Frontiers in radiology最新文献

Background: Our work aims to develop and evaluate a combined model that integrates clinical features, conventional computed tomography angiography (CTA) features, and radiomics features of perivascular adipose tissue (PVAT) to identify asymptomatic carotid stenosis (ACS) patients at high risk for short-term stroke.

Methods: We enrolled 582 ACS patients confirmed by CTA from three medical centers and divided them into a training set (n = 188), an internal validation set (n = 85), and two independent external validation sets (set 1, n = 157; set 2, n = 152). Radiomics features of PVAT were extracted from CTA images, and dimensionality reduction was performed to identify predictive features. Five machine learning classifiers were employed to construct radiomics models, and the model with the highest AUC was selected to generate the radiomics score (Rad-score). Clinical factors associated with stroke were determined using univariate and multivariate logistic regression analyses to construct a clinical model. A combined model integrating clinical factors and the Rad-score was subsequently developed, and a nomogram was created to provide a visual tool for stroke risk prediction. We assessed model performance comprehensively through calibration curves, discrimination analysis, reclassification, and clinical application.

Results: A total of nine optimal radiomics features were ultimately selected from the CTA images. Across the four datasets, the AUC values of the five classifier models ranged from 0.643 to 0.869, 0.716 to 0.826, 0.651 to 0.858, and 0.638 to 0.848, respectively, with the XGBoost model demonstrating the best performance. The combined model, incorporating hypertension, soft plaque, and the Rad-score as variables, achieved AUCs of 0.911, 0.868, 0.882, and 0.871, respectively, across the four datasets.

Conclusions: A combined model based on PVAT imaging features around carotid plaques can effectively predict the short-term stroke risk in ACS patients. This model may be expected to provide an important auxiliary tool for clinical prognosis assessment and treatment decisions, with potential clinical application value.

Introduction: The reports from the Health Organizations indicates a sudden growth in neurocognitive disorders among middle-aged and elderly individuals. The accurate detection of Alzheimer's disease (AD) is essential for improving patient care, specifically during the early stages, where timely risk identification enables individuals to adopt preventive measures before irreversible brain damage occurs. Though, several studies have discovered about computerized approaches for AD, many existing techniques remain limited by inherent methodological constraints and insufficient clinical scrutiny. The current systems struggle to reliably predict the disorder in its initial stages. To reduce the need for frequent clinical visit and lower diagnostic costs, the machine learning and deep learning have emerged as powerful tools for AD detection.

Methods: This work reviews several research relevant on studies on AD and highlights how these computational techniques can support researchers in achieving more efficient and accurate early-stage detection. The Deep Convolutional Neural Network (Deep-CNN) with Attention mechanism is proposed to augment the spatial attention module and multi-class classification of Alzheimer disease stages. The model has trained and evaluated on the OASIS dataset using subject-level which satisfy statistical-validation and standard preprocessing.

Results: The proposed Deep-CNN and attention model focuses the model capacity on diagnostically relevant regions. The proposed model achieved an accuracy of 97%, which is higher than existing methods like SVM with kernels (90.5%), SVM Gaussian radial basis kernel (85%), and traditional CNN (93.5%).

Discussion: The visualizations of attention mechanism are used to increase the interpretability and demonstrate the attention maps which are align with known AD biomarkers. These results indicates that the attention-guided deep models can both improve multi-class MRI classification accuracy and provide clinically useful regional explanations.

Verrucous Venous Malformations (VVMs) are a rare subtype of Congenital Vascular Malformations (CVMs) characterised by a hyperkeratotic, verrucous surface. We present the case of a ten-year-old male with a VVM localised to the right knee, which presented as a gradually enlarging, asymptomatic lesion since birth. A comprehensive, multi-modality diagnostic workup was performed, including thorough clinical evaluation, dermoscopy, radiologic imaging (Plain radiograph, colour Doppler ultrasonography and magnetic resonance imaging) and histopathological analysis with hematoxylin and eosin staining, along with immunohistochemical staining for CD-34. The lesion exhibited characteristic features consistent with VVM. The patient was managed by percutaneous sclerotherapy to reduce lesion size. This case highlights the importance of a multidisciplinary strategy in the diagnosis and management of VVMs to improve clinical outcomes.

Spontaneous splenic rupture (SSR) is a rare but potentially life-threatening condition, most commonly associated with underlying infectious, haematological, vascular, or neoplastic processes. Clinical presentation is often non-specific, which may lead to delayed diagnosis. Imaging, particularly contrast-enhanced computed tomography (CECT), plays a pivotal role in confirming splenic injury, identifying predisposing lesions, and guiding management. We present the case of a woman aged in her seventies with chronic atrial fibrillation on antiplatelet therapy who developed spontaneous splenic rupture secondary to an occult splenic hamartoma. Ultrasound demonstrated heterogeneous perisplenic fluid and altered splenic echotexture. CT showed a 3.5 cm laceration, moderate haemoperitoneum, and a solid lesion with delayed enhancement and no active bleeding. Follow-up CT revealed progressive organisation of haemoperitoneum and stable lesion morphology. The patient was initially managed non-operatively due to haemodynamic stability, but elective splenectomy was performed given the presence of a structural lesion and the need for chronic anticoagulation. The purpose of this article is to illustrate the diagnostic and management principles of SSR through a representative clinical case and to provide an updated review of imaging strategies, including emerging applications of radiomics and artificial intelligence (AI).

Introduction: Radiomics aims to develop image-based biomarkers by combining quantitative analysis of medical images with artificial intelligence (AI) through a robust, reproducible pipeline. Scientific societies, task groups, and consortia have published several guidelines to help researchers design robust radiomics studies. This review summarizes existing guidelines, recommendations, and regulations for designing radiomics studies that can lead to clinically adoptable biomarkers.

Methods: Relevant articles were identified through a PubMed systematic review using "radiomics" and "guideline" as keywords. Of 314 retrieved papers, after screening 99 articles were deemed relevant for extracting recommendations on developing image-based biomarkers. Additional guidelines were searched by the authors.

Results: We can synthesize the systematic review in the following high consensus recommendations divided into five major areas: a) Study Design: Carefully define the study rationale, objectives, and outcomes, ensuring the dataset is of adequate size and quality; b) Data Workflow: Use standardized protocols for image acquisition, reconstruction, preprocessing, and feature extraction-following IBSI guidelines where applicable; c) Model Development and Validation: Follow best practices for model development, including prevention of data leakage, dimensionality reduction, strategies to enhance model interpretability, and establish biological plausibility; d) Transparency and Reproducibility: Publish results with sufficient methodological details to ensure rigor and generalizability and promote open science by sharing codes and data; e) Quality and compliance: Evaluate study compliance with relevant guidelines and regulations using appropriate quality metrics.

Conclusion: Radiomics promises to offer clinically useful imaging biomarkers and can represent a significant step in personalized medicine. In the present systematic review we identified five key guidelines and regulations developed in recent years, specifically for radiomics or AI, that can guide the research community in designing and conducting radiomic studies that result in an imaging biomarker suitable for clinical practice.

This review summarizes the current advances, applications, and research prospects of computer vision in advancing medical imaging. Computer vision in healthcare has revolutionized medical practice by increasing diagnostic accuracy, improving patient care, and increasing operational efficiency. Likewise, deep learning algorithms have advanced medical image analysis, significantly improved healthcare outcomes and transforming diagnostic processes. Specifically, convolutional neural networks are crucial for modern medical image segmentation, enabling the accurate, efficient analysis of various imaging modalities and helping enhance computer-aided diagnosis and treatment planning. Computer vision algorithms have demonstrated remarkable capabilities in detecting various diseases. Artificial intelligence (AI) systems can identify lung nodules in chest computed tomography scans at a sensitivity comparable to that of experienced radiologists. Computer vision can analyze brain scans to detect problems such as aneurysms and tumors or areas affected by diseases such as Alzheimer's. In summary, computer vision in medical imaging is significantly improving diagnostic accuracy, efficiency, and patient outcomes across a range of medical specialties.

Acute myocarditis is an inflammatory condition of the myocardium, often triggered by viral infections, autoimmune diseases, or toxins. It can lead to arrhythmias, heart failure, and sudden cardiac death. Early and accurate diagnosis is crucial for timely management and preventing complications. It poses a significant diagnostic challenge in emergency departments (EDs) due to nonspecific symptoms, overlapping features with conditions like acute coronary syndrome, and limitations of conventional diagnostics. Cardiac magnetic resonance imaging (CMR) is the gold standard for noninvasive diagnosis, using the 2018 Modified Lake Louise Criteria (mLLC). However, high-field CMR (1.5-3T) faces barriers in EDs, such as longer scan times, higher cost, lack of accessibility, and contraindications in patients with implantable devices, severe kidney disease, or hemodynamic instability. Low-field MRI (<1.5T) offers advantages in portability, safety, and cost while reducing susceptibility artifacts. Recent advances in AI-driven image reconstruction (e.g., LoHiResGAN, U-net) address low signal-to-noise ratios, enabling cine imaging, strain analysis, and parametric mapping at 0.55T. Studies show that low-field CMR can detect subclinical myocarditis and predict outcomes, with ECV measurements at 0.55T strongly correlating with 1.5T (r = 0.91), demonstrating comparable reliability. By integrating low-field CMR into ED protocols, clinicians can improve early detection of occult myocarditis, guide risk stratification, and reduce long-term morbidity and healthcare costs. Standardization of imaging workflows and AI-enhanced protocols will further bridge diagnostic gaps, particularly in resource-limited settings. This review highlights low-field CMR's potential to redefine acute myocarditis management, balancing diagnostic precision with practicality in emergency care.

Low-grade endometrial stromal sarcoma (LGESS) is a rare uterine malignancy; metastasis to the inferior vena cava (IVC) and right atrium is exceptionally rare and presents significant diagnostic and therapeutic challenges. We report the case of a 37-year-old woman presenting with progressive abdominal mass enlargement, palpitations, and dyspnea. She had undergone a hysteroscopic resection for presumed uterine myoma one year prior, which was subsequently re-evaluated as LGESS. Multimodal imaging comprising ¹⁸F-FDG PET/CT, MRI, CT, and echocardiography was implemented for systemic staging and hemodynamic assessment, then revealed a solid uterine mass involving the adnexa (FIGO Stage IVB) and identified hypermetabolic tumor thrombi extending from the IVC into the right atrium and pulmonary arteries. A coordinated one-stage radical resection was performed, involving total hysterectomy and removal of intracardiac thrombi under cardiopulmonary bypass. Postoperative pathology and immunohistochemistry confirmed LGESS (CD10+, ER+, PR+) with extensive lymphovascular invasion. The patient recovered uneventfully with no residual disease on follow-up and commenced adjuvant letrozole therapy. This case highlights the necessity of multimodal imaging for accurate staging of complex vascular involvement and demonstrates that aggressive one-stage surgical management is a viable strategy to achieve locoregional control and favorable early outcomes for advanced LGESS with cardiac metastasis.

This paper introduces an Ultra-Lightweight Uncertainty-Aware Ensemble (UALE) model for large-scale multi-class medical MRI diagnosis, evaluated on the 2024 Benchmark Diagnostic MRI and Medical Imaging Dataset containing 40 classes and 33,616 images. The model integrates five specialized micro-expert networks, each designed to capture distinct MRI features, and combines them using a confidence-weighted ensemble mechanism enhanced with variance-based uncertainty quantification for robust, reliable predictions. With only 0.05M parameters and 0.18 GFLOPs, UALE achieves high efficiency and competitive performance among ultra-lightweight models with an accuracy of 69.1% and an F1 score of 68.3%. Besides lightweight models, the paper offers an extensive analysis and performance comparison with fifteen state-of-the-art models, discusses various datasets, elaborates on uncertainty estimates pertaining to the clinical trustworthiness of the models and possible clinical deployment, and highlights trade-offs and avenues for future work in economically constrained settings. The extreme compactness and reliability of the UALE affords it unique utility in scalable medical diagnostics suitable for low-resource clinical settings and portable imaging devices, such as rural hospitals.

Objective: This study aims to evaluate the diagnostic performance of diffusion-weighted imaging (DWI) with a fractional order calculus (FROC) model for differentiating breast lesions and to explore the associations between FROC/apparent diffusion coefficient (ADC)-derived diffusion metrics and prognostic biomarkers and molecular subtypes in breast cancer.

Methods: This retrospective study included 147 patients with 159 histopathology-confirmed lesions who underwent multi-b DWI using simultaneous multi-slice (SMS) readout-segmented echo-planar imaging (rs-EPI) at 3.0 T. Whole-lesion histograms were computed for mono-exponential ADC and FROC parameters (D, β, μ). The Mann-Whitney U test was used to compare the histogram metrics of each diffusion parameter between the benign and malignant groups and between groups with different prognostic biomarkers and molecular subtypes. The Kruskal-Wallis test was used to compare the histogram metrics of each DWI-derived parameter among the different molecular subtypes. The Spearman rank correlation analysis was employed to characterize correlations between diffusion parameters and prognostic biomarkers. The diagnostic performance of each DWI-derived parameter in differentiating breast lesions was assessed using receiver operating characteristic (ROC) analysis.

Results: Interobserver reproducibility was excellent (intra-class correlation coefficient 0.827-0.928). Central tendency histogram metrics (10th, 90th percentiles, mean, median) of ADC and FROC parameters were higher in benign than malignant lesions, whereas skewness (all models) and entropy/kurtosis (ADC, D, μ) were lower in benign lesions (all p < 0.05, except β-skewness). The histogram metrics of ADC-median, D_FROC-mean, and D_FROC-median showed similar diagnostic performance. The values of ADC-mean, D_FROC-10%, D_FROC-mean, D_FROC-median, β_FROC-10%, β_FROC-mean, and β_FROC-median were significantly lower in the estrogen receptor (ER)-positive group compared with those in the ER-negative group. The tumors with progesterone receptor (PR)-negative status showed significantly higher β_FROC-10%, β_FROC-mean, and β_FROC-median values than those of tumors with PR-positive status. The values of D_FROC-skewness, β_FROC-10%, and β_FROC-mean exhibited significant differences in differentiating the triple-negative and luminal subtypes.

Conclusions: FROC-based histogram analysis yields diagnostic performance comparable to ADC for benign vs. malignant classification, while providing richer associations with ER/PR status, proliferation, and nodal involvement, reflecting microstructural heterogeneity not captured by mono-exponential diffusion.