Search Results (957)

Background/Objectives: Early diagnosis of Parkinson’s Disease (PD) is essential for initiating interventions that may slow its progression and enhance patient quality of life. Gait analysis provides a non-invasive means of capturing subtle motor disturbances, enabling the prediction of both disease presence and severity. This study evaluates and contrasts Bayesian-optimized convolutional neural network (CNN) and long short-term memory (LSTM) models applied directly to Vertical Ground Reaction Force (VGRF) signals for Parkinson’s disease detection and staging. Methods: VGRF recordings were segmented into fixed-length windows of 5, 10, 15, 20, and 25 s. Each segment was normalized and supplied as input to CNN and LSTM network. Hyperparameters for both architectures were optimized via Bayesian optimization using five-fold cross-validation. Results: The Bayesian-optimized LSTM achieved a peak binary classification accuracy of 99.42% with an AUC of 1.000 for PD versus control at the 10-s window, and 98.24% accuracy with an AUC of 0.999 for Hoehn–Yahr (HY) staging at the 5-s window. The CNN model reached up to 98.46% accuracy (AUC = 0.998) for binary classification and 96.62% accuracy (AUC = 0.998) for multi-class severity assessment. Conclusions: Bayesian-optimized CNN and LSTM models trained on VGRF data both achieved high accuracy in Parkinson’s disease detection and staging, with the LSTM exhibiting a slight edge in capturing temporal patterns while the CNN delivered comparable performance with reduced computational demands. These results underscore the promise of end-to-end deep learning for non-invasive, gait-based assessment in Parkinson’s disease. Full article

The electrocardiogram (ECG), which records variations in surface electrical potential over time, has been widely used in the diagnosis of cardiovascular diseases. In recent years, the artificial intelligence (AI) + ECG paradigm has attracted considerable interest, but the two intrinsic characteristics of the ECG, namely, inter-lead correlations and multi-label classification, are often overlooked. Given that this oversight may constrain the full potential of AI models to enhance diagnostic performance, this study focuses on investigating methods for fusing information from a 12-lead ECG. A series of comprehensive experiments was conducted to evaluate the performance of various lead configurations, that is, 1-, 3-, 6-, 9-, and 12-lead combinations, with different fusion strategies. Innovatively integrating medical theory, we propose a novel five-lead-grouping strategy and develop a neural network architecture named Lead-5-Group Net (L5G-Net). After ranking the 12 leads with the AUC, we found that the aVR, V5, and V6 leads are particularly informative for single-lead ECG diagnosis. Furthermore, in multi-lead ECG classification, adopting an orthogonal lead-selection strategy which is based on the hypothesis of spatial interdependence among ECG leads was shown to enhance performance by ensuring that the information provided by each lead is complementary. Finally, the proposed L5G-Net demonstrates outstanding performance, achieving a macro-AUC of 0.9357 on the PTB-XL multi-label dataset without the use of data augmentation, attention mechanisms, or other strategies. Furthermore, considerable performance gains were observed after the five-lead-grouping strategy was applied to DenseNet and ResNet. These results imply that the proposed strategy can be seamlessly integrated into various network architectures and considerably enhance performance. Full article

Blastomycosis, caused by dimorphic fungi of the Blastomyces genus, is endemic to regions in North America, including the Great Lakes and other parts of Canada and the United States of America. The infection primarily occurs through the inhalation of airborne conidia from contaminated soil and decaying organic matter. Pulmonary involvement is most common, but dissemination to other organs such as the skin and bones can occur, especially in immunocompromised individuals. Diagnosis is challenging due to its clinical overlap with other diseases. Culture remains the gold-standard diagnostic method, but is time-consuming, with sensitivity ranging from 66.4% to 86%. Tissue histopathology offers quicker results but has sensitivities ranging from 36% to 85%. Antigen detection assays show high sensitivity from 76.3% to 91.3% but suffer from cross-reactivity with other fungi. PCR methods offer high specificity, with sensitivity ranging from 67.6% to 100%. In immunocompromised patients, blastomycosis is often more severe, with a mortality rate exceeding 30%. Multi-modal diagnostic approaches are crucial for accurate detection and management. Full article

Fish are a vital aquatic resource worldwide, and the sustainable development of aquaculture is essential for global food security and economic growth. However, the high incidence of fish diseases in complex aquaculture environments significantly hampers sustainability, and traditional manual diagnosis methods are inefficient and often inaccurate. To address the challenges of small-lesion detection, lesion area size and morphological variation, and background complexity, we propose YOLO-TPS, a high-precision fish-disease detection model based on an improved YOLOv11n architecture. The model integrates a multi-module synergy strategy and a triple-attention mechanism to enhance detection performance. Specifically, the SPPF_TSFA module is introduced into the backbone to fuse spatial, channel, and neuron-level attention for better multi-scale feature extraction of early-stage lesions. A PC_Shuffleblock module incorporating asymmetric pinwheel-shaped convolutions is embedded in the detection head to improve spatial awareness and texture modeling under complex visual conditions. Additionally, a scale-aware dynamic intersection over union (SDIoU) loss function was designed to accommodate changes in the scale and morphology of lesions at different stages of the disease. Experimental results on a dataset comprising 4596 images across six fish-disease categories demonstrate superior performance (mAP_0.5: 97.2%, Precision: 97.9%, Recall: 95.1%) compared to the baseline. This study offers a robust, scalable solution for intelligent fish-disease diagnosis and has promising implications for sustainable aquaculture and animal health monitoring. Full article

Background/Objectives: Ultrasound imaging is widely employed to assess kidney health and diagnose renal diseases. Accurate segmentation of renal structures in ultrasound images plays a critical role in the diagnosis and treatment of related kidney diseases. However, challenges such as speckle noise and low contrast still hinder precise segmentation. Methods: In this work, we propose an encoder–decoder architecture, named MAT-UNet, which incorporates two distinct attention mechanisms to enhance segmentation accuracy. Specifically, the multi-convolution pixel-wise attention module utilizes the pixel-wise attention to enable the network to focus more effectively on important features at each stage. Furthermore, the triple-branch multi-head self-attention mechanism leverages the different convolution layers to obtain diverse receptive fields, capture global contextual information, compensate for the local receptive field limitations of convolution operations, and boost the segmentation performance. We evaluate the segmentation performance of the proposed MAT-UNet using the Open Kidney US Data Set (OKUD). Results: For renal capsule segmentation, MAT-UNet achieves a Dice Similarity Coefficient (DSC) of 93.83%, a 95% Hausdorff Distance (HD95) of 32.02 mm, an Average Surface Distance (ASD) of 9.80 mm, and an Intersection over Union (IOU) of 88.74%. Additionally, MAT-UNet achieves a DSC of 84.34%, HD95 of 35.79 mm, ASD of 11.17 mm, and IOU of 74.26% for central echo complex segmentation; a DSC of 66.34%, HD95 of 82.54 mm, ASD of 19.52 mm, and IOU of 51.78% for renal medulla segmentation; and a DSC of 58.93%, HD95 of 107.02 mm, ASD of 21.69 mm, and IOU of 43.61% for renal cortex segmentation. Conclusions: The experimental results demonstrate that our proposed MAT-UNet achieves superior performance in multiple renal structure segmentation in ultrasound images. Full article

Background/Objectives: Osteosarcoma (OS) is the most common malignant bone tumor in children and adolescents; the survival rate is as low as 24%. Accurate prediction of clinical outcomes remains a challenge due to tumor heterogeneity and the complexity of pediatric cases. This study aims to improve predictions of progressive disease, therapy response, relapse, and survival in pediatric OS using MRI-based radiomics and machine learning methods. Methods: Pre-treatment contrast-enhanced coronal T1-weighted MR scans were collected from 63 pediatric OS patients, with an additional nine external cases used for validation. Three strategies were considered for target region segmentation (whole-tumor, tumor sampling, and bone/soft tissue) and used for MRI-based radiomics. These were then combined with clinical features to predict OS clinical outcomes. Results: The mean age of OS patients was 11.8 ± 3.5 years. Most tumors were located in the femur (65%). Osteoblastic subtype was the most common histological classification (79%). The majority of OS patients (79%) did not have evidence of metastasis at diagnosis. Progressive disease occurred in 27% of patients, 59% of patients showed adequate therapy response, 25% experienced relapse after therapy, and 30% died from OS. Classification models based on bone/soft tissue segmentation generally performed the best, with certain clinical features improving performance, especially for therapy response and mortality. The top performing classifier in each outcome achieved 0.94–1.0 validation ROC AUC and 0.63–1.0 testing ROC AUC, while those without radiomic features (RFs) generally performed suboptimally. Conclusions: This study demonstrates the strong predictive capabilities of MRI-based radiomics and multi-region segmentations for predicting clinical outcomes in pediatric OS. Full article

Non-invasive ultrasound diagnosis, combined with deep learning, is frequently used for detecting thyroid diseases. However, real-time detection on portable devices faces limitations due to constrained computational resources, and existing models often lack sufficient capability for small object detection of thyroid nodules. To address this, this paper proposes an improved lightweight small object detection network framework called LISA-YOLO, which enhances the lightweight multi-scale collaborative fusion algorithm. The proposed framework exploits the inherent symmetrical characteristics of ultrasound images and the symmetrical architecture of the detection network to better capture and represent features of thyroid nodules. Specifically, an improved depthwise separable convolution algorithm replaces traditional convolution to construct a lightweight network (DG-FNet). Through symmetrical cross-scale fusion operations via FPN, detection accuracy is maintained while reducing computational overhead. Additionally, an improved bidirectional feature network (IMS F-NET) fully integrates the semantic and detailed information of high- and low-level features symmetrically, enhancing the representation capability for multi-scale features and improving the accuracy of small object detection. Finally, a collaborative attention mechanism (SAF-NET) uses a dual-channel and spatial attention mechanism to adaptively calibrate channel and spatial weights in a symmetric manner, effectively suppressing background noise and enabling the model to focus on small target areas in thyroid ultrasound images. Extensive experiments on two image datasets demonstrate that the proposed method achieves improvements of 2.3% in F1 score, 4.5% in mAP, and 9.0% in FPS, while maintaining only 2.6 M parameters and reducing GFLOPs from 6.1 to 5.8. The proposed framework provides significant advancements in lightweight real-time detection and demonstrates the important role of symmetry in enhancing the performance of ultrasound-based thyroid diagnosis. Full article

Cell confluence and number are critical indicators for assessing cellular growth status, contributing to disease diagnosis and the development of targeted therapies. Accurate and efficient cell segmentation is essential for quantifying these indicators. However, current segmentation methodologies still encounter significant challenges in addressing multi-scale heterogeneity, poorly delineated boundaries under limited annotation, and the inherent trade-off between computational efficiency and segmentation accuracy. We propose an innovative network architecture. First, a preprocessing pipeline combining contrast-limited adaptive histogram equalization (CLAHE) and Gaussian blur is introduced to balance noise suppression and local contrast enhancement. Second, a bidirectional feature pyramid network (BiFPN) is incorporated, leveraging cross-scale feature calibration to enhance multi-scale cell recognition. Third, adaptive kernel convolution (AKConv) is developed to capture the heterogeneous spatial distribution of glioma stem cells (GSCs) through dynamic kernel deformation, improving boundary segmentation while reducing model complexity. Finally, a probability density-guided non-maximum suppression (Soft-NMS) algorithm is proposed to alleviate cell under-detection. Experimental results demonstrate that the model achieves 95.7% mAP50 (box) and 95% mAP50 (mask) on the GSCs dataset with an inference speed of 38 frames per second. Moreover, it simultaneously supports dual-modality output for cell confluence assessment and precise counting, providing a reliable automated tool for tumor microenvironment research. Full article

Background/Objectives: Diffuse Large B-Cell Lymphoma (DLBCL) is the most common subtype of non-Hodgkin lymphoma and demands precise segmentation and classification of nuclei for effective diagnosis and disease severity assessment. This study aims to evaluate the performance of HoVerNet, a deep learning model, for nuclei segmentation and classification in CMYC-stained whole slide images and to assess its integration into a user-friendly diagnostic tool. Methods: A dataset of 122 CMYC-stained whole slide images (WSIs) was used. Pre-processing steps, including stain normalization and patch extraction, were applied to improve input consistency. HoVerNet, a multi-branch neural network, was used for both nuclei segmentation and classification, particularly focusing on its ability to manage overlapping nuclei and complex morphological variations. Model performance was validated using metrics such as accuracy, precision, recall, and F1 score. Additionally, a graphic user interface (GUI) was developed to incorporate automated segmentation, cell counting, and severity assessment functionalities. Results: HoVerNet achieved a validation accuracy of 82.5%, with a precision of 85.3%, recall of 82.6%, and an F1 score of 83.9%. The model showed powerful performance in differentiating overlapping and morphologically complex nuclei. The developed GUI enabled real-time visualization and diagnostic support, enhancing the efficiency and usability of DLBCL histopathological analysis. Conclusions: HoVerNet, combined with an integrated GUI, presents a promising approach for streamlining DLBCL diagnostics through accurate segmentation and real-time visualization. Future work will focus on incorporating Vision Transformers and additional staining protocols to improve generalizability and clinical utility. Full article

Cardiorenal syndrome (CRS) is a term used to describe the combined dysfunction of the heart and kidneys. This complex disorder is widely acknowledged to be challenging in both its diagnosis and management, and this is the case particularly in the elderly population, due to multi-morbidity, polypharmacy, and age-related physiological changes. Given advancements in medicine and more prolonged cumulative exposure to risk factors in the elderly population, it is likely that the prevalence of chronic kidney disease (CKD) and heart failure (HF) will continue to rise going forward. Hence, understanding the mechanisms involved in the development of CRS is paramount. There are five different CRS types—they are categorised depending on the primary organ involved the acuity of disease. The pathophysiological process behind CRS is complex, involving the interplay of many processes including hemodynamic changes, neurohormonal activation, inflammation, oxidative stress, and endothelial dysfunction and vascular stiffness. The numerous diagnostic and management challenges associated with CRS are significantly further exacerbated in an elderly population. Biomarkers used to aid the diagnosis of CRS, such as serum creatinine and brain natriuretic peptide (BNP), can be challenging to interpret in the elderly population due to age-related renal senescence and multiple comorbidities. Polypharmacy can contribute to the development of CRS and therefore, before initiating treatment, coordinating a patient-centred, multi-speciality, holistic review to assess potential risks versus benefits of prescribed treatments is crucial. The overall prognosis of CRS in the elderly remains poor. Treatments are primarily directed at addressing the sequelae of the underlying aetiology, which often involves the removal of fluid through diuretics or ultrafiltration. Careful considerations when managing elderly patients with CRS is essential due to the high prevalence of frailty and functional decline. As such, in these patients, early discussions around advance care planning should be prioritised. Full article

This article describes a new software architecture for the non-invasive detection of canine leishmaniasis disease. The proposed platform combines gas-sensing technologies, artificial intelligence (AI), and modular cloud-based software components to identify disease-specific volatile organic compounds (VOCs) found in dog breath and hair samples. The system, which has a multi-tier architecture that includes data collection, pre-processing, machine learning-based analysis, diagnosis-request processing, and user interfaces for veterinarians, faculty researchers, and dog owners, has been integrated into a Li-ion Power website plug-in. The primary goal of implementing the proposed platform is to detect parasites at any point they are infectious to a host. This includes detecting parasites at all stages of their life cycle, where they can infect a new host. In addition, this is crucial for accurate diagnosis, effective treatment, and preventing further transmission. Full article

The Fusarium genus includes some of the most economically and ecologically impactful fungal pathogens affecting global agriculture and human health. Over the past 15 years, rapid advances in molecular biology, genomics, and diagnostic technologies have reshaped our understanding of Fusarium taxonomy, host–pathogen dynamics, mycotoxin biosynthesis, and disease management. This review synthesizes key developments in these areas, focusing on agriculturally important Fusarium species complexes such as the Fusarium oxysporum species complex (FOSC), Fusarium graminearum species complex (FGSC), and a discussion on emerging lineages such as Neocosmospora. We explore recent shifts in species delimitation, functional genomics, and the molecular architecture of pathogenicity. In addition, we examine the global burden of Fusarium-induced mycotoxins by examining their prevalence in three of the world’s most widely consumed staple crops: maize, wheat, and rice. Last, we also evaluate contemporary management strategies, including molecular diagnostics, host resistance, and integrated disease control, positioning this review as a roadmap for future research and practical solutions in Fusarium-related disease and mycotoxin management. By weaving together morphological insights and cutting-edge multi-omics tools, this review captures the transition into a new era of Fusarium research where integrated, high-resolution approaches are transforming diagnosis, classification, and management. Full article

Background/Objectives: Neurodegenerative proteinopathies, such as Alzheimer’s disease (AD), Parkinson’s disease (PD), and dementia with Lewy bodies (DLB), are increasingly prevalent worldwide mainly due to population aging. These conditions are marked by complex etiologies, overlapping pathologies, and progressive clinical decline, with significant consequences for patients, caregivers, and healthcare systems. This review aims to synthesize evidence on the healthcare complexities of major neurodegenerative proteinopathies to highlight current knowledge gaps, and to inform future care models, policies, and research directions. Methods: We conducted a comprehensive literature search in PubMed/MEDLINE using combinations of MeSH terms and keywords related to neurodegenerative diseases, proteinopathies, diagnosis, sex, management, treatment, caregiver burden, and healthcare delivery. Studies were included if they addressed the clinical, pathophysiological, economic, or care-related complexities of aging-related neurodegenerative proteinopathies. Results: Key themes identified include the following: (1) multifactorial and unclear etiologies with frequent co-pathologies; (2) long prodromal phases with emerging biomarkers; (3) lack of effective disease-modifying therapies; (4) progressive nature requiring ongoing and individualized care; (5) high caregiver burden; (6) escalating healthcare and societal costs; and (7) the critical role of multidisciplinary and multi-domain care models involving specialists, primary care, and allied health professionals. Conclusions: The complexity and cost of neurodegenerative proteinopathies highlight the urgent need for prevention-focused strategies, innovative care models, early interventions, and integrated policies that support patients and caregivers. Prevention through the early identification of risk factors and prodromal signs is critical. Investing in research to develop effective disease-modifying therapies and improve early detection will be essential to reducing the long-term burden of these disorders. Full article

With the growing use of deep learning in medical image analysis, automated classification of fundus images is crucial for the early detection of fundus diseases. However, the complexity of fluorescein fundus angiography (FFA) images poses challenges in the accurate identification of lesions. To address these issues, we propose the Enhanced Feature Fusion ConvNeXt (EFF-ConvNeXt) model, a novel architecture combining VGG16 and an enhanced ConvNeXt for FFA image classification. VGG16 is employed to extract edge features, while an improved ConvNeXt incorporates the Context-Aware Feature Fusion (CAFF) strategy to enhance global contextual understanding. CAFF integrates an Improved Global Context (IGC) module with multi-scale feature fusion to jointly capture local and global features. Furthermore, an SKNet module is used in the final stages to adaptively recalibrate channel-wise features. The model demonstrates improved classification accuracy and robustness, achieving 92.50% accuracy and 92.30% F1 score on the APTOS2023 dataset—surpassing the baseline ConvNeXt-T by 3.12% in accuracy and 4.01% in F1 score. These results highlight the model’s ability to better recognize complex disease features, providing significant support for more accurate diagnosis of fundus diseases. Full article

Accurate segmentation of cardiac MR images using deep neural networks is crucial for cardiac disease diagnosis and treatment planning, as it provides quantitative insights into heart anatomy and function. However, achieving high segmentation accuracy relies heavily on extensive, precisely annotated datasets, which are costly and time-consuming to obtain. This study addresses this challenge by proposing a novel data augmentation framework based on a condition-guided diffusion generative model, controlled by multiple cardiac labels. The framework aims to expand annotated cardiac MR datasets and significantly improve the performance of downstream cardiac segmentation tasks. The proposed generative data augmentation framework operates in two stages. First, a Label Diffusion Module is trained to unconditionally generate realistic multi-category spatial masks (encompassing regions such as the left ventricle, interventricular septum, and right ventricle) conforming to anatomical prior probabilities derived from noise. Second, cardiac MR images are generated conditioned on these semantic masks, ensuring a precise one-to-one mapping between synthetic labels and images through the integration of a spatially-adaptive normalization (SPADE) module for structural constraint during conditional model training. The effectiveness of this augmentation strategy is demonstrated using the U-Net model for segmentation on the enhanced 2D cardiac image dataset derived from the M&M Challenge. Results indicate that the proposed method effectively increases dataset sample numbers and significantly improves cardiac segmentation accuracy, achieving a 5% to 10% higher Dice Similarity Coefficient (DSC) compared to traditional data augmentation methods. Experiments further reveal a strong correlation between image generation quality and augmentation effectiveness. This framework offers a robust solution for data scarcity in cardiac image analysis, directly benefiting clinical applications. Full article