Search Results (2,287)

Objective: To evaluate the feasibility of simulated ultra-low-dose CT (ULD-CT) enhanced with deep learning denoising (DLD) for detecting pelvic and hip fractures. Method: This Institutional Review Board-approved retrospective study was performed at a multisite, single academic institution between October 2020 and May 2021, including 30 full-dose CT (CTfull) exams of acute pelvic and hip trauma (10 normal, 10 “easy,” 10 “hard” cases by fracture conspicuity). Simulated low-dose CT images at 10% (CT10sim) and 5% (CT5sim) radiation dose were generated using a noise model-based algorithm and reconstructed from full-dose CT datasets. A commercial deep learning denoising algorithm enhanced these images, resulting in denoised low-dose CTs (CT10dld and CT5dld) for evaluation. The 90 resulting CT cases were reviewed independently for diagnostic accuracy, confidence, sufficiency, and imaging quality. Result: Diagnostic accuracy was similar across CT modalities overall (CTfull 80.8% [72.9, 86.9]; CT10dld 78.3% [70.1, 84.8]; CT5dld 77.5% [69.2, 84.1]) and within the easy and normal strata; in hard cases, accuracy was numerically lower for CT10dld (45.0%) and CT5dld (42.5%) than for CTfull (57.5%). Diagnostic sufficiency was similarly high across modalities (CTfull 91.7%, CT10dld 87.5%, CT5dld 88.3%). CT full was rated highest in perceived image quality across all strata (mean 4.21 ± 0.83 overall vs. 3.47 ± 0.97 for CT10dld and 3.23 ± 0.98 for CT5dld) and in diagnostic confidence (mean 4.61 ± 0.63 vs. 4.45 ± 0.71 and 4.41 ± 0.72, respectively), though neither translated into a corresponding drop in diagnostic accuracy overall. Inter-reader agreement was highest between MSK radiologists, reaching substantial agreement on CT10dld (κ = 0.760) and CT5dld (κ = 0.672). Conclusions: DLD-enhanced ULD-CT showed diagnostic accuracy and sufficiency similar to full-dose CT for pelvic and hip fracture detection, at a fraction of the radiation dose, though full-dose CT was rated higher in perceived image quality and diagnostic confidence and outperformed denoised low-dose CT numerically in hard cases. Full-dose CT remains the preferred modality for complex and high-energy trauma, while denoised low-dose CT modalities represent a promising option for straightforward presentations where radiation minimization is a priority. Full article

Background: Chronic thromboembolic disease is a recognised sequela of acute pulmonary embolism and may occur with or without pulmonary hypertension. The purpose of this study was to evaluate differences in chronic thromboembolic burden, lesion type, and distribution between chronic thromboembolic pulmonary disease without pulmonary hypertension (CTEPD) and chronic thromboembolic pulmonary hypertension (CTEPH). Methods: This retrospective single-centre study included patients with CTEPD or CTEPH by right heart catheterisation using 2022 ESC/ERS criteria between 2021 and 2022. Two CTEPH patients were randomly selected per CTEPD patient. CTPA studies were reviewed by a blinded thoracic radiologist, assessing 32 pulmonary vessels from the main to segmental arteries for chronic thromboembolic lesions. Groups were compared by disease distribution, most proximal lesion level, Qanadli obstruction index, lesion type, and location. Exploratory receiver operating characteristic (ROC) analysis assessed discriminatory performance. Results: The 44 CTEPD and 88 CTEPH patients included had no differences in age, BMI, or sex. CTEPH patients had shorter six-minute walk distance (p = 0.001), greater right ventricular dilation/dysfunction (p < 0.001), and lower prevalence of deep vein thrombosis (p = 0.03). CTPA identified more lesions in CTEPH (21.2 vs. 10.0 lesions/case, p < 0.001) across more lobes (4.8 vs. 3.4, p < 0.001), with more proximal main/lobar disease (p < 0.001). CT obstruction index was 51% in CTEPH and 26% in CTEPD (p < 0.001). Total lesion number best discriminated CTEPH from CTEPD (AUC 0.91; optimal cutoff, 16 lesions). Conclusions: CTEPH demonstrates a greater, more diffuse, and more proximal chronic thromboembolic lesion burden on CTPA than CTEPD. Full article

Background/Objectives: Pretreatment imaging may help estimate axillary response after neoadjuvant chemotherapy (NAC) in clinically node-positive (cN+) breast cancer. This study compared routinely available magnetic resonance imaging (MRI) and ultrasound (US) descriptors from the primary tumor and axillary nodes for predicting axillary nodal response, defined as postneoadjuvant pathologic node-negative status (ypN0). Methods: This retrospective multicenter study included 243 patients from three centers: 146 in the training cohort, 59 in the internal validation cohort, and 38 in the external validation cohort. The index breast tumor and axillary node were identified by a senior radiologist, and two radiologists independently assessed structured descriptors based on BI-RADS 2025. Least absolute shrinkage and selection operator regression and logistic regression were used to develop imaging-only, clinical-only, and clinicoradiologic models. Performance was evaluated using area under the curve (AUC), calibration, decision curve analysis, net reclassification improvement, and integrated discrimination improvement. Results: In the internal and external validation cohorts, the trimodal imaging model achieved AUCs of 0.761 and 0.806, and the clinicoradiologic model achieved the highest AUCs of 0.858 and 0.931, respectively. In pooled validation subgroup analyses, AUCs were 0.928, 0.804, and 0.700 for HR-positive/HER2-negative, HER2-positive, and triple-negative tumors, and 0.898 and 0.880 for cN1 and cN2–3 disease, respectively. Conclusions: MRI tumor descriptors provided the strongest imaging signal for ypN0 prediction, while US descriptors offered modest complementary information. The clinicoradiologic model may support pretreatment risk stratification and multidisciplinary planning for post-NAC axillary reassessment, but should not independently determine sentinel lymph node biopsy, axillary lymph node dissection, or omission of axillary staging. Full article

Background/Objectives: Lung-RADS was introduced to standardize the management of nodules detected during lung cancer screening. However, significant interobserver variability has been reported, and its consistency across different hospital settings remains insufficiently investigated. This study aimed to compare Lung-RADS categorization and diagnostic performance between tertiary and non-tertiary hospitals, and to evaluate interobserver variability and associated differences in recommended management. Methods: This single-tertiary-center, referral-based retrospective study included patients referred to a tertiary hospital after lung cancer screening at 29 non-tertiary hospitals between September 2019 and December 2023. CT images were reinterpreted at a tertiary hospital using Lung-RADS. A blinded review was performed by an independent thoracic radiologist, and interobserver variability was assessed using Cohen’s kappa. Discordance rate and major discordance (≥9-month follow-up difference) were determined. Sensitivity, specificity, and diagnostic accuracy were calculated and compared. Results: Sixty patients (median age, 63 years [interquartile range, 58–68]; 59 men and one woman) with 43 confirmed final diagnoses (18 of lung cancer and 25 of benign lesions) were included. Interobserver variability was fair between tertiary and non-tertiary hospitals (κ = 0.30), and between non-tertiary hospitals and thoracic radiologist (κ = 0.28), but almost perfect between tertiary hospital and thoracic radiologist (κ = 0.82). Lung-RADS discordance occurred in 50.0% of the cases (30/60), with 70.0% (21/30) classified as major discordance. Among the 43 patients with confirmed final diagnoses, specificity was significantly higher in tertiary hospital reports (68.0%, 95% CI 46.5–85.1) compared to non-tertiary hospital reports (20.0%, 95% CI 6.8–40.7; p = 0.001), while sensitivity was comparable (100.0%, 95% CI 81.5–100 vs. 88.9%, 95% CI 65.3–98.6; p = 0.480). Conclusions: Frequent discordances in Lung-RADS categorization were observed between tertiary and non-tertiary hospitals. Higher specificity was observed for tertiary hospital interpretations within this referral cohort. These discrepancies may affect patient management, highlighting the need for strategies to improve consistency. Full article

(1) Background: Neoadjuvant chemotherapy (NAC) is important for breast cancer, but prognosis varies widely. Ki67 and apparent diffusion coefficient (ADC) reflect proliferation and cellularity, respectively. This study evaluated the prognostic value of the Ki67/ADC ratio (KA) and post-treatment ADC change (δADC) in breast cancer patients receiving NAC, and developed a survival prediction model incorporating these indicators. (2) Methods: Two cohorts of breast cancer patients treated with NAC were collected. Pre- and post-treatment breast MRI with diffusion-weighted imaging were obtained; ADC values were measured by two blinded radiologists. KA was calculated as pre-treatment Ki67 divided by pre-treatment ADC, and δADC as post-ADC minus pre-ADC. Disease-free survival (DFS) was the primary outcome. Cox regression and a predictive Cox model were used. (3) Results: A total of 419 patients were analyzed. Both KA and δADC were associated with survival. In multivariable analysis, KA remained an independent prognostic factor (HR 0.40, 95% CI 0.19–0.84, p = 0.015). High KA was associated with worse prognosis, particularly in patients without pathological complete response. The model incorporating KA showed better predictive performance than clinicopathological variables alone and effectively stratified high- vs. low-risk patients. (4) Conclusion: KA is a promising complementary biomarker for prognosis in breast cancer patients undergoing NAC. Its integration into a prognostic model improved survival risk prediction and may aid individualized post-treatment management. Full article

Background/Objective: International recommendations exist for MRI evaluation of sacroiliac joints (SIJs) in adult spondylarthritis (SpA) and other joints in juvenile (J)SpA. However, consensus recommendations for MRI acquisition protocols for SIJs in JSpA are lacking. Our survey gathered information on current imaging practices on SIJ MRI and expert opinions about imaging protocols. Methods: A survey was sent to an international group of pediatric radiologists and rheumatologists. Participants were asked about practices regarding sequences/planes, use of contrast, and preferred sequences/planes for evaluating individual lesions. Results: There were 38 unique survey respondents (North America, n = 19; South America, n = 1; Europe, n = 12; Asia, n = 2; Australia, n = 2; unknown = 2) from 32 institutions with a median of 15 (range 3–32) years of experience. Most (93%) institutions use the 2nd sacral vertebral body posterior cortex to plan coronal oblique sequences; most perform these as non-fat-suppressed T1W and fluid-sensitive sequences for evaluation of damage and inflammation, respectively. Among the 84% of institutions performing small field-of-view imaging, all include a coronal oblique plane, and 78% also do an axial oblique plane. Of all institutions, 22% utilize gradient echo (GRE) sequences. Most respondents (79%) did not consider contrast necessary for evaluating SIJs. Conclusions: Areas of agreement for a consensus MRI protocol for SIJ evaluation in JSpA include using a non-contrast-enhanced protocol and the S2 vertebral body posterior cortex to plan coronal oblique sequences. Further international consensus is required concerning the optimal scan plane to prescribe for axial sequences and the incorporation of an erosion-specific sequence into standard protocols. Full article

Photon-counting computed tomography (PCCT) represents a detector-level transformation in CT imaging. Unlike conventional energy-integrating detectors, photon-counting detectors directly convert individual X-ray interactions into electrical pulses and classify them according to energy. This architecture enables electronic-noise rejection, smaller detector pixels, improved geometric dose efficiency, and intrinsic spectral acquisition. However, the images available to radiologists are not produced directly by the detector; energy-resolved photon counts must first undergo calibration, correction, projection formation, reconstruction, and material decomposition. This narrative review provides an educational framework linking X-ray attenuation physics, detector materials and architectures, energy thresholds, and detector nonidealities to the resulting PCCT images. It describes conventional polyenergetic and ultra-high-resolution images, virtual monoenergetic imaging, iodine maps, virtual non-contrast imaging, calcium and bone subtraction, virtual non-calcium imaging, effective atomic number maps, electron-density maps, and emerging K-edge techniques. Particular emphasis is placed on the clinical purpose and limitations of each reconstruction, including noise, artifacts, partial-volume effects, misregistration, incomplete subtraction, calibration dependence, and limited cross-platform comparability. Practical considerations for protocol design, image selection, interpretation workflow, and spectral-data archiving are also discussed. Understanding the pathway from photon detection to image formation is essential for selecting the appropriate reconstruction, avoiding misinterpretation, and integrating PCCT effectively into clinical radiology. Full article

Background: Ultra-high-frequency ultrasound (UHFUS), performed in the present study using 48 and 70 MHz transducers, enables high-resolution assessment of superficial tissues and may provide useful information on the morphology, internal architecture, vascularity, and anatomical relationships of oral cavity lesions. Methods: This retrospective single-center study included consecutive patients examined between January 2025 and June 2026. Of 137 eligible cases, five were excluded because of inadequate image or cine-loop quality, leaving 132 lesions for analysis. All examinations were performed by the same experienced radiologist using 48 and 70 MHz linear probes. Each lesion was assessed in B-mode in at least two orthogonal planes and with Color Doppler. Archived anonymized examinations were reviewed using a predefined structured form. Morphology, margins, echogenicity, echotexture, composition, posterior acoustic features, vascularity, dimensions, presumed plane of origin, and involvement of adjacent anatomic layers were evaluated. The qualitative synthesis was performed jointly by a radiologist and an oral pathologist, with disagreements resolved by consensus. Results: UHFUS allowed detailed visualization of mucosal, submucosal, muscular, and bone/periodontal interfaces and enabled qualitative characterization of lesion boundaries, internal structure, vascular patterns, and local extension. The combined use of 48 and 70 MHz probes provided complementary information according to lesion depth and tissue composition. Five representative histologically confirmed cases from the study cohort illustrated reactive/inflammatory, benign neoplastic, and malignant conditions. One additional clinically confirmed gingival fistula, not included in the analytical cohort, was presented solely as an illustrative example of a superficial fistulous tract detectable with UHFUS. Conclusions: UHFUS provides detailed, layer-based assessment of oral cavity lesions and may complement clinical examination and histopathology in lesion characterization and preoperative evaluation. Sonographic findings should be interpreted within a multimodal diagnostic framework rather than as stand-alone criteria. Full article

Parallel to the increased use of immune checkpoint inhibitors (ICIs), the incidence of immune-related adverse events (irAEs) is also increasing. Almost all organs can be affected by the immune-mediated response, including the liver, pancreas and biliary tract. Immune-Mediated Hepatitis is a common complication of ICI therapy, while cholangitis, cholecystitis and pancreatic involvement are less frequent. Emerging evidence from clinical trials and real-world data series helps us better understand the risk factors, diagnostic challenges and management strategies for these irAEs. With wider use of ICIs, more data are also available on the management of special populations with comorbidities and patients with difficult-to-treat or treatment-resistant adverse events, but larger prospective studies and more robust evidence are required for further recommendations on their management and ICI reintroduction. In clinical practice, a multidisciplinary approach to the management of ICI-mediated complications is advised, with close collaboration among specialties such as oncologists, gastroenterologists or hepatologists, pathologists, radiologists and others. While Immune-Mediated Hepatitis is a common irAE of ICI therapy, pancreato-biliary involvement is often overlooked and underdiagnosed. These irAEs require multimodal management, development of new biomarkers and prediction models to facilitate decision-making and improve patient outcomes. Full article

While the value of XR has been broadly demonstrated in the literature, there is comparatively less empirical work seeking to establish where AR could effectively be placed within the training pathway. This is particularly true in radiology, where training relies heavily on anatomical comprehension, and AR has been proposed as a tool to support this through enhanced 3D visualisation of complex anatomical structures. A series of seven interviews with radiologists and radiology registrars was conducted, using AR anatomy tasks with the Microsoft HoloLens 2 and Meta Quest 3 to engage participants in a rich dialogue around the educational value of AR in radiological training. Reflexive thematic analysis was employed to interpret the resulting data. Four themes were generated, revealing a perceived stage specific utility whereby AR’s value is greatest for early-stage trainees and diminishes with experience, alongside a need for AR to integrate with, rather than replace, the traditional 2D methods used in practice. These themes were mapped to two design considerations for AR-enabled radiological curricula that stand as the contribution of this work; prioritising early-stage training through a structured graduation pathway into traditional practice and positioning AR as a supplement to existing training rather than a replacement for it. Full article

Primary hepatic perivascular epithelioid cell tumors (PEComas) are rare mesenchymal neoplasms that involve both melanocytic and smooth muscle differentiation. Primary hepatic PEComas remain a challenging condition for radiologists, pathologists, and surgeons. Our review provides an updated, clinically oriented synthesis of the available evidence on primary hepatic PEComas, integrating recent developments in diagnosis, imaging, histopathology, molecular biology, prognostic stratification, surgical and systemic treatment, and long-term surveillance. Although the majority of hepatic PEComas generally exhibit a slowly progressive clinical course, a small subgroup of them is characterized by aggressive biological behavior with an increased risk of recurrence, distant metastases, and disease-related mortality. As PEComas can resemble other hypervascular liver lesions such as hepatocellular carcinoma and hemangioma, preoperative diagnosis based on imaging techniques can be very difficult. Furthermore, the final diagnosis is usually made by histopathological examination of the surgical specimen, which reports characteristic expression of both smooth muscle markers and melanocytic markers such as HMB-45 and Melan-A. Although mTOR inhibitors have demonstrated antitumor activity in advanced PEComas, evidence specifically supporting their use in primary hepatic PEComas remains limited. Prognostic stratification, treatment selection, and long-term follow-up of primary hepatic PEComa remain major challenges. Further multicenter studies are needed to improve risk assessment and develop evidence-based guidelines for the management of these rare primary liver neoplasms. Full article

Classifying benign and malignant lung nodules from computed tomography (CT) images remains difficult because lung nodules can be hard to classify, and unimodal models cannot capture complementary diagnostic information. Despite the success of deep learning, existing methods rely only on image information and miss semantic information that can be obtained from an expert radiologist’s knowledge. Hence, the authors propose a new multimodal lung nodule classification model in this study, named the Graph-Guided Fusion Network (R-GGFN), that combines three-dimensional (3D) CT image features and structured radiologist annotations. The proposed architecture consists of three models. A 3D ResNet-18 network for image feature extraction, an MLP network for encoding semantic information, and a Graph Attention Network (GAT) for capturing inter-nodule relationships and fusing multimodal information with the graph. We add a tabular skip connection to preserve discriminative semantic features and use focal loss to address imbalance during training. To prevent data leakage, we partitioned the publicly available LIDC-IDRI dataset at the patient level. Experimental results on a held-out patient-level test set, accessed only once after model selection was finalized, show that the proposed R-GGFN achieves an accuracy of 85.21%, an AUROC of 0.9147, a PR-AUC of 0.9213, and an F1-score of 0.8609. Among all unimodal and multimodal baselines internally evaluated, R-GGFN achieved the best value on every reported metric, including accuracy, AUROC, PR-AUC, F1-score, Precision, sensitivity, and specificity. Furthermore, the proposed approach enhances model transparency by combining explainable AI techniques (e.g., 3D Grad-CAM, SHAP, and graph visualization) to explain the model at the image, feature, and graph levels. The results show that the graph-guided multimodal fusion method can fully leverage complementary image and semantic information, improving diagnostic accuracy and interpretability. The framework proposed here is a good and understandable computer-aided diagnosis decision-support system for lung cancer and a step towards future external dataset validation. Full article

Magnetic resonance imaging (MRI) is universally recognized as the gold standard for evaluating anterior cruciate ligament (ACL) injuries. However, differentiating partial tears from complete ruptures using the standard sagittal plane remains a diagnostic challenge. The oblique coronal orientation of the ACL often leads to volume averaging artifacts and inaccurate interpretations. While axial imaging offers a favorable alternative, distal tears near the tibial attachment are frequently missed. This review synthesizes current concepts in the anatomical and radiological evaluation of the ACL and introduces the “Namaste sign,” a novel and proposed preliminary imaging marker observed on coronal MRI to help assess ACL integrity. Grounded in the distinct native double-bundle architecture of the ACL, the Namaste sign utilizes the coronal plane to evaluate the transverse relationship and physiological tension of the anteromedial and posterolateral bundles. In a normal knee, these bundles converge symmetrically from their distinct tibial footprints and maintain tight contact with the lateral femoral condyle, mimicking hands pressed together in a traditional “Namaste” gesture. This article details the anatomical basis of this sign, provides a systematic method for its identification, and illustrates how morphological variations such as “broken hands,” “absent hands,” “absent proximal hug,” or “separation of hands” may correspond to specific ACL lesions. As a preliminary conceptual marker, the Namaste sign is intended to serve as an educational adjunct to combined three-plane evaluation rather than a standalone diagnostic criterion. Notably, this sign is not applicable to postoperative ACL reconstructions. A preliminary pilot study of 50 cases utilizing thin-slice MRI (≤3 mm) demonstrated nearly 100% visibility of the sign, 98% diagnostic accuracy, and almost perfect inter-observer agreement between two radiologists with more than 10 years of experience (Cohen’s kappa = 0.92). However, future diagnostic studies with rigorous arthroscopic reference standards are required to establish its clinical performance and reliability in larger cohorts. Full article

Objectives: The objective of this study was to evaluate the impact of virtual monoenergetic image (VMI) reconstructions derived from photon-counting computed tomography (PCCT) on the assessment of carotid arteries, with a focus on optimizing keV selection based on plaque composition. Methods: This retrospective study included 111 patients (mean age 80 ± 7.5 years; 64 men; 47 women) with carotid sclerosis who underwent PCCT between April 2022 and February 2023. One lesion was analyzed per patient, each containing both calcified and non-calcified components. Quantitative measurements were performed in calcified plaque across energy levels from 40 to 120 keV and comprised attenuation, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), corrected image noise (CIN) and artifact index (AIX). Two radiologists independently rated image quality, artifacts, and diagnostic assessability of both components using five-point scales. Results: Attenuation and CNR were highest at 40 to 50 keV, where CIN and AIX were also greatest. SNR followed a U-shaped course, lowest at 90 keV and highest at 110 to 120 keV, where intraluminal attenuation was too low for reliable luminal delineation. Reader ratings were highest at 40 to 50 keV for non-calcified components and at 70 to 80 keV for calcified plaque, with good interobserver agreement throughout (κ 0.74 to 0.92). After correction for multiple testing, adjacent energy levels were frequently indistinguishable. Conclusions: Optimal PCCT VMI energy levels depend on plaque composition. The findings support implementing standardized protocols with automatic dual-range reconstructions (40–50 keV and 70–80 keV) to enable efficient, individualized carotid plaque assessment in clinical practice. Full article

Multimodal learning has gained attention in recent years due to its ability to effectively utilize data features from various modalities. Diagnosing the vulnerability of atherosclerotic plaques directly from carotid 3D MRI images is challenging for both radiologists and conventional 3D vision networks. In clinical practice, radiologists assess patients using a multimodal approach that incorporates various imaging modalities and domain-specific expertise, paving the way for the creation of multimodal diagnostic networks. In this study, we proposed an effective framework to leverage radiologists’ domain knowledge to improve the automated diagnosis of carotid plaque vulnerability through variational inference and multimodal knowledge distillation (VMD). This framework excels in harnessing cross-modality prior knowledge from limited image annotations and radiology reports within training data, thereby enhancing the diagnostic network’s accuracy for unannotated 3D MRI images. We validated the proposed VMD framework on our in-house dataset, demonstrating its effectiveness. Full article