Quality of life is greatly affected by chronic wounds. It requires more intensive care than acute wounds. Schedule follow-up appointments with their doctor to track healing. Good wound treatment promotes healing and fewer problems. Wound care requires precise and reliable wound measurement to optimize patient treatment and outcomes according to evidence-based best practices. Images are used to objectively assess wound state by quantifying key healing parameters. Nevertheless, the robust segmentation of wound images is complex because of the high diversity of wound types and imaging conditions. This study proposes and evaluates a novel hybrid model developed for wound segmentation in medical images. The model combines advanced deep learning techniques with traditional image processing methods to improve the accuracy and reliability of wound segmentation. The main objective is to overcome the limitations of existing segmentation methods (UNet) by leveraging the combined advantages of both paradigms. In our investigation, we introduced a hybrid model architecture, wherein a ResNet34 is utilized as the encoder, and a UNet is employed as the decoder. The combination of ResNet34’s deep representation learning and UNet’s efficient feature extraction yields notable benefits. The architectural design successfully integrated high-level and low-level features, enabling the generation of segmentation maps with high precision and accuracy. Following the implementation of our model to the actual data, we were able to determine the following values for the Intersection over Union (IOU), Dice score, and accuracy: 0.973, 0.986, and 0.9736, respectively. According to the achieved results, the proposed method is more precise and accurate than the current state-of-the-art.

Introduction: Breast cancer (BC) is a malignant neoplasm that originates in the mammary gland’s cellular structures and remains one of the most prevalent cancers among women, ranking second in cancer-related mortality after lung cancer. Early and accurate diagnosis is crucial due to the heterogeneous nature of breast cancer and its rapid progression. However, manual detection and classification are often time-consuming and prone to errors, necessitating the development of automated and reliable diagnostic approaches.Methods: Recent advancements in deep learning have significantly improved medical image analysis, demonstrating superior predictive performance in breast cancer detection using ultrasound images. Despite these advancements, training deep learning models from scratch can be computationally expensive and data-intensive. Transfer learning, leveraging pre-trained models on large-scale datasets, offers an effective solution to mitigate these challenges. In this study, we investigate and compare multiple deep-learning models for breast cancer classification using transfer learning. The evaluated architectures include modified InceptionV3, GoogLeNet, ShuffleNet, AlexNet, VGG-16, and SqueezeNet. Additionally, we propose a deep neural network model that integrates features from modified InceptionV3 to further enhance classification performance.Results: The experimental results demonstrate that the modified InceptionV3 model achieves the highest classification accuracy of 99.10%, with a recall of 98.90%, precision of 99.00%, and an F1-score of 98.80%, outperforming all other evaluated models on the given datasets.Discussion: The achieved findings underscore the potential of the proposed approach in enhancing diagnostic precision and confirm the superiority of the modified InceptionV3 model in breast cancer classification tasks.

Cardiovascular diseases remain one of the main threats to human health, significantly affecting the quality and life expectancy. Effective and prompt recognition of these diseases is crucial. This research aims to develop an effective novel hybrid method for automatically detecting dangerous arrhythmias based on cardiac patients’ short electrocardiogram (ECG) fragments. This study suggests using a continuous wavelet transform (CWT) to convert ECG signals into images (scalograms) and examining the task of categorizing short 2-s segments of ECG signals into four groups of dangerous arrhythmias that are shockable, including ventricular flutter (C1), ventricular fibrillation (C2), ventricular tachycardia torsade de pointes (C3), and high-rate ventricular tachycardia (C4). We propose developing a novel hybrid neural network with a deep learning architecture to classify dangerous arrhythmias. This work utilizes actual electrocardiogram (ECG) data obtained from the PhysioNet database, alongside artificially generated ECG data produced by the Synthetic Minority Over-sampling Technique (SMOTE) approach, to address the issue of imbalanced class distribution for obtaining an accuracy-trained model. Experimental results demonstrate that the proposed approach achieves high accuracy, sensitivity, specificity, precision, and an F1-score of 97.75%, 97.75%, 99.25%, 97.75%, and 97.75%, respectively, in classifying all the four shockable classes of arrhythmias and are superior to traditional methods. Our work possesses significant clinical value in real-life scenarios since it has the potential to significantly enhance the diagnosis and treatment of life-threatening arrhythmias in individuals with cardiac disease. Furthermore, our model also has demonstrated adaptability and generality for two other datasets.

Electrocardiogram (ECG) analysis is crucial for diagnosing cardiovascular diseases (CVD), especially atrial fibrillation (AF), a prevalent cardiac rhythm abnormality. However, the variability and complexity of ECG signals make AF classification challenging, highlighting the need for more accurate and reliable methods. This paper introduces a novel deep learning (DL) architecture designed to enhance the processing, feature extraction, and analysis of ECG signals. The proposed model utilizes a hybrid framework that combines standard and dilated convolutional networks, advanced attention mechanisms, and temporal sequence learning to address the complexities of ECG data. A parallel architecture integrates a MobileViT block for efficient spatial feature extraction and an Efficient Channel Attention (ECA) module to refine feature representations. Simultaneously, a Long Short-Term Memory (LSTM) network captures temporal dependencies in the data. The concatenation of the outputs from both the MobileViT-ECA block and the LSTM network allows for the extraction of both local and global features. Fully connected layers, along with dropout regularization, ensure robust performance and effective classification. We analyzed ECG signals of three different lengths (1, 2, and 3 seconds) to investigate how segment length affects model performance. Additionally, we conducted various classification scenarios and an ablation study to simulate real-world conditions and identify key components of the architecture. Our experimental findings show that the model attains high accuracy in ECG classification and AF identification, with average metrics including accuracy of 87.80%, recall of 87.80%, F1-score of 87.45%, and specificity of 95.66%. The proposed model outperforms existing methods on the same AF dataset, demonstrating its superior performance. This method accurately classifies ECG signals and detects AF, highlighting its potential for clinical application. The results help move forward the development of automated tools for diagnosing heart diseases and create new opportunities for flexible solutions in this field.

The highly precise and trustworthy segmentation of the left ventricle (LV) and myocardium is critical for diagnosing and treating cardiovascular disorders, which includes persistent microvascular obstruction (MVO) as well as myocardial infarction (MI) diseases. This process improves diagnostic accuracy and optimizes the planning and implementation of therapeutic interventions, ultimately improving the quality of care and patient prognosis. Limitations of earlier investigations include neglecting the complex image pre-processing required to accurately delineate areas of the LV and myocardium (Myo) in MRI and the absence of a substantial, high-quality dataset. Thus, this paper presents a comprehensive end-to-end framework, which includes contrast-limited adaptive histogram equalization (CLAHE) and bilateral filtering methods for image pre-processing and the development and implementation of a proposed deep model for left ventricular and myocardium segmentation. This study utilizes the EMIDEC database for the training and assessment of the model, allowing for a detailed comparative analysis with six state-of-the-art (SOTA) segmentation models. This approach provides a high accuracy and reliability for the segmentation that is crucial for the diagnosis and treatment of cardiovascular disorders. The achievements of the proposed model are demonstrated by high average values of segmentation rates, such as an Intersection over Union (IoU) of 93.73%, Recall of 96.54%, Dice coefficient of 96.70%, Precision of 96.86%, and F1-score of 96.70%. To verify the generalization capability, we assessed our suggested model on five supplementary databases, which substantiates its exceptional efficiency and adaptability in a diverse environment. The presented findings demonstrate that the proposed deep model surpasses current methods, offering more a precise and resilient segmentation of cardiac structures.