Abdominal radiology (New York)最新文献

{"title":"Abdominal landmark detection and classification of fetal growth conditions on obstetric ultrasound: a gestational age-conditioned multi-task network.","authors":"Taoran Tong, Haijuan Gu, Hongmei Lyu","doi":"10.1007/s00261-026-05771-z","DOIUrl":"https://doi.org/10.1007/s00261-026-05771-z","url":null,"abstract":"<p><strong>Objective: </strong>This study presents GA-MTNet (Gestational-Age-Conditioned Multi-Task Network), a deep learning framework that integrates gestational age conditioning into a multi-task architecture to simultaneously perform abdominal landmark detection and classify five sonographic patterns linked to fetal growth conditions in prenatal ultrasound.</p><p><strong>Materials and methods: </strong>A retrospective multi-center dataset of 9,046 B-mode ultrasound images from 2,712 pregnant women (18-34 weeks) was collected across three institutions. Data from Centers A and B (6,750 images, 2,278 patients) were used for model development via patient-stratified 5-fold cross-validation, while Center C (1,296 images, 434 patients) served as an external test set. GA-MTNet employs a Swin Transformer V1 backbone with a Gestational Age Embedding Module based on Feature-wise Linear Modulation (FiLM), enabling dynamic adaptation of image features to fetal developmental stage. Three task heads handle: (1) detection of four abdominal landmarks, (2) five-class classification of fetal growth conditions (IUGR, GDM, pre-eclampsia, normal growth, amniotic fluid abnormalities), and (3) biometric regression. Post-deployment adaptability is supported through uncertainty-guided continual learning combining Monte Carlo Dropout, Elastic Weight Consolidation, and Low-Rank Adaptation. Interpretability was assessed via SHAP and Grad-CAM++, scored by two blinded fetal medicine specialists.</p><p><strong>Results: </strong>Internally, GA-MTNet achieved a macro-AUC of 0.863, accuracy of 84.7%, macro-F1 of 0.821, and landmark detection mAP@0.5 of 0.791. Externally, performance remained strong (AUC 0.841, accuracy 82.3%, F1 0.798), with only a 2.2-point AUC drop. Per-class AUC ranged from 0.803 to 0.921. Ablation studies confirmed significant contributions from gestational age conditioning (+ 3.1 pp, p = 0.003), multi-task learning (+ 1.0 pp, p = 0.011), and continual learning (+ 1.0 pp, p = 0.014). Calibration was excellent (ECE = 0.047), and clinical relevance scored 3.2/4.</p><p><strong>Conclusions: </strong>GA-MTNet demonstrates that gestational age conditioning meaningfully improves sonographic pattern recognition and landmark detection across the second and third trimesters, while its continual learning mechanism enables safe, practical post-deployment model refinement.</p>","PeriodicalId":520541,"journal":{"name":"Abdominal radiology (New York)","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148932212","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Added diagnostic value of pseudocapsule and ADC heterogeneity beyond ccLS v2.0 in small renal masses.","authors":"Uluhan Eryuruk, Merve Nur Tasdemir, Esra Pinar, Ramazan Orkun Onder, Serdar Aslan","doi":"10.1007/s00261-026-05778-6","DOIUrl":"https://doi.org/10.1007/s00261-026-05778-6","url":null,"abstract":"<p><strong>Objective: </strong>To identify which multiparametric MRI parameters provide independent diagnostic value for clear cell renal cell carcinoma (ccRCC) beyond the clear cell likelihood score (ccLS) version 2.0 in small renal masses (SRMs), and to determine whether their addition improves discriminative performance.</p><p><strong>Methods: </strong>This retrospective single-center study included patients with surgically confirmed SRMs (≤ 4 cm, > 25% enhancing component, no macroscopic fat) who underwent preoperative 1.5 T multiparametric MRI between September 2021 and May 2025. Two blinded radiologists of differing experience independently assigned ccLS v2.0 and evaluated qualitative and quantitative MR features. Univariate and multivariate logistic regression identified independent predictors; ROC analysis with the DeLong test assessed the added value of an augmented model over ccLS alone, with calibration and decision-curve analysis. Inter-reader agreement was quantified using Cohen's κ, quadratic-weighted κ, and the intraclass correlation.</p><p><strong>Results: </strong>Of 817 patients, 108 eligible SRMs (64 ccRCC) across 102 patients were analyzed. At a cutoff of ≥ 4, ccLS v2.0 yielded AUCs of 0.837 (Reader 1) and 0.834 (Reader 2). On multivariate analysis with ccLS entered as a covariate, pseudocapsule and normalized ADC standard deviation (nADCsd) were the independent predictors of ccRCC in both readers, with pseudocapsule the strongest binary predictor (OR 6.96, p = 0.003; OR 4.25, p = 0.015). Adding pseudocapsule and nADCsd to the ccLS score significantly improved discrimination (Reader 1: AUC 0.905 vs. 0.837, p = 0.032; Reader 2: 0.882 vs. 0.834, p = 0.048); after bootstrap optimism correction, the improvement persisted (corrected AUC 0.890 and 0.872), with favorable calibration and net benefit on decision-curve analysis. Within the indeterminate ccLS = 3 subgroup, pseudocapsule was present in 100% and 90% of ccRCC lesions versus 22% and 31% of non-ccRCC lesions, and nADCsd was the only quantitative feature significant in both readers. Pseudocapsule showed excellent inter-reader agreement (κ = 0.862) and nADCsd good agreement (ICC 0.755).</p><p><strong>Conclusion: </strong>Pseudocapsule presence and nADCsd independently predicted ccRCC beyond ccLS v2.0 and provided significant added value, particularly in indeterminate ccLS = 3 lesions, pending multicenter validation.</p>","PeriodicalId":520541,"journal":{"name":"Abdominal radiology (New York)","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148932282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Neurogenic tumors of the abdomen and pelvis: imaging features, differential diagnosis, and diagnostic pitfalls.","authors":"Mustufa Babar, Aneka Khilnani, Ariel Felman, Michelle Clark, Sean O'Rourke, Alex Lin, Lyndon Luk","doi":"10.1007/s00261-026-05774-w","DOIUrl":"https://doi.org/10.1007/s00261-026-05774-w","url":null,"abstract":"<p><p>Neurogenic tumors of the abdomen and pelvis are a diverse group of neoplasms arising from paraganglia, peripheral nerves, and autonomic ganglia. Their imaging appearances range from benign incidental lesions to aggressive neoplasms with metastatic potential, creating diagnostic challenges because of overlapping imaging features and broad differential diagnoses. Cross-sectional imaging, supplemented by functional imaging, plays a central role in lesion characterization, staging, and surgical planning. This review summarizes the imaging features of paraganglion cell-derived, nerve sheath-derived, and ganglion cell-derived tumors, emphasizing characteristic imaging findings, anatomic distribution, clinical presentation, and pathologic correlation. Representative cases illustrate both classic and atypical appearances while highlighting important diagnostic pitfalls, including life-threatening catecholamine crisis from biopsy of an unrecognized pheochromocytoma or paraganglioma. A practical, imaging-based diagnostic algorithm is presented to facilitate systematic evaluation of abdominal and pelvic neurogenic tumors and narrow the differential diagnosis. Recognition of characteristic imaging patterns and integration of clinical, laboratory, and pathologic findings are essential for accurate diagnosis, appropriate management, and avoidance of potentially serious diagnostic and therapeutic errors.</p>","PeriodicalId":520541,"journal":{"name":"Abdominal radiology (New York)","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148932221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnostic performance of liver imaging reporting and data system ancillary features for hepatocellular carcinoma: a systematic review and evidence synthesis.","authors":"Xueyong Chang, Zhengyue Wang, Fangying Fan, Ping Liang, Jie Yu","doi":"10.1007/s00261-026-05734-4","DOIUrl":"10.1007/s00261-026-05734-4","url":null,"abstract":"<p><strong>Objective: </strong>To systematically review and evaluate the evidence supporting the role of Liver Imaging Reporting and Data System (LI-RADS) ancillary features (AFs) in optimizing hepatocellular carcinoma (HCC) diagnosis across magnetic resonance imaging (MRI), computed tomography (CT), and contrast-enhanced ultrasound (CEUS) modalities, with a focus on their incremental value in specific clinical scenarios.</p><p><strong>Methods: </strong>A comprehensive literature search was performed across PubMed and Embase from 2011 to 2024 to identify studies on LI-RADS AFs. Significant ancillary features (SAFs)-a review-specific descriptive framework rather than an official LI-RADS category-were defined as features demonstrating a statistically significant contribution to HCC diagnosis or LI-RADS diagnostic performance in at least one included study (p < 0.05).</p><p><strong>Results: </strong>A total of 101 articles were included. In terms of imaging modality distribution, MRI was predominant (91.1%, 92/101), while CT (21.8%, 22/101) and CEUS (9.9%, 10/101) studies were relatively limited. For LI-RADS categories LR-1 to LR-5, fourteen SAFs were identified on MRI (e.g., hepatobiliary phase hypointensity, diffusion restriction). For lesions ≤ 3 cm, the incremental value of applying a single guideline-recommended AF was marginal. In contrast, applying combinations of ≥ 4 AFs significantly improved sensitivity by 10.6-18.3% without a significant loss of specificity. Evidence for CT-based AFs was limited and inconsistent. For CEUS LR-1 to LR-5 observations, six AFs were identified, with exploratory markers showing potential incremental value, whereas the two official AFs showed inconsistent performance. For LR-M lesions, 14 SAFs significantly contributed to differentiating HCC from other hepatic malignancies (p < 0.05). In treatment response assessment (TRA), five SAFs-two of which are guideline-recommended-improved diagnostic sensitivity by 3.2-42.8% without loss of specificity.</p><p><strong>Conclusion: </strong>LI-RADS AFs enhance HCC diagnostic accuracy when complementing major features, with the most robust evidence supporting MRI-based AFs. In contrast, AFs based on CT and CEUS require further validation.</p>","PeriodicalId":520541,"journal":{"name":"Abdominal radiology (New York)","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148932280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prostate MRI reporting and its impact on clinical decision-making: the urologists' perspective.","authors":"Mert Emre Erden, Seyfettin Anıl Tantekin, Ahmad Gharehmohammadlou, Öner Şanlı","doi":"10.1007/s00261-026-05780-y","DOIUrl":"https://doi.org/10.1007/s00261-026-05780-y","url":null,"abstract":"<p><p>Multiparametric MRI (mpMRI) has fundamentally changed the diagnostic and management pathways for prostate cancer (PCa). Its clinical utility depends not only on image quality and interpretative accuracy but also on the completeness and precision of the radiological report. This review synthesizes the available evidence across five key reporting domains that directly impact clinical decision-making: (1) pre-biopsy triage, including Prostate Imaging Reporting and Data System (PI-RADS) scoring and Prostate Imaging Quality (PI-QUAL) assessment; (2) prostate volume measurement and PSA density (PSAD) reporting; (3) local staging, with particular emphasis on extraprostatic extension (EPE) and seminal vesicle invasion (SVI); (4) regional lymph node assessment, and (5) serial MRI monitoring using the PRECISE v2 framework for men undergoing active surveillance. Evidence from randomised controlled trials, large cohort studies, meta-analyses, and clinical practice guidelines published up to March 2026 was synthesised, with priority given to the highest level of available evidence and current European Association of Urology guidance. For each domain, we define the core reporting elements and discuss the evidence supporting their clinical relevance from both radiological and urological perspectives. Across all five domains, the clinical value of prostate MRI depends as much on complete and standardised reporting as on the quality of image acquisition and interpretation.</p>","PeriodicalId":520541,"journal":{"name":"Abdominal radiology (New York)","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148932259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Maintaining the balance: wellbeing strategies for abdominal radiologists.","authors":"Ashlesha Satish Udare, Lauren M B Burke, Iva Petkovska, Harshna V Vadvala, Luke Yoon, Kerry L Thomas","doi":"10.1007/s00261-026-05763-z","DOIUrl":"https://doi.org/10.1007/s00261-026-05763-z","url":null,"abstract":"<p><p>Burnout rates are high amongst radiologists due to intense cognitive load, time pressure of reporting ever-increasing imaging studies with high diagnostic accuracy and procedural demands. Abdominal radiologists must review large and complex imaging datasets, oncological imaging, reporting incidental findings with recommendations, and frequent multidisciplinary collaborations. Increased work volume and complexity require significant time sitting at a computer workstation with few breaks. Over time, these may have negative impact on one's physical wellbeing and professional satisfaction. While not all factors that contribute to diminished wellness can be easily changed, one can address individual and environmental factors that foster sustained wellbeing and professional satisfaction. This review article outlines several personal and departmental strategies to support the wellbeing of abdominal radiologists including organization support of wellbeing and professional development, workflow optimization strategies, leveraging innovative solutions, ergonomic improvements and lifestyle modifications.</p>","PeriodicalId":520541,"journal":{"name":"Abdominal radiology (New York)","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148932262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An MRI-based habitat radiomics nomogram for preoperative prediction of lymphovascular invasion in rectal cancer patients.","authors":"Fangrui Xu, Jianwei Hong, Xianhua Wu, Xiangming Fang","doi":"10.1007/s00261-026-05736-2","DOIUrl":"https://doi.org/10.1007/s00261-026-05736-2","url":null,"abstract":"<p><strong>Objective: </strong>This study seeks to assess the potential of using an MRI-based habitat radiomics nomogram to predict lymphovascular invasion (LVI) preoperatively in rectal cancer (RC) patients, while also comparing its performance to traditional intratumoral radiomics models.</p><p><strong>Methods: </strong>This study retrospectively included 197 RC patients diagnosed with LVI, who were randomly assigned to a training cohort (n = 139) and a validation cohort (n = 58). The K-means algorithm was used to perform clustering on the arterial phase of contrast-enhanced MRI images. Following feature extraction and selection, separate models were developed for intratumoral radiomics and habitat analysis to preoperatively predict LVI status in RC patients. A nomogram was created by combining the intratumoral radiomics model, habitat radiomics model, and clinical model. The performance and advantages of the model were evaluated through the area under the receiver operating characteristic curve (AUC), calibration curve and decision curve analysis (DCA).</p><p><strong>Results: </strong>Three habitats were clustered, and in the validation cohort, the habitat radiomics model demonstrated a higher AUC of 0.783, outperforming the intratumoral radiomics model, which had an AUC of 0.743. The nomogram, combining intratumoral radiomics features, habitat characteristics, and the clinical independent predictor (mrN stage), demonstrated the highest AUC of 0.833.</p><p><strong>Conclusion: </strong>The findings indicate that the model utilizing habitat characteristics demonstrates superior performance compared to the traditional intratumoral radiomics model. The nomogram, which incorporates intratumoral and habitat radiomic features along with the independent clinical predictor, demonstrated the highest accuracy for preoperative prediction of LVI in RC, representing a significant advancement in model performance.</p>","PeriodicalId":520541,"journal":{"name":"Abdominal radiology (New York)","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148932270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CT-derived visceral adiposity and paraspinal muscle depletion associated with severe acute pancreatitis according to the Revised Atlanta Classification.","authors":"Halil Tekdemir, Asiye Sözeri, Bilal Egemen Çifçi","doi":"10.1007/s00261-026-05782-w","DOIUrl":"https://doi.org/10.1007/s00261-026-05782-w","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate whether CT-derived visceral adiposity and skeletal muscle metrics are associated with severe acute pancreatitis (AP), as defined by the Revised Atlanta Classification, in a selected cohort of CT-imaged patients.</p><p><strong>Methods: </strong>This retrospective study included 254 adults with AP who underwent abdominal CT and had follow-up imaging. Mild and moderately severe AP were combined as the non-severe group and compared with severe AP. Visceral adipose tissue (VAT), subcutaneous adipose tissue (SAT), bilateral erector spinae and psoas muscle areas, and muscle attenuation were measured at L3 on the earliest available unenhanced CT series. ROC analysis with exploratory Youden cutoffs, DeLong tests, bootstrap internal validation, and age- and sex-adjusted logistic regression were performed.</p><p><strong>Results: </strong>The cohort included 198 non-severe and 56 severe AP cases. Severe AP was associated with higher VAT and SAT areas and lower muscle area and attenuation. VAT outperformed SAT (AUC 0.810 vs. 0.645; p = 0.00048), and erector spinae area outperformed psoas area (AUC 0.923 vs. 0.870; p = 0.0086). VAT (OR 4.88 per 5,000 mm² increase; p < 0.001) and erector spinae area (OR 2.71 per 1,000 mm² decrease; p < 0.001) remained independently associated with severe AP.</p><p><strong>Conclusion: </strong>CT-derived VAT and erector spinae muscle area were independently associated with Revised Atlanta-defined severe AP. These opportunistic imaging biomarkers may complement, rather than replace, clinical risk stratification, and the proposed thresholds require external validation.</p>","PeriodicalId":520541,"journal":{"name":"Abdominal radiology (New York)","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148932245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantitative assessment of postoperative urinary jet dynamics after unilateral ureteral stricture reconstruction using non-contrast cine MR urography.","authors":"Zheng Li, Tengxin Wang, Deying Wen, Xinyu Tang, Jiayu Wei, Jingran Peng, Qianlan Wan, Jiayu Sun, Yu Liu","doi":"10.1007/s00261-026-05776-8","DOIUrl":"https://doi.org/10.1007/s00261-026-05776-8","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate non-contrast cine magnetic resonance urography (MRU) for quantifying postoperative urinary jet dynamics in unilateral ureteral stricture disease (USD) and explore their relevance to ureteral functional recovery.</p><p><strong>Methods: </strong>This prospective single-center study included 53 patients examined within 1 week before and 3 months after surgery. Five 60-s cine acquisitions were obtained per examination. Two radiologists assessed image quality and measured urinary jet frequency and injection duration. Intraclass correlation coefficients (ICCs) assessed interobserver agreement. Jet parameters were compared between affected and contralateral ureters before and after surgery, and their correlations were analyzed.</p><p><strong>Results: </strong>Image quality and quantitative measurements showed excellent interobserver agreement (ICC = 0.895 and 0.910, respectively; both P < 0.001). Jet frequency and injection duration were lower in the affected than contralateral ureter before and after surgery (all P < 0.001) and increased in the affected ureter postoperatively (both P < 0.001). Contralateral jet frequency decreased modestly (P = 0.007), whereas injection duration did not change (P = 0.443). Frequency and duration were positively correlated under all conditions, most strongly in the preoperative affected ureter (r = 0.974, P < 0.001).</p><p><strong>Conclusion: </strong>Non-contrast cine MRU enabled quantitative assessment of postoperative urinary jet changes. Increased affected-side jet activity was consistent with improved ureteral urine transport and may provide indirect, complementary functional information during follow-up. Urinary jet parameters should not be considered standalone measures of complete recovery of ureteral function, and cine MRU should not replace CTU for anatomical evaluation.</p>","PeriodicalId":520541,"journal":{"name":"Abdominal radiology (New York)","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148922534","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Radiology considerations for the PREMIUM study: a multicenter randomized controlled trial of abbreviated MRI versus ultrasound for liver cancer screening in cirrhosis.","authors":"Dell P Dunn, Genta Dani, Ashu Sharma, George N Ioannou, Tamar H Taddei, Stephanie T Chang, Ifeyinwa Y Onyiuke, Beata M Planeta, Grant D Huang, Noel S Weiss, Timothy R Morgan, Jason A Dominitz, Ghassan K Abou-Alfa, Mustafa R Bashir, Michael V Beheshti, Amit G Singal, Cynthia A Moylan, Robin J Boland, Rajni L Mehta, Lynn F Buchwalder, Rafael B Fricks, Alexey Kotlik, Nhan V Do, Luis E Selva, Shari S Rogal, David E Kaplan, Jihane N Benhammou, Grace L Su, Linda M Mcdonald, Tassos C Kyriakides","doi":"10.1007/s00261-026-05720-w","DOIUrl":"https://doi.org/10.1007/s00261-026-05720-w","url":null,"abstract":"<p><p>This paper describes the rationale and radiology considerations in the implementation of the Preventing Liver Cancer Mortality through Imaging with Ultrasound versus MRI (PREMIUM) study. PREMIUM is a multicenter, randomized controlled trial sponsored by the Department of Veterans Affairs comparing dynamic contrast-enhanced (DCE) abbreviated MRI (aMRI) plus serum AFP versus ultrasound (US) plus serum AFP for hepatocellular carcinoma (HCC) screening in patients with cirrhosis. PREMIUM aims to randomize 4,700 participants across over 47 Veterans Affairs Medical Centers to semiannual surveillance for up to eight years, with HCC-related mortality as the primary endpoint. To date, 35 sites have been activated with 1,085 patients randomized. To ensure uniform implementation and reporting of per-protocol screening, the PREMIUM Radiology Workgroup developed standardized imaging protocols, structured LI-RADS-based reporting templates, and a centralized training program for radiologists and technologists. They also perform ongoing quality control on both scans and reports. The aMRI protocols utilize multiphasic post-contrast imaging to allow LI-RADS scoring. A non-contrast-enhanced aMRI protocol is available for participants who develop renal impairment or contrast allergy during the study. US protocols conform to US LI-RADS standards. Structured reporting promotes consistency in documentation of findings, visualization scores, and follow-up recommendations. A centralized Image Repository was established, incorporating advanced de-identification methods to remove metadata and pixel-embedded protected health information from imaging files. More than 20,000 curated liver MRI and US exams are anticipated, supporting both trial outcomes and future radiomics and artificial intelligence research. PREMIUM aims to determine whether screening for HCC with a DCE aMRI protocol reduces HCC-related mortality and also facilitates ancillary studies utilizing the Image Repository.</p>","PeriodicalId":520541,"journal":{"name":"Abdominal radiology (New York)","volume":" ","pages":""},"PeriodicalIF":2.2,"publicationDate":"2026-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148901805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}