Search Results (1,873)

Introduction: This study evaluated the performance of automated dual-energy computed tomography (DECT)-based quantification of perfusion defects (PDs) in acute pulmonary embolism and examined its correlation with clinical parameters. Methods: We retrospectively analyzed data from 171 patients treated for moderate-to-severe acute pulmonary embolism, who underwent DECT imaging at two separate time points. PDs were quantified using a fully automated AI-based segmentation method that relied exclusively on iodine perfusion maps. This was compared with a semi-automatic clinician-guided segmentation, where radiologists manually adjusted thresholds to eliminate artifacts. Clinical variables including the Miller obstruction score, right-to-left ventricular diameter ratio, oxygen saturation, and patient-reported symptoms were also collected. Results: The semiautomatic method demonstrated stronger correlations with embolic burden (Miller score; r = 0.4, p < 0.001 at follow-up) and a negative correlation with oxygen saturation (r = −0.2, p = 0.04). In contrast, the fully automated AI-based quantification consistently produced lower PD values and demonstrated weaker associations with clinical parameters. Conclusions: Semiautomatic quantification of PDs currently provides superior accuracy and clinical relevance for evaluating lung PDs in acute pulmonary embolism. Future multimodal AI models that incorporate both anatomical and clinical data may further enhance diagnostic precision. Full article

Background/Objectives: The diagnosis of pediatric dental conditions from panoramic radiographs is uniquely challenging due to the dynamic nature of the mixed dentition phase, which can lead to subjective and inconsistent interpretations. This study aims to develop and rigorously validate an advanced deep learning model to enhance diagnostic accuracy and efficiency in pediatric dentistry, providing an objective tool to support clinical decision-making. Methods: An initial comparative study of four state-of-the-art YOLO variants (YOLOv8, v9, v10, and v11) was conducted to identify the optimal architecture for detecting four common findings: Dental Caries, Deciduous Tooth, Root Canal Treatment, and Pulpotomy. A stringent two-tiered validation strategy was employed: a primary public dataset (n = 644 images) was used for training and model selection, while a completely independent external dataset (n = 150 images) was used for final testing. All annotations were validated by a dual-expert team comprising a board-certified pediatric dentist and an experienced oral and maxillofacial radiologist. Results: Based on its leading performance on the internal validation set, YOLOv11x was selected as the optimal model, achieving a mean Average Precision (mAP50) of 0.91. When evaluated on the independent external test set, the model demonstrated robust generalization, achieving an overall F1-Score of 0.81 and a mAP50 of 0.82. It yielded clinically valuable recall rates for therapeutic interventions (Root Canal Treatment: 88%; Pulpotomy: 86%) and other conditions (Deciduous Tooth: 84%; Dental Caries: 79%). Conclusions: Validated through a rigorous dual-dataset and dual-expert process, the YOLOv11x model demonstrates its potential as an accurate and reliable tool for automated detection in pediatric panoramic radiographs. This work suggests that such AI-driven systems can serve as valuable assistive tools for clinicians by supporting diagnostic workflows and contributing to the consistent detection of common dental findings in pediatric patients. Full article

Introduction: Although lipomas are common benign tumors found in adults, lipomas of the bladder are extremely rare. Bladder lipomas are infrequently reported in the urologic literature, with only 19 cases published worldwide. These can present as a mass on cystoscopy and cause irritative voiding symptoms, depending on their location. Upon transurethral resection, seeing fat can be concerning for a perforation, as lipoma can be mistaken for extravesical fat. Hence, familiarity with this rare entity is of paramount importance for urologists to prevent unnecessary investigations and interventions that are needed in case of a true bladder perforation. Case presentation: This study presents a case of bladder lipoma in a 73-year-old male with end-stage renal disease who presented for pretransplant urologic evaluation due to microscopic hematuria and irritative lower urinary tract symptoms (LUTS). During cystoscopy, a bladder mass was seen, and a transurethral resection of the bladder tumor (TURBT) revealed bright yellow adipose tissue immediately underneath the bladder mucosa. Concerns about perforation were obviated when seeing intact detrusor muscle underneath, visually confirming the integrity of the bladder wall. The resection was completed, and the CT scan was re-read with the radiologist, which confirmed the presence of a lipoma that was missed pre-operatively due to patient’s oliguria and collapsed bladder. No catheter drainage or cystogram was performed based on these findings. Outcome: The patient healed without any complications. Histopathology confirmed the diagnosis of a mature lipoma. The patient was cleared for transplant from a urologic standpoint and had a successful renal transplantation without delay. Discussion: This case documents the anomalous occurrence of a lipoma within the bladder and supports maintaining a broad differential, including liposarcoma, angiomyolipoma, and other non-malignant fatty tumors during the evaluation of a bladder mass. Full article

Background and Objectives: The causes and clinical outcomes of renal perfusion abnormalities occurring after para-aortic lymphadenectomy (PANDx) for gynecologic malignancies are unknown. We investigated the potential involvement of accessory renal artery (ARA) obstruction in their development by reassessing perioperative contrast-enhanced computed tomography (CECT). Materials and Methods: This retrospective study investigated a clinical database to identify urinary contrast defects using CECT in all patients who had undergone PANDx between January 2020 and December 2024. The perfusion defects in the kidney detected by CECT were extracted by a gynecologic oncologist and evaluated by a radiologist and urologist for suspected obstruction of ARAs. Results: Postoperative renal contrast defects were observed in 3.8% (6/157) of patients. Renal parenchymal fibrosis, cortical atrophy, and parenchymal thinning were observed as universal findings in all patients showing renal contrast defects. In five of the six cases, ARAs supplying the infarcted renal segments were identified on preoperative CECT, and arterial obstruction was confirmed on postoperative imaging. The remaining case was considered to be latent pyelonephritis. All five patients underwent laparotomy, and preoperative CECT failed to detect ARAs. The median resected para-aortic lymph node was 23 nodes (range: 15–33) in five patients, showing no statistically significant difference compared to patients without perfusion abnormalities (p = 0.19). Postoperative serum creatinine levels remained stable. Conclusions: ARA obstruction appears to be a risk factor for segmental renal infarction after para-aortic lymphadenectomy in gynecological malignancies; however, the clinical impact on urinary function may be limited. Awareness of this potential complication is essential for gynecologic oncologists performing PANDx. Full article

Diagnosing digital flexor tendon sheath (DFTS) pathologies, particularly manica flexoria (MF) tears, can be challenging with standard imaging modalities. Standing low-field MRI tenography (MRIt) may improve the detection rate of MF tears. This study aimed to compare ultrasonography, contrast radiography, pre-contrast MRI, and MRIt to detect naturally occurring MF lesions in horses undergoing tenoscopy. Ten horses with a positive DFTS block, which underwent contrast radiography, ultrasonography, MRI, MRIt, and tenoscopy were included. Two radiologists evaluated the images and recorded whether an MF lesion was present and determined the lesion side. Sensitivity and specificity were calculated for each modality using tenoscopy as a reference. MRIt and contrast radiography detected MF lesions with the same frequency, both showing 71% sensitivity and 100% specificity. Pre-contrast MRI and ultrasonography detected MF lesions with a lower sensitivity (57%); however, the MRI (100%) demonstrated a higher specificity than ultrasonography (33%). Adding contrast in MRI changed the sensitivity from (4/7 lesions) 57% to (5/7 lesions) 71%, with a constant high specificity (100%). MRIt diagnoses MF tears with a similar sensitivity to contrast radiography, with the same specificity, but with the added benefit of lesion laterality detection. The combined advantages of the anatomical detail of the T1 sequence and the post-contrast hyperintense appearance of the fluid may help diagnose MF tears and identify intact MFs. However, this needs to be substantiated in a larger number of cases. Full article

Introduction: Breast density is a well-recognized factor in breast cancer risk assessment, with higher density linked to increased malignancy risk and reduced sensitivity of conventional mammography. Background parenchymal enhancement (BPE), observed in contrast-enhanced imaging, reflects physiological contrast uptake in non-pathologic breast tissue. While extensively characterized in breast MRI, the role of BPE in contrast-enhanced mammography (CEM) remains uncertain due to inconsistent findings regarding its correlation with breast density and cancer risk. Unlike breast density—standardized through the ACR BI-RADS lexicon—BPE lacks a uniform classification system in CEM, leading to variability in clinical interpretation and research outcomes. To address this gap, we introduce the BPE-CEM Standard Scale (BCSS), a structured four-tiered classification system specifically tailored to the two-dimensional characteristics of CEM, aiming to improve consistency and diagnostic alignment in BPE evaluation. Materials and Methods: In this retrospective single-center study, 213 patients who underwent mammography (MG), ultrasound (US), and contrast-enhanced mammography (CEM) between May 2022 and June 2023 at the “A. Perrino” Hospital in Brindisi were included. Breast density was classified according to ACR BI-RADS (categories A–D). BPE was categorized into four levels: Minimal (< 10% enhancement), Light (10–25%), Moderate (25–50%), and Marked (> 50%). Three radiologists independently assessed BPE in a subset of 50 randomly selected cases to evaluate inter-observer agreement using Cohen’s kappa. Correlations between BPE, breast density, and age were examined through regression analysis. Results: BPE was Minimal in 57% of patients, Light in 31%, Moderate in 10%, and Marked in 2%. A significant positive association was found between higher breast density (BI-RADS C–D) and increased BPE (p < 0.05), whereas lower-density breasts (A–B) were predominantly associated with minimal or light BPE. Regression analysis confirmed a modest but statistically significant association between breast density and BPE (R² = 0.144), while age showed no significant effect. Inter-observer agreement for BPE categorization using the BCSS was excellent (κ = 0.85; 95% CI: 0.78–0.92), supporting its reproducibility. Conclusions: Our findings indicate that breast density is a key determinant of BPE in CEM. The proposed BCSS offers a reproducible, four-level framework for standardized BPE assessment tailored to the imaging characteristics of CEM. By reducing variability in interpretation, the BCSS has the potential to improve diagnostic consistency and facilitate integration of BPE into personalized breast cancer risk models. Further prospective multicenter studies are needed to validate this classification and assess its clinical impact. Full article

Background/Objectives: To develop a DL-based model predicting recurrence risk in HER2-low breast cancer patients and to compare performance of the MRI-alone, clinicopathologic-alone, and combined models. Methods: We analyzed 453 patients with HER2-low breast cancer who underwent surgery and preoperative breast MRI between May 2018 and April 2022. Patients were randomly assigned to either a training cohort (n = 331) or a test cohort (n = 122). Imaging features were extracted from DCE-MRI and ADC maps, with regions of interest manually annotated by radiologists. Clinicopathological features included tumor size, nodal status, histological grade, and hormone receptor status. Three DL prediction models were developed: a CNN-based MRI-alone model, a clinicopathologic-alone model based on a multi-layer perceptron (MLP) and a combined model integrating CNN-extracted MRI features with clinicopathological data via MLP. Model performance was evaluated using AUC, sensitivity, specificity, and F1-score. Results: The MRI-alone model achieved an AUC of 0.69 (95% CI, 0.68–0.69), with a sensitivity of 37.6% (95% CI, 35.7–39.4), specificity of 87.5% (95% CI, 86.9–88.2), and F1-score of 0.34 (95% CI, 0.33–0.35). The clinicopathologic-alone model yielded the highest AUC of 0.92 (95% CI, 0.92–0.92) and sensitivity of 93.6% (95% CI, 93.4–93.8), but showed the lowest specificity (72.3%, 95% CI, 71.8–72.8) and F1-score of 0.50 (95% CI, 0.49–0.50). The combined model demonstrated the most balanced performance, achieving an AUC of 0.90 (95% CI, 0.89–0.91), sensitivity of 80.0% (95% CI, 78.7–81.3), specificity of 83.2% (95% CI: 82.7–83.6), and the highest F1-score of 0.55 (95% CI, 0.54–0.57). Conclusions: The DL-based model combining MRI and clinicopathological features showed superior performance in predicting recurrence in HER2-low breast cancer. This multimodal approach offers a framework for individualized risk assessment and may aid in refining follow-up strategies. Full article

Targeted radioligand therapy (RLT) is an emerging field in anticancer therapeutics with great potential across tumor types and stages of disease. While much progress has focused on agents targeting somatostatin receptors and prostate-specific membrane antigen (PSMA), the same advanced radioconjugation methods and molecular targeting have spurred the development of numerous theranostic combinations for other targets. A number of the most promising agents have progressed to clinical trials and are poised to change the landscape of positron emission tomography (PET) imaging. Here, we present recent data on some of the most important emerging molecular targeted agents with their exemplar clinical images, including agents targeting fibroblast activation protein (FAP), hypoxia markers, gastrin-releasing peptide receptors (GRPrs), and integrins. These radiopharmaceuticals share the promising characteristic of being able to image multiple types of cancer. Early clinical trials have already demonstrated superiority to ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) for some, suggesting the potential to supplant this longstanding PET radiotracer. Here, we provide a primer for practicing radiologists, particularly nuclear medicine clinicians, to understand novel PET imaging agents and their clinical applications, as well as the availability of companion targeted radiotherapeutics, the status of their regulatory approval, the potential challenges associated with their use, and the future opportunities and perspectives. Full article

Background: Post-hepatectomy liver failure (PHLF) is the most worrisome complication after a major hepatectomy and is the leading cause of postoperative mortality. The most important predictor of PHLF is the future liver remnant (FLR), the volume of the liver that will remain after the hepatectomy, representing a major concern for hepatobiliary surgeons, radiologists, and patients. Therefore, an accurate preoperative assessment of the FLR and the prediction of PHLF are crucial to minimize risks and enhance patient outcomes. Recent radiomics and deep learning models show potential in predicting PHLF and the FLR by integrating imaging and clinical data. However, most studies lack external validation and methodological homogeneity and rely on small, single-center cohorts. This review outlines current CT-based approaches for surgical risk stratification and key limitations hindering clinical translation. Methods: A literature analysis was performed on the PubMed Dataset. We reviewed original articles using the subsequent keywords: [(Artificial intelligence OR radiomics OR machine learning OR deep learning OR neural network OR texture analysis) AND liver resection AND CT]. Results: Of 153 pertinent papers found, we underlined papers about the prediction of PHLF and about the FLR. Models were built according to machine learning (ML) and deep learning (DL) automatic algorithms. Conclusions: Radiomics models seem reliable and applicable to clinical practice in the preoperative prediction of PHLF and the FLR in patients undergoing major liver surgery. Further studies are required to achieve larger validation cohorts. Full article

Background/Objectives: Although MRI with fat-suppression sequences is the gold standard for diagnosis of bone marrow edema (BME), Dual-Layer Spectral CT (DL-SCT) with electron density (ED) provides a viable alternative, particularly in situations where an MRI is not accessible. Using MRI as the reference standard, this study analyzed how DL-SCT with ED reconstructions may be a valid alternative in the detection of BME. Methods: This retrospective study included 28 patients with a suspected diagnosis of BME via MRI conducted between March and September 2024. Patients underwent DL-SCT using ED reconstructions obtained through IntelliSpace software v. 12.1. Images were evaluated by two experienced radiologists and one young radiologist in a blinded way, giving a grade from 0 to 3 to classify BME (0 absence; 1 mild; 2 moderate; 3 severe). To reduce the recall bias effect, the order of image evaluations was set differently for each reader. p-Values were considered significant when <0.05. Fleiss’ Kappa was used to assess inter-rater reliability: agreement was considered poor for k < 0; slight for k 0.01–0.20; fair for 0.21–0.40; moderate for 0.41–0.60; substantial for 0.61–0.80; and almost perfect for 0.81–1.00. Results: All the readers detected the presence or absence of BME using DL-SCT. Inter-rater reliability for grade 0 resulted in 1 (p-value < 0.001); for grade 1: 0.21 (p-value < 0.001); for grade 2: 0.197 (p-value < 0.001); and for grade 3: 0.515 (p-value < 0.001). Conclusions: ED reconstructions allowed the identification of BME presence or absence in all analyzed cases, thus suggesting DL-SCT as a potentially effective method for its detection. Full article

Background/Objectives: To evaluate the diagnostic performance of non-enhanced MRA in detecting intratumoral aneurysms in renal AML, using digital subtraction angiography (DSA) as the reference standard. Methods: Fourteen female patients (mean age, 39 years; range, 21–57 years) who received prophylactic transcatheter arterial embolization (TAE) for non-hemorrhagic renal AML(s) between July 2010 and September 2018 were included in this study. All received a non-enhanced MRA scan prior to TAE. Non-enhanced MRA images were obtained using the flow-in technique with three-dimensional balanced steady-state free precession (SSFP). The MRA and DSA images were jointly evaluated by three radiologists. In this study, significant aneurysms were defined as aneurysms with a diameter of 3 mm or more within the renal AML. The MRA images assessed the number and location of significant aneurysms. The DSA images were used as the reference standard. Results: DSA identified 30 significant aneurysms in eight kidneys; MRA identified 26, giving a sensitivity of 87%. There were no false positives, resulting in a specificity of 100%. Conclusions: Flow-balanced SSFP MRA is effective in detecting significant aneurysms in renal AML and could be a viable alternative for patient follow-up. Full article

Background/Objectives: Accurate visualization of the Achilles tendon enthesis is critical for distinguishing mechanical, degenerative, and inflammatory pathologies. Although ultrasonography is the first-line modality for suspected enthesis disease, recent technical advances may expand the role of magnetic resonance imaging (MRI). This study evaluated the utility of ultra-short echo time (UTE) and zero echo time (ZTE) sequences versus proton density-weighted imaging (PD-WI) for depicting the enthesis organ in healthy volunteers. Methods: In this institutional review board (IRB)-approved prospective single-center study, 50 asymptomatic adult volunteers underwent 3-Tesla hindfoot MRI with fat-suppressed PD-WI, UTE, and ZTE between 2018 and 2023. Four radiologists assessed image quality, signal-to-noise ratio, visibility, and abnormal high signal intensities (SIs) of the periost, sesamoid, and enthesis fibrocartilages (PCa, SCa, and ECa, respectively). Statistical tests included Chi-square, McNemar, paired Wilcoxon, and Benjamini–Hochberg adjustments for multiple comparisons. Results: The median age was 36 years (range: 20–51); 58% women were included. PD-WI and ZTE sequences were always available while UTE was unavailable in 24% of patients. PD-WI consistently failed to concomitantly visualize all fibrocartilages. ZTE and UTE visualized all fibrocartilages in 72% and 92.1% of volunteers, respectively, with significant differences favoring ZTE and UTE over PD-WI (p < 0.0001) and UTE over ZTE (p = 0.027). Inter-rater agreement exceeded 80% except for SCa on ZTE (68%, 95%CI: 53.2–80.1). Abnormal SCa findings in asymptomatic patients were more frequent with UTE (23.7%) and ZTE (34%) than with PD-WI (2%) (p = 0.0045). Conclusions: At 3-Tesla, UTE and ZTE sequences reliably depict the enthesis organ of the Achilles tendon, outperforming PD-WI. However, the high sensitivity of these sequences also presents challenges in interpretation. Full article

The growing demand for accurate and efficient Chest X-Ray (CXR) interpretation has prompted the development of AI-driven systems to alleviate radiologist workload and reduce diagnostic variability. This paper introduces the Intelligent Humanized Radiology Analysis System (IHRAS), a modular framework that automates the end-to-end process of CXR analysis and report generation. IHRAS integrates four core components: (i) deep convolutional neural networks for multi-label classification of 14 thoracic conditions; (ii) Grad-CAM for spatial visualization of pathologies; (iii) SAR-Net for anatomical segmentation; and (iv) a large language model (DeepSeek-R1) guided by the CRISPE prompt engineering framework to generate structured diagnostic reports using SNOMED CT terminology. Evaluated on the NIH ChestX-ray dataset, IHRAS demonstrates consistent diagnostic performance across diverse demographic and clinical subgroups, and produces high-fidelity, clinically relevant radiological reports with strong faithfulness, relevancy, and alignment scores. The system offers a transparent and scalable solution to support radiological workflows while highlighting the importance of interpretability and standardization in clinical Artificial Intelligence applications. Full article

Interpreting diagnostic imaging and identifying clinically relevant features remain challenging tasks, particularly for novice radiologists who often lack structured guidance and expert feedback. To bridge this gap, we propose an Eye-Gaze Guided Multimodal Fusion framework that leverages expert eye-tracking data to enhance learning and decision-making in medical image interpretation. By integrating chest X-ray (CXR) images with expert fixation maps, our approach captures radiologists’ visual attention patterns and highlights regions of interest (ROIs) critical for accurate diagnosis. The fusion model utilizes a shared backbone architecture to jointly process image and gaze modalities, thereby minimizing the impact of noise in fixation data. We validate the system’s interpretability using Gradient-weighted Class Activation Mapping (Grad-CAM) and assess both classification performance and explanation alignment with expert annotations. Comprehensive evaluations, including robustness under gaze noise and expert clinical review, demonstrate the framework’s effectiveness in improving model reliability and interpretability. This work offers a promising pathway toward intelligent, human-centered AI systems that support both diagnostic accuracy and medical training. Full article

Background and Objectives: Acute appendicitis is a common cause of abdominal pain requiring surgery in pediatric patients. Given concerns regarding radiation exposure from computed tomography (CT), ultrasound (US) has become the first-line diagnostic modality. In many emergency and resource-limited settings, non-radiologist physicians often perform these examinations. This study aimed to evaluate the diagnostic accuracy of a non-radiologist-performed ultrasound in detecting acute appendicitis in children. Materials and Methods: We conducted a systematic review and meta-analysis according to the PRISMA guidelines. The literature was searched across PubMed, Ovid MEDLINE, EMBASE, the Cochrane Library, and Google Scholar through June 2024. Studies reporting on the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of non-radiologist-performed ultrasounds in pediatric appendicitis were included. Study quality was assessed using the QUADAS-2 tool, and a bivariate random-effects model was used for statistical analysis. Results: Eight studies, with a total of 1006 pediatric patients, were included. The pooled sensitivity and specificity were 0.87 (95% CI, 0.83–0.90) and 0.93 (95% CI, 0.91–0.95), respectively. The area under the SROC curve was 0.783 (95% CI, 0.708–0.853), suggesting moderate-to-good diagnostic accuracy. Substantial heterogeneity was observed across studies, possibly due to differences in operator training and ultrasound techniques. Conclusions: Non-radiologist-performed ultrasound demonstrates moderate-to-good diagnostic accuracy in identifying pediatric appendicitis. These findings support its implementation in emergency or resource-constrained settings and suggest that incorporating structured ultrasound training for non-radiologists may improve timely diagnosis and optimize clinical decision-making in pediatric emergency care. Full article