Frontiers in radiology最新文献

Background: Aortic stenosis (AS) is diagnosed by echocardiography, the current gold standard, but examinations are often performed only after symptoms emerge, highlighting the need for earlier detection. Recently, artificial intelligence (AI)-based screening using non-invasive and widely available modalities such as electrocardiography (ECG) and chest x-ray(CXR) has gained increasing attention for valvular heart disease. However, single-modality approaches have inherent limitations, and in clinical practice, multimodality assessment is common. In this study, we developed a multimodal AI model integrating ECG and CXR within a cooperative learning framework to evaluate its utility for earlier detection of AS.

Methods: We retrospectively analyzed 23,886 patient records from 7,483 patients who underwent ECG, CXR, and echocardiography. A multimodal model was developed by combining a 1D ResNet50-Transformer architecture for ECG data with an EfficientNet-based architecture for CXR. Cooperative learning was implemented using a loss function that allowed the ECG and CXR models to refine each other's predictions. We split the dataset into training, validation, and test sets, and performed 1,000 bootstrap iterations to assess model stability. AS was defined echocardiographically as peak velocity ≥2.5 m/s, mean pressure gradient ≥20 mmHg, or aortic valve area ≤1.5 cm².

Results: Among 7,483 patients, 608 (8.1%) were diagnosed with AS. The multimodal model achieved a test AUROC of 0.812 (95% CI: 0.792-0.832), outperforming the ECG model (0.775, 95% CI: 0.753-0.796) and the CXR model (0.755, 95% CI: 0.732-0.777). Visualization techniques (Grad-CAM, Transformer attention) highlighted distinct yet complementary features in AS patients.

Conclusions: The multimodal AI model via cooperative learning outperformed single-modality methods in AS detection and may aid earlier diagnosis and reduce clinical burden.

[This corrects the article DOI: 10.3389/fradi.2025.1509377.].

Mucormycosis is a serious fungal infection affecting immunocompromised individuals, caused by fungi from the Mucorales order, particularly Rhizopus species. It primarily spreads through inhalation of spores, with diabetes, cancers, organ transplants, immunosuppressive drugs, and COVID-19 being major risk factors. The infection manifests in various forms such as encephalic, cutaneous, gastrointestinal, pulmonary, and rhino cerebral, often leading to tissue necrosis and blood vessel invasion. Imaging diagnosis is aided by CT and MRI scans, while 99m Tc MDP bone scintigraphy has found to be a more accurate imaging tool to look for bone remodelling and erosive changes associated with invasive fungal sinusitis including mucormycosis. Treatment involves prompt surgical debridement and addressing the underlying immune deficiency. Here we present a series of cases where 99m Tc MDP bone scintigraphy played a key role in management of mucormycosis of the head. In conclusion, 99mTc MDP scintigraphy is a promising tool for evaluation, guiding diagnosis and management of mucormycosis.

Background: Tunneled cuffed catheter (TCC) remains a crucial vascular access option for patients undergoing hemodialysis, particularly in those who are not candidates for arteriovenous fistulas or grafts. However, placement carries immediate and delayed complications.

Objective: This narrative review aims to provide a comprehensive overview of the complications encountered during and after the placement of a TCC for hemodialysis, highlighting current evidence, risk factors, prevention strategies, and management approaches.

Methods: A critical selection of relevant literature was performed through PubMed and Scopus databases, focusing on articles published in the last two decades. Particular attention was given to studies reporting on mechanical, infectious, thrombotic, and late-onset complications, as well as technical factors influencing outcomes.

Results: Complications of TCCs can be classified as immediate (e.g., arterial puncture, pneumothorax, bleeding), early (e.g., catheter malposition, exit-site infections), and late (e.g., central venous stenosis, catheter-related bloodstream infections, thrombosis). Patient- and procedure-related factors increase risk. Ultrasound and fluoroscopy, strict sterility, and timely management reduce complications rates.

Conclusion: TCCs are indispensable in selected patients, but understanding their complications is key to patient safety and outcomes. Optimal outcomes depend on accurate patient selection, operator expertise, and standardized post-placement care.

Purpose: This study aimed to assess the feasibility and accuracy of fiducial marker placement using US-CT/MRI fusion imaging guidance in poorly conspicuous liver tumors prior to percutaneous thermal ablation (PTA).

Method: From January 2016 to February 2018, 30 consecutive patients with 38 liver lesions that were poorly or not visible on conventional ultrasound underwent fiducial marker placement under real-time US-CT/MRI fusion imaging before the PTA procedure. Marker position was confirmed via CT or MRI immediately after placement. The shortest distance between the marker and the edge of the target lesion, the lesion size, and the depth were measured. The fiducial marker placement was considered successful if the marker was within, in contact or ≤5 mm distance from the lesion; a distance >5 mm was considered a failure.

Results: Of the 38 lesions, 28 (74%) were undetectable using ultrasound alone, while 10 (26%) were not confidently identified. After fusion, 26 lesions (68%) showed enhanced visibility, while 12 (32%) remained undetectable. Overall, the mean distance between the fiducial marker and the lesion's edge was 4 mm (range: 0-45 mm). Successful placement was achieved in 30 lesions (79%): 27, inside or in contact, and 3, at a <5 mm distance from the target lesion. Placement was unsuccessful in eight lesions (21%). No procedure-related complications occurred.

Conclusions: The present work suggests that pre-PTA placement of a fiducial marker in poorly visible tumors using real-time US-CT/MRI fusion imaging is accurate, potentially enhancing the effectiveness of subsequent PTA.

Introduction: Vietnam still faces a high burden of infectious diseases compared with developed countries, and improving its health and sanitation environment is essential for addressing both infectious and non-communicable diseases. Chest radiography is key for early detection of cardiopulmonary diseases. Artificial Intelligence (AI) research on detecting cardiopulmonary diseases from chest radiographs has advanced; however, no AI development studies have used Vietnamese data, despite its high burden of both disease types, for early detection. Therefore, we aimed to develop an AI model to classify normal and abnormal images using a Vietnamese chest radiograph dataset.

Methods: We retrospectively analyzed 12,827 normal and 4,644 abnormal cases from two Vietnamese institutions. Features were derived from principal component analysis and extracted using Vision Transformer and EfficientnetV2. We performed binary classification of normal and abnormal images using Light Gradient Boosting Machine with 5-fold cross-validation.

Results: The model achieved an F1-score of 0.668, sensitivity of 0.596, specificity of 0.931, accuracy of 0.842, and AUC of 0.897. Subgroup evaluation revealed high accuracy in both infectious and non-communicable cases, as well as in urgent cases.

Conclusion: We developed an AI system that classifies normal and abnormal chest radiographs with high clinical accuracy using Vietnamese data.

Erectile dysfunction (ED) is a worldwide health concern and clinical condition for men, leading to high medical costs and imposing significant emotional and psychological burdens on sufferers annually. ED is associated with multiple causes, including psychological factors and organic issues such as arterial insufficiency and venous leakage. Endovascular treatments have emerged as promising options for managing ED, offering minimally invasive procedures that can improve blood flow to the penis and restore erectile function. Different endovascular interventional approaches have been implemented with varying success rates and therapeutic impacts, and efforts continue to optimize these methods (both arterial and venous) for maximum effectiveness and minimal invasiveness. This narrative review aims to provide an overview of endovascular treatments for arterial and venous types of ED, discussing their mechanisms of action, efficacy, safety, and future directions.

Fibrolipomatous hamartoma is a rare benign overgrowth of tissue consisting of intermixed adipose and fibrous connective tissue within the epineurium. However, involvement of the sciatic nerve is exceptionally rare. We present the case of a 46-year-old female who exhibited a progressively enlarging mass in her right posterior thigh, accompanied by sciatica and gluteal pain. Clinical assessment and MRI revealed a large lesion along the sciatic nerve with characteristic features of fibrolipomatous hamartoma. MRI findings demonstrated characteristic features, including isointense (to fat) on T1-weighted images and hyperintense with fat suppression on short tau inversion recovery sequences, indicating a sciatic nerve fibrolipomatous hamartoma. The diagnosis was histopathologically confirmed following surgical excision. This case highlights the critical role of identifying specific MRI features of this rare entity to avoid unnecessary invasive interventional procedures. An accurate MRI-based diagnosis can significantly impact clinical decisions and improve patient care.

Objective: In this study, the accuracy of deep learning-based models developed for synthetic CT (sCT) generation from conventional Cone Beam Computed Tomography (CBCT) images of prostate cancer patients was evaluated. The clinical applicability of these sCTs in treatment planning and their potential to support adaptive radiotherapy decision-making were also investigated.

Methods: A total of 50 CBCT-CT mappings were obtained for each of 10 retrospectively selected prostate cancer patients, including one planning CT (pCT) and five CBCT scans taken on different days during the treatment process. All images were preprocessed, anatomically matched and used as input to the U-Net and ResU-Net models trained with PyTorch after z-score normalisation. The sCT outputs obtained from model outputs were quantitatively compared with the pCT with metrics such as SSIM, PSNR, MAE, and HU difference distribution.

Results: Both models produced sCT images with higher similarity to pCT compared to CBCT images. The mean SSIM value was 0.763 ± 0.040 for CBCT-CT matches, 0.840 ± 0.026 with U-Net and 0.851 ± 0.026 with ResU-Net, with a significant increase in both models (p < 0.05). PSNR values were 21.55 ± 1.38 dB for CBCT, 24.74 ± 1.83 dB for U-Net, and 25.24 ± 1.61 dB for ResU-Net. ResU-Net provided a statistically significant higher PSNR value compared to U-Net (p < 0.05). In terms of MAE, while the mean error in CBCT-CT matches was 75.2 ± 18.7 HU, the U-Net model reduced this value to 65.3 ± 14.8 HU and ResU-Net to 61.8 ± 13.7 HU (p < 0.05).

Conclusion: Deep learning models trained with simple architectures such as U-Net and ResU-Net provide effective and feasible solutions for the generation of clinically relevant sCT from CBCT images, supporting accurate dose calculation and facilitating adaptive radiotherapy workflows in prostate cancer management.