Microscopy Research and Technique · مجلد 89 (5) · 687-704
Prostate cancer is a prevalent and serious health concern, ranking among the most frequently diagnosed cancers and a leading cause of cancer-related deaths in men worldwide. Early detection and accurate diagnosis are crucial for improving patient outcomes by limiting disease progression. Histopathological image analysis remains the gold standard for prostate cancer detection; however, manual interpretation is time-consuming and requires specialized expertise. To address these challenges, this study proposes a hybrid deep learning framework that combines an ensemble of transfer-learned CNNs (VGG-16, DenseNet-121, and AlexNet) with a fine-tuned Vision Transformer (ViT). The CNN ensemble extracts rich local features, while the ViT captures global contextual dependencies through a self-attention mechanism and a multilayer perceptron (MLP). Additionally, a cross-attention fusion (CAF) module integrates local and global features, and knowledge distillation (KD) enables a lightweight student network suitable for efficient clinical deployment. The study utilizes the publicly available PANDA dataset for training and testing. Preprocessing steps, including patch generation, gamma correction, and stain deconvolution, enhance image quality and feature representation. A comprehensive evaluation was conducted using standard performance metrics such as accuracy, true positive rate (TPR), true negative rate (TNR), precision, F1-score, false negative rate (FNR), and false positive rate (FPR). An ablation study confirmed the contribution of each module, highlighting the critical role of ensemble CNNs, CAF, and ViT in improving performance. Experimental results demonstrate that the proposed model outperforms conventional transfer learning models and existing state-of-the-art techniques, achieving 97.91% accuracy, along with significant improvements in TPR, TNR, and reduced FNR/FPR. The computational complexity, evaluated in terms of parameters, FLOPs, GPU memory, and inference time, indicates that the proposed model is more demanding than traditional CNNs. Nevertheless, the architecture strikes a practical balance between predictive accuracy and efficiency, making it suitable for real-world clinical applications. These findings underscore the potential of AI-powered hybrid models in expediting prostate cancer diagnosis and enabling timely intervention for improved patient outcomes.
prostate cancer detectionhistopathology image analysishybrid CNN-ViT modelcross-attention fusion
International Journal of Imaging Systems and Technology · مجلد 35 (5)
ABSTRACT Recent advancements in Deep Learning (DL) have enabled the development of Computer‐Aided Diagnosis (CAD) systems for detecting Acute Lymphoblastic Leukemia (ALL) and its subtypes. However, this field faces challenges, particularly due to limited annotated datasets and a lack of efficient modalities. To address these issues, we propose MHAOSL‐net, a novel hybrid DL model specifically designed for the accurate classification of B‐ALL, T‐ALL, and normal cells in blood smear images. The key contributions lie in the integration of four primary components: (1) lightweight MobileNetV2 for backbone feature extraction, (2) a Global Context Information Convolutional Block Attention Module (GCI‐CBAM) for refined local representation using contextual information, (3) an Attention‐Free Transformer (AFT) that captures global dependencies replacing traditional self‐attention, and (4) an Orthogonal SoftMax Layer (OSL) that improves class separability by enforcing orthogonality in the decision space. This unified architecture not only reduces computational overhead but also improves classification performance and generalizability. To the best of our knowledge, this is the first framework that combines an AFT with an OSL in the context of leukemia subtype detection. The performance analysis of the proposed 3‐class classification scheme has been assessed on two novel datasets, namely BBCI_B&T_ALL_2024 and heterogeneous datasets. The experimental results show that the proposed scheme provides better performance, with 99.52% accuracy, 99.36% average precision, and 99.36% average F1‐score on the BBCI_B&T_ALL_2024. Similarly, it achieves better performance with 99.55% accuracy, 99.40% average precision, and 99.40% average F1‐score on the heterogeneous dataset. The qualitative investigation using Gradient‐weighted Class Activation Mapping (Grad‐CAM) visualization also confirms the efficacy of the proposed model for detecting B‐ALL, T‐ALL, and normal cells. The comparative studies establish the superiority of the proposed scheme over other state‐of‐the‐art approaches. These findings indicate that MHAOSL‐Net offers a promising and efficient solution for reliable ALL subtype detection in clinical settings.
Advanced Health Science and Technology Journal · مجلد 1 (2) · 92-99
Abstract Background: Epilepsy remains one of the most prevalent neurological disorders worldwide, characterized by recurrent seizures resulting from abnormal electrical brain activity. Traditional diagnostic methods, such as electroencephalography (EEG) and magnetic resonance imaging (MRI), although widely used, often fail to provide sufficient accuracy when applied in isolation due to their inherent limitations in temporal or spatial resolution. These challenges highlight the need for integrated analytical approaches capable of leveraging complementary modalities for improved diagnostic precision. Objectives: This study aims to address the limitations of single-modality diagnostic techniques by proposing a multimodal deep learning framework that integrates EEG and MRI data to enhance the accuracy of epilepsy detection. The objectives include preprocessing EEG signals to remove artifacts, segmenting MRI scans for structural feature extraction, employing CNNs to model EEG spatio-temporal dependencies, using ViTs to capture hierarchical MRI features, and integrating these representations through a cross-attention fusion mechanism for effective supervised classification. Method: The methodology involves preprocessing EEG signals to eliminate artifacts and ensure clean temporal representation, along with MRI scan segmentation to extract structural information. Convolutional neural networks (CNNs) were used to model spatio-temporal patterns within EEG signals, while vision transformers (ViTs) extracted spatially hierarchical features from MRI data. A cross-attention fusion mechanism was designed to integrate these complementary modalities, and a supervised classifier performed the final prediction. Model training and evaluation were carried out using a high-performance computing setup with GPU acceleration to efficiently handle multimodal data. Results: Experimental results demonstrated that the proposed multimodal deep learning model significantly outperformed state-of-the-art pretrained CNN and ViT baselines across major evaluation metrics, including accuracy, precision, recall, F1-score, and Matthews correlation coefficient. The confusion matrix further confirmed robust differentiation between normal and epileptic classes, emphasizing the reliability of the proposed framework for accurate clinical decision-making. Conclusion: The findings of this study indicate that integrating EEG and MRI data through a multimodal fusion framework provides a substantial improvement in epilepsy detection compared to single-modality approaches. The results highlight the importance of combining complementary temporal and structural information to achieve reliable diagnostic performance. This work contributes to advancing early detection, reducing diagnostic errors, and supporting timely treatment strategies, reinforcing the value of multimodal deep learning approaches in personalized healthcare.
To identify patterns in big medical datasets and use Deep Learning and Machine Learning (ML) to reliably diagnose Cardio Vascular Disease (CVD), researchers are currently delving deeply into these fields. Training on large datasets and producing highly accurate validation results is exceedingly difficult. Furthermore, early and precise diagnosis is necessary due to the increased global prevalence of cardiovascular disease (CVD). However, the increasing complexity of healthcare datasets makes it challenging to detect feature connections and produce precise predictions. To address these issues, the Intelligent Cardiovascular Disease Diagnosis based on Ant Colony Optimisation with Enhanced Deep Learning (ICVD-ACOEDL) model was developed. This model employs feature selection (FS) and hyperparameter optimization to diagnose CVD. Applying a min-max scaler, medical data is first consistently prepared. The key feature that sets ICVD-ACOEDL apart is the use of Ant Colony Optimisation (ACO) to select an optimal feature subset, which in turn helps to upgrade the performance of the ensuring deep learning enhanced neural network (DLENN) classifier. The model reforms the hyperparameters of DLENN for CVD classification using Bayesian optimization. Comprehensive evaluations on benchmark medical datasets show that ICVD-ACOEDL exceeds existing techniques, indicating that it could have a significant impact on CVD diagnosis. The model furnishes a workable way to increase CVD classification efficiency and accuracy in real-world medical situations by incorporating ACO for feature selection, min-max scaling for data pre-processing, and Bayesian optimization for hyperparameter tweaking.
BMC Medical Informatics and Decision Making · مجلد 24 (1) · 92-92
Emerging from the convergence of digital twin technology and the metaverse, consumer health (MCH) is witnessing a transformative shift. The amalgamation of bioinformatics with healthcare Big Data has ushered in a new era of disease prediction models that harness comprehensive medical data, enabling the anticipation of illnesses even before the onset of symptoms. In this model, deep neural networks stand out because they improve accuracy remarkably by increasing network depth and making weight changes using gradient descent. Nonetheless, traditional methods face their own set of challenges, including the issues of gradient instability and slow training. In this case, the Broad Learning System (BLS) stands out as a good alternative. It gets around the problems with gradient descent and lets you quickly rebuild a model through incremental learning. One problem with BLS is that it has trouble extracting complex features from complex medical data. This makes it less useful in a wide range of healthcare situations. In response to these challenges, we introduce DAE-BLS, a novel hybrid model that marries Denoising AutoEncoder (DAE) noise reduction with the efficiency of BLS. This hybrid approach excels in robust feature extraction, particularly within the intricate and multifaceted world of medical data. Validation using diverse datasets yields impressive results, with accuracies reaching as high as 98.50%. DAE-BLS's ability to rapidly adapt through incremental learning holds great promise for accurate and agile disease prediction, especially within the complex and dynamic healthcare scenarios of today.
disease predictiondigital twinmetaverseconsumer health
Expert Systems with Applications · مجلد 255 · 124650-124650
Most existing methods for detecting fraudulent news or other forms of disinformation primarily rely on user profiling or content analysis, determining whether a given article aligns with a user’s stylistic or content-related preferences. This research departs from conventional approaches by concentrating not only on the characteristics of shared content but also on user interactions and the resultant topologies of content propagation trees. In our study, we have introduced a deep learning model based on Graph Convolutional Neural Networks (GCNN) and enhanced with multi-head attention mechanisms. This model leverages a wide range of psycholinguistic attributes extracted from users’ posts, including sentiment, emotional content, linguistic features, personality traits, readability, and communication style. We further enrich these attributes with BERT embeddings to improve textual representation. Our research framework involves creating two distinct graph networks: the user interaction graph and the semantic propagation graph. These graphical representations are essential for visualizing dynamic interactions and patterns of information dissemination among users. For each user, we generate a set of carefully crafted features that capture their unique characteristics and behaviors. These user-specific features are then integrated into the User Interaction Graph, enabling a more nuanced understanding and representation of user interactions within our proposed model. The proposed framework has demonstrated superior performance on benchmark datasets, achieving accuracies and precisions of 91.07% and 91.24% on the FakeNewsNet dataset, and 94.20% and 94.92% on the FibVid dataset, respectively. The results obtained from the experimental evaluation have also revealed the effect of various parameters significant to profile disinformers, signifying a substantial improvement in the field of fake news detection and profiling.
The Internet of Things (IoT) is essential in several Internet application areas and remains a key technology for communication technologies. Shorter delays in transmission between Roadside Units (RSUs) and vehicles, road safety, and smooth traffic flow are the major difficulties of Intelligent Transportation System (ITS). Machine Learning (ML) was an advanced technique to find hidden insights into ITSs. This article introduces an Improved Arithmetic Optimization with Deep Learning Driven Traffic Congestion Control (IAOADL-TCC) for ITS in Smart Cities. The presented IAOADL-TCC model enables traffic data collection and route traffic on existing routes for avoiding traffic congestion in smart cities. The IAOADL-TCC algorithm exploits a hybrid convolution neural network attention long short-term memory (HCNN-ALSTM) method for traffic congestion control. In addition, an IAOA-based hyperparameter tuning strategy is derived to optimally modify the parameters of the HCNN-ALSTM model. The presented IAOADL-TCC model effectively enhances the flow of traffic and reduces congestion. The experimental validation was performed using the road traffic dataset from the Kaggle repository. The proposed model obtained an average accuracy of 98.03 % with an error rate of 1.97 %. The experimental analysis stated the superior performance of the IAOADL-TCC approach over other DL methods.
traffic congestion controlInternet of Thingsintelligent transportation systemsarithmetic optimization
Frontiers in Computational Neuroscience · مجلد 18 · 1485121-1485121
Facial emotion recognition (FER) can serve as a valuable tool for assessing emotional states, which are often linked to mental health. However, mental health encompasses a broad range of factors that go beyond facial expressions. While FER provides insights into certain aspects of emotional well-being, it can be used in conjunction with other assessments to form a more comprehensive understanding of an individual's mental health. This research work proposes a framework for human FER using UNet image segmentation and transfer learning with the EfficientNetB4 model (called FacialNet). The proposed model demonstrates promising results, achieving an accuracy of 90% for six emotion classes (happy, sad, fear, pain, anger, and disgust) and 96.39% for binary classification (happy and sad). The significance of FacialNet is judged by extensive experiments conducted against various machine learning and deep learning models, as well as state-of-the-art previous research works in FER. The significance of FacialNet is further validated using a cross-validation technique, ensuring reliable performance across different data splits. The findings highlight the effectiveness of leveraging UNet image segmentation and EfficientNetB4 transfer learning for accurate and efficient human facial emotion recognition, offering promising avenues for real-world applications in emotion-aware systems and effective computing platforms. Experimental findings reveal that the proposed approach performs substantially better than existing works with an improved accuracy of 96.39% compared to existing 94.26%.
facial emotion recognitionmental health assessmentEfficientNet-B4transfer learning
In the realm of medical imaging, the early detection of kidney issues, particularly renal cell hydronephrosis, holds immense importance. Traditionally, the identification of such conditions within ultrasound images has relied on manual analysis, a labor-intensive and error-prone process. However, in recent years, the emergence of deep learning-based algorithms has paved the way for automation in this domain. This study aims to harness the power of deep learning models to autonomously detect renal cell hydronephrosis in ultrasound images taken in close proximity to the kidneys. State-of-the-art architectures, including VGG16, ResNet50, InceptionV3, and the innovative Novel DCNN, were put to the test and subjected to rigorous comparisons. The performance of each model was meticulously evaluated, employing metrics such as F1 score, accuracy, precision, and recall. The results paint a compelling picture. The Novel DCNN model outshines its peers, boasting an impressive accuracy rate of 99.8%. In the same arena, InceptionV3 achieved a notable 90% accuracy, ResNet50 secured 89%, and VGG16 reached 85%. These outcomes underscore the Novel DCNN's prowess in the realm of renal cell hydronephrosis detection within ultrasound images. Moreover, this study offers a detailed view of each model's performance through confusion matrices, shedding light on their abilities to categorize true positives, true negatives, false positives, and false negatives. In this regard, the Novel DCNN model exhibits remarkable proficiency, minimizing both false positives and false negatives. In conclusion, this research underscores the Novel DCNN model's supremacy in automating the detection of renal cell hydronephrosis in ultrasound images. With its exceptional accuracy and minimal error rates, this model stands as a promising tool for healthcare professionals, facilitating early-stage diagnosis and treatment. Furthermore, the model's convergence rate and accuracy hold potential for enhancement through further exploration, including testing on larger and more diverse datasets and investigating diverse optimization strategies.
Internet of Things (IoT) sensor networks are connected systems of physical devices set with actuators, sensors, and communication abilities, allowing them to gather, spread, and exchange information with centralized methods. These networks are essential in numerous businesses, such as healthcare, manufacturing, agriculture, and smart cities, as they deliver real-time observation, data-driven insights, and automation. Threat recognition in IoT sensor networks is a vital feature of safeguarding the protection and consistency of interconnected systems in the IoT. As IoT sensor networks endure to increase across various industries, the vulnerability to malicious actions and cyber-attacks increases. Threat recognition utilizing deep learning (DL) leverages neural networks to examine complex patterns and anomalies in data, permitting the identification of potential safety threats. DL techniques like convolutional neural networks (CNNs) or recurrent neural networks (RNNs) excel at learning complex representations of data and feature extraction, making them suitable for identifying sophisticated attacks in different fields, including cybersecurity. This research develops a Hybrid Sine-Cosine Chimp Optimization Feature Selection with a Deep Learning (HSCCOFS-DL) approach for Threat Recognition in IoT Sensor Networks. The foremost aim of the HSCCOFS-DL system lies in the automated detection of threats using DL models. To accomplish this, the HSCCOFS-DL approach undergoes a data normalization process. Besides, the selection of features can be performed using the HSCCO algorithm. Meanwhile, the symmetrical autoencoder (SAE) technique effectively classifies threats. Finally, the sparrow search algorithm (SSA) can be applied to the selection of the hyperparameter of the SAE system. The experimental assessment of the HSCCOFS-DL technique takes place on a benchmark dataset. The simulation results indicated that the HSCCOFS-DL approach attains enhanced performance over other methods.
Osteosarcoma is the most normal kind of cancer that arises in bones, which appears on the surface to resemble earlier types of bone cells that assist in forging new bone tissues, but the tissue in osteosarcoma is weaker and softer than normal bone tissue. The usage of automated techniques for the detection of osteosarcoma has the potential to mitigate the obligations and burdens confronted by pathologists owing to its abundant quantity of cases. Artificial intelligence (AI) has an emerging progress in diagnostic pathology. In recent years, numerous studies using deep learning (DL) techniques to histopathological images (HI) have been published. While several studies claim higher accuracy, they might lack generalization and fall into the pitfall of overfitting owing to the wide range of HI. The study objective is to enhance the diagnosis and detection of osteosarcoma by employing computer-assisted detection (CAD) and diagnoses (CADx). Technique like convolutional neural networks (CNN) make better prognoses for patient conditions and considerably reduce the surgeon’s workload. CNN needs to be trained on the massive quantity of data to accomplish a remarkable performance. Therefore, the study presents a novel Group Teaching Optimization Algorithm with Deep Learning-Driven Osteosarcoma Detection on Histopathological Images (GTOADL-ODHI) technique. The purpose of the GTOADL-ODHI technique is to examine the HIs for the detection and classification of osteosarcoma. To accomplish this, the GTOADL-ODHI algorithm applies the Gaussian filtering (GF) method for image pre-processed to become rid of the noise. Besides, the capsule network (CapsNet) model is utilized for the extractor of the feature vector. Furthermore, the hyperparameter selection of the CapsNet approach takes place using the GTOA. Finally, the self-attention bidirectional long short-term memory (SA-BiLSTM) model can be employed for osteosarcoma recognition and classification. The widespread experimental analysis of the GTOADL-ODHI method is tested on the benchmark datasets. The simulation validation reported the optimum solution of the GTOADL-ODHI algorithm related to existing systems concerning distinct aspects.
Cervical cancer is one of the deadly diseases that affects women, which requires periodic examinations to identify and treat any cancerous tumors at a preliminary stage. The most prevalent examination tool for cervical cancer prompt identification is the cervical smear (Pap smear) testing; however, due to human negligence, this examination method has an elevated probability of negative findings. Cervical cancer classification using machine learning (ML) and deep learning (DL) has been extensively studied to enhance the conventional diagnostic process. Robust classification results were achieved through the pre-segmented imagery in most current investigations. Conversely, cellular grouping makes reliable cervical cellular segmentation difficult. Additionally, the deep learning methods used in the existing works perform poorly on a multiclass classification when the data distribution is skewed, which is common in the cervical cancer dataset. To mitigate these restrictions in cervical cancer research, this proposed work uses a combination of four different deep-learning methods in various phases of this research. The proposed work is segregated into five phases: pre-processing, data augmentation, segmentation, feature extraction, and classification. Contrast maximization is performed in the pre-processing phase, and the images are augmented using Multi-modal Generative Adversarial Networks (m-GAN) in the second phase. In the third phase, cervical cancer images are segmented using the Seg-UNet model, which is forwarded to the feature extraction phase that employs denoising autoencoders. Finally, the classification is implemented using the Dense CapsNet model and applied to the SIPaKMeD dataset to categorize between normal, abnormal, and benign classes. The proposed system achieves an accuracy of 99.65%, which is higher than the other works in the literature.
cervical cancer classificationPap smeardenoising autoencoderdata augmentation