Search Results (574)

Background/Objectives: Despite the high complete response (CR) rate to first-line therapy, approximately one-third of patients with advanced-stage Hodgkin lymphoma (HL) eventually relapse. In up to 30–50% of cases, relapses are subclinical, i.e., initially detected only by imaging procedures. However, there is no definitive consensus on the optimal surveillance strategy for high-risk HL patients. Methods: The purpose of this cohort study is to evaluate the long-term outcome of stage II-B/IV HL patients who relapsed under routine imaging surveillance (imaging cohort) compared to those who relapsed under conventional clinical monitoring (standard cohort). Follow-up in the imaging cohort systematically included FDG-PET/CT, ultrasonography, and/or chest X-ray. At relapse, patients were treated with the same approach (salvage therapy and autologous hematopoietic stem cell transplantation [AHSCT]) in both cohorts. Results: A total of 123 high-risk HL patients were assessed at their first relapse: 80 in the imaging cohort and 43 in the standard cohort. The 2-year event-free survival (EFS) was significantly higher in the imaging cohort compared to the standard cohort (70% vs. 37.2%, respectively; p = 0.001). Similarly, the CR rate following salvage treatment was greater in the imaging cohort as compared to the standard cohort (68.8% vs. 41.9%, respectively; p < 0.004). These differences were due to the capability of routine imaging surveillance to detect disease with more limited extension (early onset of clinically silent relapses) as compared to standard clinical monitoring, which was associated with relapsed disease in a more advanced stage. Conclusions: Our findings suggest that routine imaging surveillance in patients with high-risk HL leads to improved EFS detecting relapses, which were characterized by more favorable prognostic factors (low tumor burden), thus enabling the timely administration of salvage therapy. Full article

Background: Pulmonary lobectomy remains the gold standard for early-stage non-small cell lung cancer, with the primary goal of complete tumor removal. Postoperative imaging is critical for evaluating recovery and identifying complications, yet systematic descriptions of radiologic patterns after lobectomy are limited. Methods: We conducted a retrospective analysis of 125 patients who underwent pulmonary lobectomy between 2019 and 2024 at a tertiary thoracic surgery center. Preoperative and postoperative imaging findings were coded and compared using a standardized classification system. Modalities included chest radiography, thoracic CT, ultrasound, PET-CT and MRI. Results: Postoperative imaging demonstrated a clear reduction in pathological findings. Emphysema decreased from 29.6% to 21.6%, pleural effusion from 12.8% to 3.2%, atelectasis/pleural thickening from 15.2% to 8.8%, and ground-glass infiltrates from 12.0% to 8.0%. The proportion of patients without abnormalities increased from 18.5% to 24.8%. Chest radiography (92%) and CT (89.6%) were the most frequently employed modalities. Patients treated with VATS lobectomy showed slightly fewer postoperative abnormalities compared with those undergoing open surgery. Conclusions: Pulmonary lobectomy is associated with measurable radiologic improvement, reflecting favorable structural recovery. Routine imaging follow-up, particularly chest radiography, remains essential for early detection of complications and guiding postoperative care. However, the retrospective single-center design and limited generalizability represent important limitations that should be considered when interpreting these findings. Full article

Producing high-quality segmentation masks for medical images is a fundamental challenge in biomedical image analysis. Recent research has investigated the use of supervised learning with large volumes of labeled data to improve segmentation across medical imaging modalities and unsupervised learning with unlabeled data to segment without detailed annotations. However, a significant hurdle remains in constructing a model that can segment diverse medical images in a zero-shot manner without any annotations. In this work, we introduce the attention diffusion zero-shot unsupervised system (ADZUS), a new method that uses self-attention diffusion models to segment biomedical images without needing any prior labels. This method combines self-attention mechanisms to enable context-aware and detail-sensitive segmentations, with the strengths of the pre-trained diffusion model. The experimental results show that ADZUS outperformed state-of-the-art models on various medical imaging datasets, such as skin lesions, chest X-ray infections, and white blood cell segmentations. The model demonstrated significant improvements by achieving Dice scores ranging from 88.7% to 92.9% and IoU scores from 66.3% to 93.3%. The success of the ADZUS model in zero-shot settings could lower the costs of labeling data and help it adapt to new medical imaging tasks, improving the diagnostic capabilities of AI-based medical imaging technologies. Full article

The medical imaging domain frequently encounters the dual challenges of annotation scarcity and class imbalance. A critical issue lies in effectively extracting information from limited labeled data while mitigating the dominance of head classes. The existing approaches often overlook in-depth modeling of sample relationships in low-dimensional spaces, while rigid or suboptimal dynamic thresholding strategies in pseudo-label generation are susceptible to noisy label interference, leading to cumulative bias amplification during the early training phases. To address these issues, we propose a semi-supervised medical image classification framework combining labeled data-contrastive learning with class-adaptive pseudo-labeling (CLCP-MT), comprising two key components: the semantic discrimination enhancement (SDE) module and the class-adaptive pseudo-label refinement (CAPR) module. The former incorporates supervised contrastive learning on limited labeled data to fully exploit discriminative information in latent structural spaces, thereby significantly amplifying the value of sparse annotations. The latter dynamically calibrates pseudo-label confidence thresholds according to real-time learning progress across different classes, effectively reducing head-class dominance while enhancing tail-class recognition performance. These synergistic modules collectively achieve breakthroughs in both information utilization efficiency and model robustness, demonstrating superior performance in class-imbalanced scenarios. Extensive experiments on the ISIC2018 skin lesion dataset and Chest X-ray14 thoracic disease dataset validate CLCP-MT’s efficacy. With only 20% labeled and 80% unlabeled data, our framework achieves a 10.38% F1-score improvement on ISIC2018 and a 2.64% AUC increase on Chest X-ray14 compared to the baselines, confirming its effectiveness and superiority under annotation-deficient and class-imbalanced conditions. Full article

Early and accurate detection of pneumonia from chest X-ray images is essential for improving treatment and clinical outcomes. Medical imaging datasets often exhibit class imbalance and uncertainty in feature extraction, which complicates conventional classification methods and motivates the use of advanced approaches combining deep learning and fuzzy logic. This study proposes a hybrid approach that combines deep learning architectures (VGG16, EfficientNetV2, MobileNetV2, ResNet50) for feature extraction with fuzzy logic-based classifiers, including Fuzzy C-Means, Fuzzy Decision Tree, Fuzzy KNN, Fuzzy SVM, and ANFIS (Adaptive Neuro-Fuzzy Inference System). Feature selection techniques were also applied to enhance the discriminative power of the extracted features. The best-performing model, ANFIS with MobileNetV2 features and Gaussian membership functions, achieved an overall accuracy of 98.52%, with Normal class precision of 97.07%, recall of 97.48%, and F1-score of 97.27%, and Pneumonia class precision of 99.06%, recall of 98.91%, and F1-score of 98.99%. Among the fuzzy classifiers, Fuzzy SVM and Fuzzy KNN also showed strong performance with accuracy above 96%, while Fuzzy Decision Tree and Fuzzy C-Means achieved moderate results. These findings demonstrate that integrating deep feature extraction with neuro-fuzzy reasoning significantly improves diagnostic accuracy and robustness, providing a reliable tool for clinical decision support. Future research will focus on optimizing model efficiency, interpretability, and real-time applicability. Full article

Alveolar echinococcosis (AE) is a zoonotic disease caused by the larval form of the tapeworm Echinococcus multilocularis, which is considered one of the most dangerous parasites for humans. E. multilocularis infections are most frequently observed in forestry workers, farmers, hunters, berry harvesters, and workers employed in animal shelters. The subject of this study was a four-year follow-up profile of cytokines, including tumor necrosis factor alpha (TNFα), interleukin-1 (IL-1), interleukin-6 (IL-6), interleukin-4 (IL-4), and interleukin-10 (IL-10), in a patient with advanced liver alveolar echinococcosis and non-optimal antiparasitic treatment. Ultrasound, computed tomography (CT) of the abdomen, X-ray, CT of the chest, and magnetic resonance imaging (MRI) of the head were performed during the observation and treatment of the AE patient. After antiparasitic treatment was initiated, decreased activity of the gamma-glutamyl transpeptidase (GGTP), decreased serum concentrations of immunoglobulin E, C-reactive protein (CRP), and the pro-inflammatory cytokines TNFα, IL-1, and IL-6 were observed, as well as slightly increased levels of the anti-inflammatory cytokines (IL-4 and IL-10). Conclusions. During a four-year follow-up in a patient with advanced hepatic alveolar echinococcosis and non-optimal antiparasitic treatment, a decrease in proinflammatory cytokines (TNFα, IL-1β, IL-6) and a slight increase in anti-inflammatory cytokines (IL-4, IL-10) were detected. A better understanding of cytokine regulation in infectious diseases may be important to the development of new therapeutic strategies aimed at antiparasitic treatment. We suggest that broad initiatives (preferably at the local community level) should be implemented to raise awareness of the threat of alveolar echinococcosis and methods for avoiding E. multilocularis infection. Full article

Automated analysis for tumor segmentation and illness classification is hampered by the noise, low contrast, and ambiguity that are common in medical pictures. This work introduces a new 12-step fuzzy-based improvement pipeline that uses fuzzy entropy, fuzzy standard deviation, and histogram spread functions to enhance picture quality in CT, MRI, and X-ray modalities. The pipeline produces three improved versions per dataset, lowering BRISQUE scores from 28.8 to 21.7 (KiTS19), 30.3 to 23.4 (BraTS2020), and 26.8 to 22.1 (Chest X-ray). It is tested on KiTS19 (CT) for kidney tumor segmentation, BraTS2020 (MRI) for brain tumor segmentation, and Chest X-ray Pneumonia for classification. A Concatenated CNN (CCNN) uses the improved datasets to achieve a Dice coefficient of 99.60% (KiTS19, +2.40% over baseline), segmentation accuracy of 0.983 (KiTS19) and 0.981 (BraTS2020) versus 0.959 and 0.943 (CLAHE), and classification accuracy of 0.974 (Chest X-ray) versus 0.917 (CLAHE). A classic CNN is trained on original and CLAHE-filtered datasets. These outcomes demonstrate how well the pipeline works to improve image quality and increase segmentation/classification accuracy, offering a foundation for clinical diagnostics that is both scalable and interpretable. Full article

Background/Objectives: The limited availability of labeled data, particularly in the medical domain, poses a significant challenge for training accurate diagnostic models. While deep learning techniques have demonstrated notable efficacy in image-based tasks, they require large annotated datasets. In data-scarce scenarios—especially involving rare diseases—their performance deteriorates significantly. Meta-learning offers a promising alternative by enabling models to adapt quickly to new tasks using prior knowledge and only a few labeled examples. This study aims to evaluate the effectiveness of representative meta-learning models for thoracic disease classification in chest X-rays. Methods: We conduct a comparative evaluation of four meta-learning models: Prototypical Networks, Relation Networks, MAML, and FoMAML. First, we assess five backbone architectures (ConvNeXt, DenseNet-121, ResNet-50, MobileNetV2, and ViT) using a Prototypical Network. The best-performing backbone is then used across all meta-learning models for fair comparison. Experiments are performed on the ChestX-ray14 dataset under a 2-way setting with multiple k-shot configurations. Results: Prototypical Networks combined with DenseNet-121 achieved the best performance, with a recall of 68.1%, an F1-score of 67.4%, and a precision of 0.693 in the 2-way, 10-shot configuration. In a disease-specific analysis, Hernia obtains the best classification results. Furthermore, Prototypical and Relation Networks demonstrate significantly higher computational efficiency, requiring fewer FLOPs and shorter execution times than MAML and FoMAML. Conclusions: Prototype-based meta-learning, particularly with DenseNet-121, proves to be a robust and computationally efficient approach for few-shot chest X-ray disease classification. These findings highlight its potential for real-world clinical applications, especially in scenarios with limited annotated medical data. Full article

Background and Clinical Significance: Mycotic aortic aneurysm is a rare but life-threatening vascular condition characterized by infection-induced dilation or pseudoaneurysm formation in the aorta. The condition carries a high risk of rupture and mortality, especially in individuals with underlying cardiovascular disease, who have undergone recent vascular procedures, or with immunocompromising comorbidities such as diabetes. Its diagnosis is challenging due to its non-specific symptoms and often requires a high index of suspicion, especially in patients presenting with persistent fever and negative initial imaging. Early recognition and intervention are critical, as delayed treatment significantly worsens outcomes. Case Presentation: A 68-year-old male with a history of coronary artery disease, recent stent placement, and hypertension presented with two days of fever, chills, rigors, and a mild nonproductive cough. The laboratory findings were only significant for leukocytosis. The initial chest X-ray and non-contrast CT scans were unremarkable. He was admitted for presumed pneumonia and started on intravenous antibiotics. Persistent fever prompted further investigation with contrast-enhanced CT, which revealed a distal-aortic-arch pseudoaneurysm and mild mediastinal stranding. Blood cultures grew methicillin-sensitive Staphylococcus aureus (MSSA). Transthoracic echocardiogram was negative for endocarditis. The patient was transferred to a tertiary center, where repeat imaging confirmed a 1.5 cm pseudoaneurysm and a 4 mm penetrating atherosclerotic ulcer. After multidisciplinary assessment, he underwent thoracic endovascular aortic repair (TEVAR) and completed four weeks of intravenous cefazolin. Follow-up imaging showed successful aneurysm repair with no complications. Conclusions: Thoracic mycotic aneurysm is a rapidly fatal entity despite intervention. High clinical suspicion is necessary given its non-specific presentation. It is diagnosed most practically using CTA. In addition to antibiotics, TEVAR is gaining traction as a feasible and a safe alternative to open surgical repair (OSR). Full article

Background/Objectives: Pleural effusion is a common pulmonary condition that, if left untreated, may lead to respiratory distress and severe complications. Chest X-ray (CXR) imaging is routinely used by physicians to identify signs of pleural effusion. However, manually examining large volumes of CXR images on a daily basis can require substantial time and effort. To address this issue, this study proposes an automated pleural effusion detection system for CXR images. Methods: The proposed system integrates image cropping, image enhancement, and the EfficientNet-B0 deep learning model to assist in detecting pleural effusion, a task that is often challenging due to subtle symptom presentation. Image cropping was applied to extract the region from the heart to the costophrenic angle as the target area. Subsequently, image enhancement techniques were employed to emphasize pleural effusion features, thereby improving the model’s learning efficiency. Finally, EfficientNet-B0 was used to train and classify pleural effusion cases based on processed images. Results: In the experimental results, the proposed image enhancement approach improved the model’s recognition accuracy by approximately 4.33% compared with the non-enhanced method, confirming that enhancement effectively supports subsequent model learning. Ultimately, the proposed system achieved an accuracy of 93.27%, representing a substantial improvement of 21.30% over the 77.00% reported in previous studies, highlighting its significant advancement in pleural effusion detection. Conclusions: This system can serve as an assistive diagnostic tool for physicians, providing standardized detection results, reducing the workload associated with manual interpretation, and improving the overall efficiency of pulmonary care. Full article

Chest X-ray (CXR) imaging is essential for diagnosing thoracic diseases, and computer-aided diagnosis (CAD) systems have made substantial progress in automating the interpretation of CXR images. However, some existing methods often overemphasize local features while neglecting global context, limiting their ability to capture the broader pathological landscape. Moreover, most methods fail to model label correlations, leading to insufficient utilization of prior knowledge. To address these limitations, we propose a novel multi-label CXR image classification framework, termed the Label Masking-enhanced Residual Attention Network (LMeRAN). Specifically, LMeRAN introduces an original label-specific residual attention to capture disease-relevant information effectively. By integrating multi-head self-attention with average pooling, the model dynamically assigns higher weights to critical lesion areas while retaining global contextual features. In addition, LMeRAN employs a label mask training strategy, enabling the model to learn complex label dependencies from partially available label information. Experiments conducted on the large-scale public dataset ChestX-ray14 demonstrate that LMeRAN achieves the highest mean AUC value of 0.825, resulting in an increase of 3.1% to 8.0% over several advanced baselines. To enhance interpretability, we also visualize the lesion regions relied upon by the model for classification, providing clearer insights into the model’s decision-making process. Full article

Background: Mass gatherings like the Hajj pilgrimage present unique challenges for radiological services, with high patient volumes and increased respiratory disease risks necessitating reliable chest X-ray interpretation. Objectives: The objective of this study is to assess the diagnostic quality, abnormality rates, and peer-review concordance of chest X-rays in patients transferred during the Hajj seasons of 1444–1445 H/2023–2024 G, with an additional focus on gender-based differences in radiological interpretation. Methods and Materials: A cross-sectional analysis of 2093 chest X-rays from Hajj healthcare facilities was conducted. Two blinded radiologists independently reinterpreted images using standardized criteria. Data included demographic variables, radiographic findings (quality, opacities, nodules, cardiomegaly, effusions), and tuberculosis likelihood. Results: Among interpretable films (89.7% acceptable quality), 69.2% showed abnormalities, primarily opacities (56.4%) and cardiomegaly (27.0%). Tuberculosis was considered probable by radiographic appearance in 21.0% of cases. Peer review demonstrated 94.2% overall concordance. Regression analysis identified the presence of any abnormality (OR = 10.67, p < 0.001) and female gender (OR = 2.97, p = 0.003) as significant independent predictors of interpretive discordance. A trend towards higher discordance was noted for pulmonary nodules, though it was not statistically significant (9.4% vs. 5.6%, p = 0.062). Conclusions: While chest X-rays proved reliable for Hajj screening, gender disparities in interpretation and challenges in certain assessments, such as nodule evaluation, highlight opportunities to refine radiological protocols in mass gatherings. Full article

Pneumonia remains a major global health concern, leading to significant mortality and morbidity. The identification of pneumonia by chest X-rays can be difficult due to its similarity to other lung disorders. In this paper, Natural Gradiant Boost (NGBoost) classifier is employed on deep features obtained from ResNet50 model to classify chest X-ray images as normal or pneumonia-affected. NGBoost classifier, a probabilistic machine learning model is used in this study to evaluate the discriminative power of handcrafted features like haar, shape and texture and deep features obtained from convolution neural network models like ResNet50, DenseNet121 and VGG16. The dataset used in this study is obtained from the pneumonia RSNA challenge, which consists of 26,684 chest X-ray images. The experimental results show that NGBoost classifier obtained an accuracy of 0.98 using deep features extracted from ResNet50 model. From the analysis, it is found that deep features play an important role in pneumonia chest X-ray classification. Full article

Intra-fractional respiratory management represents one of the greatest challenges of modern cancer radiotherapy (RT), as significant breathing-induced lesion motion might affect target coverage and organs at risk (OARs) sparing, jeopardizing oncological and toxicity outcomes. The detrimental effects on dosage of uncompensated organ motion are exacerbated in RT with charged particles (e.g., protons and carbon ions), due to their higher ballistic selectivity. The simplest strategies to counteract this phenomenon are the use of larger treatment margins and reductions in or control of respiration (e.g., by means of compression belts, breath hold). Gating and tracking, which synchronize beam delivery with the respiratory signal, also represent widely adopted solutions. When tracking the tumor itself or surrogates, invasive procedures (e.g., marker implantation), an unnecessary imaging dose (e.g., in X-ray-based fluoroscopy), or expensive equipment (e.g., magnetic resonance imaging, MRI) is usually required. When chest and abdomen excursions are measured to infer internal tumor displacement, the additional devices needed to perform this task, such as pressure sensors or surface cameras, present inherent limitations that can impair the procedure itself. In this context, radars have intrigued the radiation oncology community, being inexpensive, non-invasive, contactless, and insensitive to obstacles. Even if real-world clinical implementation is still lagging behind, there is a growing body of research unraveling the potential of these devices in this field. The purpose of this narrative review is to provide an overview of the studies that have delved into the potential of radar-based technologies for motion-adaptive photon and particle RT applications. Full article

Background/Objectives: Recent state-of-the-art advances in deep learning have significantly improved diagnostic accuracy in medical imaging, particularly in chest radiograph (CXR) analysis. Motivated by these developments, a comprehensive comparison was conducted to investigate how architectural choices affect performance of 14 deep learning models across Convolutional Neural Networks (CNNs), Transformer-based models, and Mamba-based State Space Models. Methods: These models were trained and evaluated under identical conditions on the NIH ChestX-ray14 dataset, a large-scale and widely used benchmark comprising 112,120 labeled CXR images with 14 thoracic disease categories. Results: It was found that recent hybrid architectures—particularly ConvFormer, CaFormer, and EfficientNet—deliver superior performance in both common and rare pathologies. ConvFormer achieved the highest mean AUROC of 0.841 when averaged across all 14 thoracic disease classes, closely followed by EfficientNet and CaFormer. Notably, AUROC scores of 0.94 for hernia, 0.91 for cardiomegaly, and 0.88 for edema and effusion were achieved by the proposed models, surpassing previously reported benchmarks. Conclusions: These results not only highlight the continued strength of CNNs but also demonstrate the growing potential of Transformer-based architectures in medical image analysis. This work contributes to the literature by providing a unified, state-of-the-art benchmarking of diverse deep learning models, offering valuable guidance for researchers and practitioners developing clinically robust AI systems for radiology. Full article