International Journal of Imaging Systems and Technology最新文献

Diabetic retinopathy (DR), one of the most prevalent microvascular complications of diabetes, stands as a leading cause of vision loss globally. Due to its asymptomatic nature in early stages, delayed diagnosis and staging may result in irreversible visual impairment. Therefore, accurate and simultaneous lesion segmentation and stage classification of DR are of critical clinical importance. In this study, a two-stage, end-to-end, holistic framework is proposed for automated DR diagnosis. In the first stage, an Improved U-Net architecture enhanced with residual blocks and additional convolutional layers is employed to segment small and low-contrast lesions such as microaneurysms, hemorrhages, and hard/soft exudates with high precision. Model hyperparameters are optimized using the harmony search algorithm to enhance training efficiency. In the second stage, lesion-based weight maps obtained from the segmentation step are applied to fundus images from the APTOS dataset, generating enriched inputs for classification. A vision transformer (ViT)-based model, augmented with a Convolutional Block Attention Module (CBAM), is utilized to improve feature extraction. In addition, features derived from ViT are further refined using a graph convolutional network (GCN) and traditional machine-learning classifiers. The proposed approach achieves high performance in multi-class DR stage classification. Compared to existing studies, the framework demonstrates notable improvements in both segmentation and classification accuracy, offering a robust and generalizable solution for DR diagnosis.

Accurate segmentation of medical images is critical for disease diagnosis and treatment planning. However, challenges such as fuzzy boundaries, low contrast, and complex anatomical structures often hinder performance. We propose EGCF-Net, a novel U-Net-based architecture that integrates a hybrid encoder with an edge-aware graph-based attention network to address these limitations. The hybrid encoder integrates the Swin transformer and Kronecker convolution to capture global and local contextual dependencies. Additionally, skip connections are enhanced using an edge-aware graph-based attention module, which combines graph spatial attention and graph channel attention to dynamically model spatial correlations and edge-aware contextual affinities. This design leads to edge-enhanced boundary delineation and improved regional consistency. We evaluate EGCF-Net on four benchmark datasets (Synapse, Kidney Stone, ISIC 2016, and ISIC 2018), achieving Dice scores of 84.70%, 93.07%, 91.07%, and 88.62%, respectively, surpassing existing state-of-the-art methods. Quantitative and qualitative results further validate the efficacy and robustness of the proposed approach, highlighting its potential for advancing medical image segmentation.

Gastrointestinal disorders include diseases that negatively affect people's daily life and carry the risk of cancer. Therefore, accurate and early diagnosis of these diseases is important for treatment process of patients. Deep learning architectures, which have achieved significant success in medical image analysis, are effectively used in early diagnosis and diagnosis systems. Therefore, in this study, a new approach that achieves higher accuracy in the detection of gastrointestinal diseases by combining DenseNet and Vision Transformer models with stacking ensemble is proposed. As a result of the experiments, the proposed model achieved 99.06% accuracy in a single test and 98.64% accuracy on mean as a result of 5-fold cross-validation. The proposed approach shows promising accuracy and reliability as evidenced by the results of experiments on the KvasirV2 dataset, and has the potential to be an effective method for the detection of gastrointestinal diseases. To improve model interpretability, the Explainable AI technique Grad-CAM and attention map visualizations were used, allowing visual justification of the model's predictions and highlighting clinically relevant regions in endoscopic images. The model obtained by combining DenseNet and Vision Transformer models with the stacking ensemble method is expected to be an example for future studies in the field of health and image processing, especially gastrointestinal diseases.

The skin, the largest organ of the human body, is vulnerable to numerous pathological conditions collectively referred to as skin lesions, encompassing a wide spectrum of dermatoses. Diagnosing these lesions remains challenging for medical practitioners due to their subtle visual differences, many of which are imperceptible to the naked eye. While not all lesions are malignant, some serve as early indicators of serious diseases such as skin cancer, emphasizing the urgent need for accurate and timely diagnostic tools. This study advances dermatological diagnostics by curating a comprehensive and balanced dataset containing 9360 dermoscopic and clinical images across 39 lesion categories, synthesized from five publicly available datasets. Five state-of-the-art deep learning architectures—MobileNetV2, Xception, InceptionV3, EfficientNetB1, and Vision Transformer (ViT)—were systematically evaluated on this dataset. To enhance model precision and robustness, Efficient Channel Attention (ECA) and Convolutional Block Attention Module (CBAM) mechanisms were integrated into these architectures. Extensive evaluation across multiple performance metrics demonstrated that the Vision Transformer with CBAM achieved the best results, with 93.46% accuracy, 94% precision, 93% recall, 93% F1-score, and 93.67% specificity. These findings highlight the effectiveness of attention-guided Vision Transformers in addressing complex, large-scale, multi-class skin lesion classification. By combining dataset diversity with advanced attention mechanisms, the proposed framework provides a reliable and interpretable tool to assist medical professionals in accurate and efficient lesion diagnosis, thereby contributing to improved clinical decision-making and patient outcomes.

Heart disease (HD) is still a major cause of death worldwide, which emphasizes the importance of early and precise prediction. This paper presents DenseEchoNet, a deep learning model that has been optimized with the Gazelle Optimizer Algorithm (GOA). The hybrid HD-ENN technique is used for balanced learning to solve class imbalance and high dimensionality, while squared exponential kernel-based PCA (SEKPCA) effectively reduces dimensionality. DenseEchoNet outperforms current baseline models with accuracies of 0.9795 as well as 0.9785, respectively, when tested on the HDHI and Cleveland datasets. XAI approaches, such as LIME and SHAP, improve model interpretability by offering distinct insights on feature contributions to HD risk. For early HD prediction, this system provides a straightforward, accurate, and efficient solution.

Skin lesion segmentation from dermoscopic images must be done accurately and consistently in order to diagnose diseases and arrange treatments. However, when dealing with issues like fuzzy lesion region boundaries, multiscale features, and notable variations in the lesion region's size, shape, and color, existing methods typically have high computational complexity and large parameter counts. They also frequently suffer from decreased segmentation accuracy due to inadequate capture of local features and global information. In this paper, a lightweight deep learning network based on high-performance adaptive attention is proposed to overcome these issues. Specifically, a deep convolutional neural network is introduced to capture local information. Meanwhile, we create a high-performance adaptive attention feature fusion module (EAAF) that uses dynamic feature selection to achieve adaptive fusion of global information with multiscale local features. Furthermore, we created a reverse dynamic feature fusion module (RDFM) at the decoding stage to efficiently fuse features at various levels while taking into account the integrity and specifics of the lesion region to increase the precision of complex lesion region segmentation. We carried out in-depth tests on three publicly accessible datasets International Skin Imaging Collaboration (ISIC)-2016, ISIC-2018, and PH² to assess the method's efficacy and contrasted the outcomes with those of the most advanced techniques; the results confirmed that the suggested approach was superior.

Gastrointestinal (GI) bleeding, arising from various conditions, can be critical if untreated. Wireless capsule endoscopy (WCE) is a highly effective method for detecting GI bleeding, offering full visualization of the GI tract. However, the large number of images generated per patient poses challenges for clinicians, leading to prolonged analysis times and increased risk of human error. This emphasizes the need for computer-aided diagnosis systems. In this study, we introduce SEA-Net (Structured Efficient Attention Network), a novel deep learning network for detecting bleeding regions in WCE images. SEA-Net integrates a Convolutional Block Attention Module (CBAM) with long skip connections to enhance gradient flow and improve blood region localization. The EfficientNet-B4 encoder improves feature extraction efficiency and generalizability. A five-fold cross validation demonstrates consistent performance, while generalization tests, including precision-recall curves, ROC curves, and F1 measure, further validate the model's robustness. Minimal performance degradation was observed when the training data was reduced from 80% to 20%. Experimental results show that SEA-Net achieves a Dice score of 93.64% and an IoU score of 88.61% on a publicly available WCE dataset, outperforming state-of-the-art models and highlighting its strong potential for clinical application.

Heart disease remains a leading global health concern, necessitating accurate and interpretable risk prediction models for effective clinical decision-making. Accurate heart disease risk prediction is crucial for preventive healthcare, yet traditional machine learning models often struggle with the inherent uncertainty and nonlinear patterns in medical data. While deep neural networks (DNNs) excel at feature extraction, their lack of interpretability limits clinical utility, whereas fuzzy inference systems (FIS) offer transparency but lack hierarchical learning capabilities. To bridge this gap, we propose a novel Deep Fuzzy Inference System (DFIS) that integrates DNNs and FIS into a unified architecture, combining the strengths of both approaches. The DFIS leverages a weighted fusion mechanism to combine probabilistic outputs from an Adam Cuckoo Search-optimized DNN and a trapezoidal membership-based FIS, enabling simultaneous high accuracy and interpretability. The performance is evaluated on the Cleveland heart disease dataset; the DFIS achieves 97.2% accuracy, outperforming a standalone DNN (95.4%) and ANFIS (91.7%) under the same experimental conditions while providing clinically actionable risk stratification into normal, less critical, and very critical categories.