Search

The world is facing the pandemic situation due to a beta corona virus named Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). The disease caused by this virus known as Corona Virus Disease 2019 (COVID-19) has affected the entire world. The current diagnosis methods are laboratory based and require specialized testing kits for performing the test. Therefore, to overcome the limitations of testing kits a diagnosis method from chest X-ray images is proposed in this paper. Chest X-ray images can be easily obtained by X-ray machines that are readily available at medical centres. The radiological examinations augmented with chest X-ray images is an effective way of disease diagnosis. The automated analysis of the chest X-ray images requires a highly efficient method for identifying COVID-19 from these images. Thus, a novel deep convolution neural network (CNN) optimized using Grasshopper Optimization Algorithm (GOA) is proposed. The deep learning model comprises depth wise separable convolutions that independently look at cross channel and spatial correlations. The optimization of deep learning models is a complex task due the multiple layers and their non-linearities. In image classification problems optimizers like Adam, SGD etc. get stuck in local minima. Thus, in this paper a metaheuristic optimization algorithm is used to optimize the network. Grasshoper Optimization Algorithm (GOA) is a metaheuristic algorithm that mimics the behaviour of grasshoppers for food search. This algorithm is a fast converging and is capable of exploration and exploitation of large search spaces. Maximum Probability Based Cross Entropy Loss (MPCE) loss function is used as it minimizes the back propogation error of cross entropy and improves the training. The experimental results show that the proposed method gives high classification accuracy. The interpretation of results is augmented with class activation maps. Grad-CAM visualization algorithm is used for class activation maps.

Brain diseases are a growing concern in healthcare, with an estimated 50 million people worldwide living with dementia and 15 million new cases each year. This research paper explores the significance of early identification and diagnosis in mitigating the impact of brain diseases on individuals and society at large. Moreover, the study delves into the current state of diagnostic practices, highlighting the limitations and emerging opportunities in the field. The paper concludes by advocating for increased research, improved access to advanced medical technologies, and enhanced training for healthcare professionals to address the growing burden of brain diseases effectively. [ABSTRACT FROM AUTHOR]

Lung abnormalities are among the significant contributors to morbidity and mortality worldwide. It induces symptoms like coughing, sneezing, fever, breathlessness, etc., which, if left untreated, may lead to death. In current clinical practice, chest X-ray (CXR) images are widely preferred to diagnose different lung abnormalities. However, the pathological tests are time-consuming, expensive and require domain experts. On the other hand, diagnosis through CXR images is manual and subject to inter-observer and intra-observer variability. The recent advancement in deep learning (DL) algorithms may be employed to address these challenges. However, the selection of correct algorithms along with finetuned parameters is challenging. In this study, we comprehensively compared the performance of two state-of-the-art DL algorithms, Resnet-50 and Efficient-B0. These two models are pervasively used in literature and have shown promising classification performance. The performance of the used algorithms is validated using the multi-centric dataset from Kaggle (having Covid-19, Normal, Pneumonia classes) and Mendeley chest X-ray dataset (having Normal, Pneumonia-Bacterial, Pneumonia-Viral, Covid-19 classes). Upon training the algorithms with a mini-batch size 32 and a maximum epoch of 40 using training data, we achieved 0.9807 and 0.9874 accuracy for Kaggle Dataset and Mendeley Dataset, respectively. Similarly, we achieved 0.9962 and 9.9978 for Kaggle dataset and Mendeley dataset for test data, respectively. From the result, it is evident that the EfficientNet-B0 model outperformed the multi-centric datasets. [ABSTRACT FROM AUTHOR]

The regular monitoring and accurate diagnosis of arrhythmia are critically important, leading to a reduction in mortality rate due to cardiovascular diseases (CVD) such as heart stroke or cardiac arrest. This paper proposes a novel convolutional neural network (CNN) model for arrhythmia classification. The proposed model offers the following improvements compared with traditional CNN models. Firstly, the multi-channel model can concatenate spectral and spatial feature maps. Secondly, the structural unit is composed of a depthwise separable convolution layer followed by activation and batch normalization layers. The structural unit offers effective utilization of network parameters. Also, the optimization of hyperparameters is done using Hyperopt library, based on Sequential Model-Based Global Optimization algorithm (SMBO). These improvements make the network more efficient and accurate for arrhythmia classification. The proposed model is evaluated using tenfold cross-validation following both subject-oriented inter-patient and class-oriented intra-patient evaluation protocols. Our model achieved 99.48% and 99.46% accuracy in VEB (ventricular ectopic beat) and SVEB (supraventricular ectopic beat) class classification, respectively. The model is compared with state-of-the-art models and has shown significant performance improvement. [ABSTRACT FROM AUTHOR]

In this research work, a new deep learning model named VGG-COVIDNet has been proposed which can classify COVID-19 cases from normal cases over X-Rays and CT scan images of lungs. Medical practitioners use the X-Rays and CT scan images of lungs to identify whether a person is infected from COVID or not. In present times, it is very important to give real time COVID prediction with high reliability of results. Deep learning models equipped with machine learning support have been found very influential in accurate prediction of COVID or Non-COVID cases in real time. However, there are some limitations associated with the performance of these model which are model size, achieving good balance of model size and accuracy, and making a single model fitting well for both X-Ray and CT Scan image datasets. Keeping in mind these performance constraints, this new model (VGG-COVIDNet) has been proposed for real time prediction of COVID cases with good balance of model size and accuracy working well for both type of datasets (CT Scan and X-Ray). In order to control model size, an improved version of VGG-16 architecture has been proposed which contains only 13 convolutional layers and 5 fully connected layers. Multiple dropout layers have been added in the proposed architecture which can drop some percentage of features and applies random transformations to decrease the model over-fitting issue. Keeping in mind the primary goal to increase the model accuracy the proposed model has been trained on different datasets with ReLU activation function which is one of the best non-linear activation functions. Four different capacity datasets with CT scan and X-Ray images have been used to validate the performance of proposed model. The proposed model gives an overall accuracy of more than 90% on both types of input datasets i.e. X-Ray and CT Scan. [ABSTRACT FROM AUTHOR]

Deep learning has become a topic of great concern in many domains and also in end-to-end image encryption. Traditional image encryption techniques employ rounds of diffusion and confusion to obtain an explicit trade-off between security and efficiency. With deep learning approach adequate solutions are obtained for current challenges in image encryption schemes such as efficiency, cryptographic strength, etc. In this paper, the latest trends in end-to-end encryption schemes based on deep learning are summarized. Firstly, the existing deep learning-based encryption systems are categorized into three categories: encryption with style transfer, Style transfer with enhanced diffusion properties, and Combining Deep Neural networks with chaotic systems. Each of these methodologies is discussed and relevant conclusions are made. Secondly, these methods are compared and analyzed for their achievements and drawbacks in terms of cryptographic properties of generated cipher images and quality of the recovered images. Third, the possibility of new cryptographic attacks are discussed such as Hidden Factors Leakage and Network Architecture Leakage as consequences of combination of deep learning approaches with an encryption system. Finally, conclusions are made based on comparison and analysis of deep learning approach in end-to-end encryption/decryption systems, providing basis for further research. [ABSTRACT FROM AUTHOR]

Chaos-based image encryption schemes are applied widely for their cryptographic properties. However, chaos and cryptographic relations remain a challenge. The chaotic systems are defined on the set of real numbers and then normalized to a small group of integers in the range 0–255, which affects the security of such cryptosystems. This paper proposes an image encryption system developed using deep learning to realize the secure and efficient transmission of medical images over an insecure network. The non-linearity introduced with deep learning makes the encryption system secure against plaintext attacks. Another limiting factor for applying deep learning in this area is the quality of the recovered image. The application of an appropriate loss function further improves the quality of the recovered image. The loss function employs the structure similarity index metric (SSIM) to train the encryption/decryption network to achieve the desired output. This loss function helped to generate cipher images similar to the target cipher images and recovered images similar to the originals concerning structure, luminance and contrast. The images recovered through the proposed decryption scheme were high-quality, which was further justified by their PSNR values. Security analysis and its results explain that the proposed model provides security against statistical and differential attacks. Comparative analysis justified the robustness of the proposed encryption system. [ABSTRACT FROM AUTHOR]