did not reduce PTX incidence when puncture depth exceeded 7 cm. For tumors larger than 40 mm and puncture depths ≤7 cm, using gelatin sponge slurry reduced PH incidence.</p><p><strong>Conclusion: </strong>For patients preoperatively identified as at high risk for pneumothorax and pulmonary hemorrhage, using gelatin sponge slurry to seal the needle tract significantly reduc","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144081868","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}
Jin Chen, Bing Zhang, Yuan Yan, Fu-Qun Wei, Rui Guo, Bing-Yu Huang, Bin Lv, Zheng-Yu Lin
{"title":"Percutaneous MR-Guided Thermal Ablation for Recurrent Subcentimeter Hepatocellular Carcinoma.","authors":"Jin Chen, Bing Zhang, Yuan Yan, Fu-Qun Wei, Rui Guo, Bing-Yu Huang, Bin Lv, Zheng-Yu Lin","doi":"10.1016/j.acra.2025.04.053","DOIUrl":"https://doi.org/10.1016/j.acra.2025.04.053","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>To evaluate the technical efficacy and therapeutic outcomes of percutaneous MR-guided thermal ablation, including microwave ablation (MWA) and radiofrequency ablation (RFA) for recurrent subcentimeter hepatocellular carcinomas (HCCs). MATERIALS AND METHODS: From January 2015 to May 2024, we recruited 101 patients with 119 recurrent subcentimeter HCCs (mean diameter: 8.0±1.3 mm, range: 5.6-9.9mm), who were treated with MR-guided thermal ablation. Technical success, technical efficacy, complications, and local tumor progression (LTP) rate were evaluated after ablation. Cumulative LTP rate, recurrence-free survival (RFS), and overall survival (OS) rates were estimated using the Kaplan-Meier method.</p><p><strong>Results: </strong>A retrospective analysis showed that MR-guided thermal ablation (MWA, n=84; RFA, n=17) was successfully executed in all cases. Technical success and efficacy were achieved in all lesions in single sessions without major complications. The mean follow-up duration was 41.1±27.1 months (median:38.0 months; range:3-105 months). The cumulative LTP rate at 1 year was 1.2%, and 5.8% at 3, 5, 7, and 9 years. The cumulative RFS rates at 1, 3, 5, 7, and 9 years were 82.2%, 44.6%, 29.0%, 23.2%, and 23.2%, respectively. The cumulative OS rates at 1, 3, 5, 7, and 9 years were 99.0%, 91.8%, 84.4%, 69.7%, and 62.0%, respectively.</p><p><strong>Conclusion: </strong>Percutaneous MR-guided thermal ablation for recurrent subcentimeter HCCs demonstrated ready visualization of lesions and ablation margins as well as high technical efficacy rate, and minimal LTP after a single treatment session.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144081880","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}
Jinhua Qian, Qinjie Chi, Li Zhu, Tianhao Zhang, Wenbing Ding, Ruifan Yuan, Zhuo Chen, Tianle Wang
{"title":"Carotid Plaque-RADS Score Combined with Pericarotid Fat Density-An Incremental Prediction Model for Stroke Recurrence.","authors":"Jinhua Qian, Qinjie Chi, Li Zhu, Tianhao Zhang, Wenbing Ding, Ruifan Yuan, Zhuo Chen, Tianle Wang","doi":"10.1016/j.acra.2025.04.051","DOIUrl":"https://doi.org/10.1016/j.acra.2025.04.051","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>This study aimed to evaluate the prognostic value of combined carotid plaque reporting and data system (RADS) score and pericarotid fat density (PFD) for predicting stroke recurrence risk, and to explore its utility in stroke risk stratification.</p><p><strong>Methods: </strong>We developed a novel binary comprehensive risk index (CRI) that integrates the carotid plaque-RADS and PFD: low CRI (RADS <3 and PFD ≤ -74 HU) and high CRI (RADS ≥3 or PFD > -74 HU). Net reclassification improvement, Kaplan-Meier survival analysis, multivariate logistic regression, receiver operating characteristic curves (ROC), and decision curve analysis (DCA) were used to assess the predictive value of CRI over stenosis degree.</p><p><strong>Results: </strong>During a mean follow-up period of 17.24±11.93 months, 64 of 272 patients (23.3%) experienced recurrent stroke. CRI significantly improved stroke recurrence risk stratification in mild-to-moderate stenosis patients. Kaplan-Meier survival analysis revealed significant differences in stroke recurrence rates across varying plaque-RADS and CRI (P < 0.0001). Independent predictors of stroke recurrence included plaque-RADS ≥ 3 (OR=2.68, 95% CI: 1.03-6.96), CRI (OR=8.25, 95% CI: 2.23-30.44), affected-side PFD (OR=0.97, 95% CI: 0.94-0.99), and bilateral PFD difference (OR=1.09, 95% CI: 1.05-1.13). The combined model incorporating stenosis degree, plaque-RADS, affected-side PFD, bilateral PFD difference, and CRI demonstrated superior prediction performance, achieving an area under the ROC curve of 0.892.</p><p><strong>Conclusion: </strong>Integrating carotid plaque-RADS and PFD significantly enhances the accuracy of stroke recurrence risk prediction, especially in patients with mild-to-moderate stenosis. This combined assessment model provides valuable insights for personalized prevention and treatment strategies for stroke recurrence.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144059884","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}
Ali Borhani, Iman Yazdani Nia, Ghazal Zandieh, Stephen C Mathai, Steven Hsu, Paul M Hassoun, Ihab R Kamel, Stefan L Zimmerman, Bharath Ambale Venkatesh
{"title":"Semi-quantitative analysis of Right Ventricular Myocardial First-pass Perfusion Using Cardiac Magnetic Resonance Imaging in Systemic Sclerosis and Pulmonary Arterial Hypertension.","authors":"Ali Borhani, Iman Yazdani Nia, Ghazal Zandieh, Stephen C Mathai, Steven Hsu, Paul M Hassoun, Ihab R Kamel, Stefan L Zimmerman, Bharath Ambale Venkatesh","doi":"10.1016/j.acra.2025.04.034","DOIUrl":"https://doi.org/10.1016/j.acra.2025.04.034","url":null,"abstract":"<p><strong>Background: </strong>Right ventricular (RV) myocardial perfusion has been touted as a primary mechanism to understand impairment in RV function in patients with pulmonary arterial hypertension (PAH). However, measuring RV perfusion presents technical challenges. In this study, our aim is to employ a semi-quantitative approach using cardiac magnetic resonance (CMR) imaging to measure RV free wall first-pass perfusion in patients with PAH and controls, and to evaluate the intra- and inter-reader reproducibility of this approach.</p><p><strong>Methods: </strong>This study included 37 subjects (mean age 58.2±12 years, 72.9% female), 8 with idiopathic pulmonary arterial hypertension (IPAH), 10 with systemic sclerosis (SSc) and pulmonary arterial hypertension (PAH), 12 with SSc without PAH, and seven healthy controls. All participants underwent rest and adenosine stress perfusion CMR imaging using a 3 T scanner as part of a research protocol for evaluating pulmonary hypertension. Two readers delineated three regions of interest (ROIs) within the visible RV myocardium and manually traced contours of endocardial and epicardial borders of the left ventricle (LV) in two planes. Semi-quantitative perfusion analysis was performed with dedicated software for the measurement of first-pass myocardial perfusion. Concordance correlation coefficients (CCC) assessed inter- and intra-reader agreement of measurements.</p><p><strong>Results: </strong>Patients had an RV Ejection fraction (EF) of 50.9±11.3% and LVEF of 63.8±6.4 % and controls had an RVEF of 61.3±6.7 % and LVEF of 65.5±5.1 %. RV myocardial perfusion measurements at rest and stress were similar between the two readers (2.29±1.17 (mL/g × min) and 2.77±1.44 (mL/g × min) at rest, 4.02±2.45 (mL/g × min) and 4.35±2.72 (mL/g × min) during stress. The agreement was best for stress phase (0.90), followed by rest phase (0.83), and myocardial perfusion reserve index (MPRI) (0.72). The agreement was higher between readers for LV perfusion measurements (rest phase: 0.97, stress phase: 0.99, and MPRI: 0.89). RV MPRI was significantly higher in controls (2.62±0.73) as compared to all patients (1.63±0.75). The differences remained when controls were compared to patients with PAH.</p><p><strong>Conclusion: </strong>Semi-quantitative first-pass RV perfusion reserve measures are technically feasible and show excellent inter-reader agreement. RV perfusion reserve index was lower in patients with PAH compared to healthy controls.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144025357","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 Locus of Excellence: A Lesson from Tolstoy","authors":"Richard B. Gunderman MD, PhD","doi":"10.1016/j.acra.2025.04.052","DOIUrl":"10.1016/j.acra.2025.04.052","url":null,"abstract":"","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 6","pages":"Pages 3764-3765"},"PeriodicalIF":3.8,"publicationDate":"2025-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144059820","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 Radiomics for Identifying Primary Central Nervous System Diffuse Large B-cell Lymphomas' Pathological Subtypes.","authors":"Hao Liu, Mengyang He, Eryuan Gao, Yong Zhang, Jingliang Cheng, Guohua Zhao","doi":"10.1016/j.acra.2025.04.046","DOIUrl":"https://doi.org/10.1016/j.acra.2025.04.046","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>To explore the predictive potential of radiomics features extracted from preoperative multiparametric magnetic resonance imaging (MRI) for identifying pathological subtypes of primary central nervous system diffuse large B-cell lymphomas (PCNS-DLBCL).</p><p><strong>Methods: </strong>This study recruited 186 patients with PCNS-DLBCL, including 55 with germinal center B-cell-like (GCB) subtype and 131 with non-GCB subtype. The largest abnormal signal regions of the tumor were automatically segmented in T1-weighted images (T1WI), T2-weighted images, T2 fluid-attenuated inversion recovery, contrast-enhanced T1-weighted (CE-T1WI), and apparent diffusion coefficient (ADC) maps, respectively. Radiomics features were extracted from preprocessed multiparameter preoperative MRI images. To identify GCB and non-GCB subtypes, radiomics models were constructed based on each MRI sequence and combinations of sequences. Clinical models and models combining radiomics and clinical features were also constructed to compare performance.</p><p><strong>Results: </strong>Radiomics models combining multiple sequences generally outperformed single-sequence radiomics models. The ADC+CE-T1WI model exhibited superior discriminative power, with an area under the curve of 0.867 (95% CI, 0.745-0.988). Models incorporating more sequences (3-5 sequences) did not demonstrate better performance. The performance of the model combining radiomics features with clinical features showed no improvement.</p><p><strong>Conclusion: </strong>Radiomics based on multiparametric MRI have independent value in predicting the pathological subtypes of PCNS-DLBCL patients.</p>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144055271","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}