AIM:The 2019 WHO classification of pancreatic ductal adenocarcinoma (PDAC) recognizes undifferentiated carcinoma with osteoclast-like giant cells (UCOG) as a rare subset. There is sparse literature on the imaging appearances of this type of cancer. Pathologists also increasingly recognize that poorly-differentiated PDAC may occasionally contain osteoclast-like giant cells (PDO). This study aims to compare the imaging features and natural history of these two groups. MATERIALS AND METHODS:In this retrospective case-controlled study, we searched the Institutional pathology and imaging databases for "pancreas cancer" and "osteoclasts." Of the 59 subjects identified, preoperative imaging (CT or MRI) and acceptable pathology data were available in 25 patients who formed the final study cohort. Two specialist abdominal radiologists independently reviewed the imaging findings. The cohort included 10 patients with PDO and 15 with UCOG. RESULTS:There were no differences in age or gender between these groups. On logistic regression analysis, only the presence of tumor hemorrhage (p=0.007), and pancreatic duct obstruction (p=0.02) were significantly different between the groups. UCOG had fewer metastases at presentation and follow-up, though the differences were not significant. UCOG had significantly higher overall survival (median 35.4 months vs. 10.7 months, p=0.007) and progression-free survival (median 33.0 months vs. 9.1 months, p=0.003), compared to PDO. CONCLUSION:The presence of a large (>6 cm) solid pancreatic mass that shows hemorrhage, exophytic growth, and lack of pancreatic duct obstruction may raise the possibility of UCOG. Despite larger size at presentation, these tumors generally have a better prognosis than the published prognosis for conventional PDAC.

Bias field artifacts in magnetic resonance imaging (MRI) scans introduce spatially smooth intensity inhomogeneities that degrade image quality and hinder downstream analysis. To address this challenge, we propose a novel variational Hadamard U-Net (VHU-Net) for effective body MRI bias field correction. The encoder comprises multiple convolutional Hadamard transform blocks (ConvHTBlocks), each integrating convolutional layers with a Hadamard transform (HT) layer. Specifically, the HT layer performs channel-wise frequency decomposition to isolate low-frequency components, while a subsequent scaling layer and semi-soft thresholding mechanism suppress redundant high-frequency noise. To compensate for the HT layer’s inability to model inter-channel dependencies, the decoder incorporates an inverse HT-reconstructed transformer block, enabling global, frequency-aware attention for the recovery of spatially consistent bias fields. The stacked decoder ConvHTBlocks further enhance the capacity to reconstruct the underlying ground-truth bias field. Building on the principles of variational inference, we formulate a new evidence lower bound (ELBO) as the training objective, promoting sparsity in the latent space while ensuring accurate bias field estimation. Comprehensive experiments on body MRI datasets demonstrate the superiority of VHU-Net over existing state-of-the-art methods in terms of intensity uniformity. Moreover, the corrected images yield substantial downstream improvements in segmentation accuracy. Our framework offers computational efficiency, interpretability, and robust performance across multi-center datasets, making it suitable for clinical deployment. The codes are available at https://github.com/Holmes696/Probabilistic-Hadamard-U-Net.

Automated 3D segmentation of prostate lesions from biparametric MRI (bp-MRI) is essential for reliable algorithmic analysis, but achieving high precision remains challenging. Volumetric methods must combine multiple modalities while ensuring anatomical consistency, but current models struggle to integrate cross-modal information reliably. While vision-language models (VLMs) are replacing the currently used architectural designs, they still lack the fine-grained, lesion-level semantics required for effective localized guidance. To address these limitations, we propose a new multi-encoder U-Net architecture incorporating three key innovations: (1) an alignment loss that enhances foreground text-image similarity to inject lesion semantics; (2) a heatmap loss that calibrates the similarity map and suppresses spurious background activations; and (3) a final-stage, confidence-gated multi-head cross-attention refiner that performs localized boundary edits in high-confidence regions. A phase-scheduled training regime stabilizes the optimization of these components. Our method consistently outperforms prior approaches, establishing a new state-of-the-art on the PI-CAI dataset through enhanced multi-modal fusion and localized text guidance. Our code is available at https://github.com/NUBagciLab/Prostate-Lesion-Segmentation.

PURPOSE:Distinguishing high-risk intraductal papillary mucinous neoplasms (IPMNs) from low-risk lesions remains a clinical challenge, often resulting in unnecessary procedures due to limited specificity of current methods. While radiomics and deep learning (DL) have been explored for pancreatic cancer, cyst-level malignancy risk stratification of IPMNs remains untapped. METHODS:Our multi-institutional assessed the feasibility of AI for predicting IPMN dysplasia grade using cyst-level image features using 359 T2-weighted (T2W) MRI images from seven centers. We developed and compared 2D and 3D radiomics-only, DL-only, and radiomics-DL fusion models using expert radiologist scoring as a baseline reference. Model performance was evaluated using held-out test data. RESULTS:The radiomics-DL fusion model showed the highest discriminatory ability on the test set AUC of 69.2%, outperforming the radiomics-only model, AUC of 66.5%. Expert accuracy varied widely from 37.4% to 66.7%, and the inter-rater agreement varied as well with weighted Cohen's kappa coefficients of 0.33-0.67. CONCLUSION:The fusion model, which combines DL with radiomics features from routine T2W MRI, shows promise for objective, cyst-level risk stratification of IPMNs in a multi-center cohort, outperforming radiomics-only models and nearly matching expert radiologists using only T2W and T1-weighted (T1W) sequences. While performance requires improvement for standalone clinical use, this approach offers a scalable, non-invasive method to potentially improve diagnostic accuracy and reduce unnecessary surgical interventions.

A broad spectrum of inflammatory and infiltrative conditions can affect the genitourinary (GU) system. Radiologists play a crucial role in diagnosing these disorders, and a strong understanding of these entities and their potential complications is essential. Imaging features are often key factors in identifying these conditions, assessing their severity, and guiding appropriate management. This review provides an overview of inflammatory and infiltrative disorders of the GU tract, focusing on their etiology, characteristic imaging findings, and potential complications to aid practicing radiologists in diagnosis.

We present the first federated learning (FL) approach for pancreas part (head, body, tail) segmentation in MRI, addressing a critical clinical challenge as a significant innovation. Pancreatic diseases exhibit marked regional heterogeneity—cancers predominantly occur in the head region while chronic pancreatitis causes tissue loss in the tail—making accurate segmentation of the organ into head, body, and tail regions essential for precise diagnosis and treatment planning. This segmentation task remains exceptionally challenging in MRI due to variable morphology, poor soft-tissue contrast, and anatomical variations across patients. Our novel contribution tackles two fundamental challenges: first, the technical complexity of pancreas part delineation in MRI, and second the data scarcity problem that has hindered prior approaches. We introduce a privacy-preserving FL framework that enables collaborative model training across seven medical institutions without direct data sharing, leveraging a diverse dataset of 711 T1W and 726 T2W MRI scans. Our key innovations include: (1) a systematic evaluation of three state-of-the-art segmentation architectures (U-Net, Attention U-Net, Swin UNETR) paired with two FL algorithms (FedAvg, FedProx), revealing Attention U-Net with FedAvg as optimal for pancreatic heterogeneity, which was never been done before; (2) a novel anatomically-informed loss function prioritizing region-specific texture contrasts in MRI. Comprehensive evaluation demonstrates that our approach achieves clinically viable performance despite training on distributed, heterogeneous datasets.

Pancreatic cancer is projected to be the second-deadliest cancer by 2030, making early detection critical. Intraductal papillary mucinous neoplasms (IPMNs), key cancer precursors, present a clinical dilemma, as current guidelines struggle to stratify malignancy risk, leading to unnecessary surgeries or missed diagnoses. Here, we introduce Cyst-X, a multi-center MRI benchmark and a federated learning framework for IPMN malignancy-risk stratification. The dataset comprises 1,461 abdominal MRI scans from 764 patients at seven international centers, with three-tier malignancy labels anchored in histopathology or three-year imaging follow-up and expert pancreas segmentations. The pipeline couples the PanSegNet pancreas segmenter with a 3D DenseNet-121 classifier and a parallel radiomics predictor. On internal cross-validation, the deep learning classifier reached a mean area under the receiver operating characteristic curve (AUC) of 0.85 (95

Artificial Intelligence (AI) is reshaping healthcare through advancements in clinical decision support and diagnostic capabilities. While human expertise remains foundational to medical practice, AI-powered tools are increasingly matching or exceeding specialist-level performance across multiple domains, paving the way for a new era of democratized healthcare access. These systems promise to reduce disparities in care delivery across demographic, racial, and socioeconomic boundaries by providing high-quality diagnostic support at scale. As a result, advanced healthcare services can be affordable to all populations, irrespective of demographics, race, or socioeconomic background. The democratization of such AI tools can reduce the cost of care, optimize resource allocation, and improve the quality of care. In contrast to humans, AI can potentially uncover complex relationships in the data from a large set of inputs and generate new evidence-based knowledge in medicine. However, integrating AI into healthcare raises several ethical and philosophical concerns, such as bias, transparency, autonomy, responsibility, and accountability. In this study, we examine recent advances in AI-enabled medical image analysis, current regulatory frameworks, and emerging best practices for clinical integration. We analyze both technical and ethical challenges inherent in deploying AI systems across healthcare institutions, with particular attention to data privacy, algorithmic fairness, and system transparency. Furthermore, we propose practical solutions to address key challenges, including data scarcity, racial bias in training datasets, limited model interpretability, and systematic algorithmic biases. Finally, we outline a conceptual algorithm for responsible AI implementations and identify promising future research and development directions.

Eye-tracking analysis plays a vital role in medical imaging, providing key insights into how radiologists visually interpret and diagnose clinical cases. In this work, we first analyze radiologists' attention and agreement by measuring the distribution of various eye-movement patterns, including saccades direction, amplitude, and their joint distribution. These metrics help uncover patterns in attention allocation and diagnostic strategies. Furthermore, we investigate whether and how doctors' gaze behavior shifts when viewing authentic (Real) versus deep-learning-generated (Fake) images. To achieve this, we examine fixation bias maps, focusing on first, last, short, and longest fixations independently, along with detailed saccades patterns, to quantify differences in gaze distribution and visual saliency between authentic and synthetic images.

Cholangiocarcinoma, a primary epithelial malignancy originating in the biliary tree, can be classified based on anatomical location into intrahepatic and extrahepatic cholangiocarcinoma. Extrahepatic cholangiocarcinoma (eCCA) is the more common of the two. CT and MRI play a central role in the diagnosis, staging, and management of eCCA, yet radiological reporting of eCCA often lacks uniformity and completeness which can hamper optimal treatment decision-making. Standardized reporting including standardized terminology and structured reports can address these shortcomings. Standardization produces clear, concise, and accurate terminology to facilitate communication between radiologists, surgeons, oncologists, pathologists, and interventionalists, which can be particularly important in complex cases where treatment hinges on discerning fine anatomical details. Structured report templates organize reporting elements in ordered sections to ensure consistency and completeness when conveying relevant imaging findings. In this manuscript, we aim to provide guidance on eCCA reporting, discussing the relevance of each proposed reporting element and presenting a recommended and structured eCCA reporting template. The proposed structured report, adapted from the template proposed by the Korean Society of Abdominal Radiology, is tailored particularly to North American clinical practice and addresses additional reporting elements such as background liver information and radial dimension.

ObjectiveThe aim of the study is to assess the validity of a recently published consensus magnetic resonance imaging (MRI) diagnostic algorithm for differentiating degenerating leiomyomas from uterine sarcomas and other atypical appearing uterine malignancies.MethodsAtypical uterine masses on pelvic MRI were identified using a radiology report search engine and teaching files with the keywords "atypical leiomyoma," "atypical fibroid," and "sarcoma." All cases were pathology-proven. Two radiologists blinded to clinical, surgical, and pathologic reports retrospectively and independently reviewed 40 pelvic MRI examinations dated 1/2007-9/2022 to determine whether the masses appeared benign or malignant, using the 2022 consensus atypical uterine mass flow chart. Imaging features assessed included intermediate/high signal intensity (SI) at T2-weighted imaging, high diffusion weighted imaging SI (equal or higher SI than endometrium or lymph nodes on high b value imaging), apparent diffusion coefficient (ADC) value <= 0.905 x 10-3 mm2/s, peritoneal metastases, and abnormal lymph nodes.ResultsAmong the 40 atypical uterine mass cases reviewed, 24 masses were benign (22 leiomyomas, 1 adenomyoma, and 1 borderline ovarian tumor) and 16 masses were malignant (6 leiomyosarcomas, 6 carcinosarcomas, 2 endometrial stromal sarcomas, 1 high-grade adenosarcoma, and 1 low-grade uterine sarcoma). Sensitivity, specificity, positive predictive value, and negative predictive value of whether a mass was benign or malignant were 75%, 95.8%, 92.3%, and 85% for reader 1, and 81.2%, 91.7%, 86.7%, and 88% for reader 2, respectively. Interrater agreement was strong, with a kappa statistic of 0.89. When excluding nonleiomyosarcoma uterine malignancies, sensitivity and negative predictive value improved to 100%.ConclusionsThe new consensus pelvic MRI algorithm for evaluating atypical uterine masses has good specificity, sensitivity, positive predictive value, and negative predictive value for determining malignancy, particularly for uterine sarcomas that are leiomyosarcomas. However, if ADC value is near but not below 0.905 x 10-3 mm2/s, the mass may still be malignant, especially if a b value lower than 1000 is used. If the atypical uterine mass is predominantly endometrial, morphological features on T2 and postgadolinium sequences should guide suspicion, as some atypical appearing nonleiomyosarcoma uterine malignancies may have an ADC value greater than 0.905 x 10-3 mm2/s.

Background/Objectives: Pancreatic ductal adenocarcinoma (PDAC) prediction in high-risk individuals is essential for early detection and improved outcome. While prior studies have utilized pancreatic radiomics for PDAC prediction, the added value of main pancreatic duct (MPD) features remains unclear. This study aims to assess the additional value of features of the main pancreatic duct (MPD) for predicting PDAC occurrence across different timeframes in advance. Methods: In total, 321 contrast-enhanced CT scans of the MPD and pancreas carried out across control, pre-diagnostic, and diagnostic cohorts were segmented, and radiomics were extracted. A support vector machine (SVM) classifier was used to classify the control and pre-diagnostic cohorts, with model performance assessed using area under the receiver operating characteristic (ROC) curves (AUCs) Results: The MPD diameter and volume significantly increased from the control to the pre-diagnostic and diagnostic CT scans (p < 0.05). The addition of features of the MPD to the pancreas improved the PDAC prediction AUC from 0.83 to 0.96 for subjects 6 months to 3 years in advance, from 0.81 to 0.94 for 3–6 years in advance, and 0.75 to 0.84 for 6–10 years in advance of diagnosis. Additionally, integrating MPD radiomics with diameter and volume significantly improved the AUC from 0.81 to 0.88 for subjects 6 months to 3 years in advance. Conclusions: Radiomic features from abdominal CT scans allow PDAC prediction up to 10 years in advance. Integrating MPD features, including diameter and volume, significantly improves PDAC prediction compared to using radiomics of the pancreas alone.

Noncirrhotic portal hypertension (NCPH) is an uncommon but important entity caused by impaired flow dynamics in the portal venous system in the absence of advanced fibrosis. The exact prevalence of this disease is unknown since many patients with NCPH are labeled as having cryptogenic cirrhosis. Numerous disease processes performed with different mechanisms can result in this entity. Based on the anatomic level of impairment of portal flow, NCPH is classified into prehepatic, intrahepatic, and posthepatic forms. The exact pathophysiology in many cases of intrahepatic NCPH is not well known, and there are overlapping terminologies used to describe histopathologic changes in the liver. The clinical and imaging findings are heterogeneous and are influenced by the mechanism and the underlying cause. In particular, patterns of portal hypertension and liver morphology are different among pre-, intra-, and posthepatic forms. All causes of NCPH can result in liver dysmorphism, but these changes are more drastic with intrahepatic and posthepatic forms (especially when associated with nodular regenerative hyperplasia) and can occasionally mimic cirrhosis. Prehepatic NCPH classically results in marked splenomegaly and large collateral formation with no ascites. On the other hand, ascites is the most common sign in posthepatic NCPH. Venographic pressure measurement and liver biopsy are required for definitive diagnosis. The authors review the current understanding of the mechanisms and causes of NCPH and discuss the approach to imaging findings, role of elastography, management, and complications. ©RSNA, 2025 Supplemental material is available for this article.

Roux-en-Y gastric bypass (RYGB) is a common and effective treatment of obesity. The development of an internal hernia after RYGB is the result of herniation of the small bowel through mesenteric defects created at the time of surgery. This can lead to further complications including recurrent abdominal pain and small bowel obstruction. In the most dire cases, closed-loop obstruction and/or volvulus can occur and lead to bowel ischemia and necrosis. Given the potentially severe complications of internal hernias after RYGB, it is incumbent on the radiologist to assess for them in all patients undergoing abdominal CT who have undergone RYGB, especially those presenting with abdominal pain. Detection of an internal hernia after RYGB at CT can be challenging. The authors discuss the postoperative anatomy after RYGB and the manner in which it can lead to internal hernias, the incidence of and risk factors for internal hernias, and the various signs at CT that can signal the presence of an internal hernia after RYGB. ©RSNA, 2025 Supplemental material is available for this article.

PURPOSE:Prostate Imaging Reporting and Data System (PIRADS) v2.1 scoring with multiparametric (mp) MRI has a pooled 90% negative predictive value (NPV). PSA density (PSAD) ≤ 0.15 ng/mL/cm3 has been shown to enhance mpMRI's NPV in non-Black men. Populations with higher disease prevalence are known to have lower NPVs. Given that Black men have higher prostate cancer prevalence, we evaluate sensitivity and NPV of mpMRI in Black vs non-Black men to assess possible mpMRI performance differences. As an exploratory objective, we investigate PSAD thresholds providing ≥ 90% sensitivity in Black men. MATERIALS AND METHODS:We prospectively recruited Black and non-Black men referred to outpatient urology clinics for abnormal PSA or prostate examination in 3 similar biomarker validation studies from 2017 to 2023 before MRI-informed diagnostic prostate biopsy. We combined the research cohorts with a retrospective clinical cohort of clinically similar Black and non-Black men from 1 academic institution who also underwent mpMRIs and MRI-informed biopsies. MRIs were scored using PIRADS version 2.0 or 2.1. RESULTS:Our analysis included 286 Black men and 965 non-Black men with PSA ≤ 15.0 ng/mL. PIRADS < 3 had an NPV of 77.1% vs 87.6% and a sensitivity of 90.7% vs 96.3% for Gleason grade group 2 to 5 prostate cancer in Black vs non-Black men, respectively (both P < .05). Using PSAD ≥ 0.09 for Black men with PIRADS 1 to 2 lesions increased sensitivity to 92.9%. CONCLUSIONS:PIRADS < 3 has a lower NPV and sensitivity in Black men. For negative prostate MRIs, PSAD ≥ 0.09 may be a better threshold for safe biopsy deferral in Black men to maintain a ≥ 90% sensitivity.

Accurate classification of Intraductal Papillary Mucinous Neoplasms (IPMN) is essential for identifying high-risk cases that require timely intervention. In this study, we develop a federated learning framework for multi-center IPMN classification utilizing a comprehensive pancreas MRI dataset. This dataset includes 652 T1-weighted and 655 T2-weighted MRI images, accompanied by corresponding IPMN risk scores from 7 leading medical institutions, making it the largest and most diverse dataset for IPMN classification to date. We assess the performance of DenseNet-121 in both centralized and federated settings for training on distributed data. Our results demonstrate that the federated learning approach achieves high classification accuracy comparable to centralized learning while ensuring data privacy across institutions. This work marks a significant advancement in collaborative IPMN classification, facilitating secure and high-accuracy model training across multiple centers.