The YODO algorithm: An efficient computational framework for sensitivity analysis in Bayesian networks

Sensitivity analysis measures the influence of a Bayesian network's parameters on a quantity of interest defined by the network, such as the probability of a variable taking a specific value. In the literature, this influence is often measured by computing the partial derivative with respect to the network parameters. However, this can become computationally expensive in large networks with thousands of parameters. We propose an algorithm combining automatic differentiation and exact inference to calculate the sensitivity measures in a single pass efficiently. It first marginalizes the whole network once, using e.g. variable elimination, and then backpropagates this operation to obtain the gradient with respect to all input parameters. Our method can be used for one-way and multi-way sensitivity analysis and the derivation of admissible regions. Simulation studies highlight the efficiency of our algorithm by scaling it to massive networks with up to 100,000 parameters and investigate the feasibility of generic multi-way analyses. Our routines are also showcased over two medium-sized Bayesian networks: the first modeling the country risks of a humanitarian crisis, the second studying the relationship between the use of technology and the psychological effects of forced social isolation during the COVID-19 pandemic. An implementation of the methods using the popular machine learning library PyTorch is freely available.

Detection of Covid-19 Through the Analysis of Radiographic Images of the Chest using Convolutional Neural Networks

There are different ways to detect Covid-19, which have emerged so far giving an effective response in detecting the disease, the PCR test is a reliable diagnostic method, which requires a well-equipped laboratory to obtain results, which can take hours or days. Another detection technique for this disease is by analyzing the chest image;This technique is used as a diagnostic tool in emergency areas in health centers, because it can reveal characteristics related to lung involvement. For this reason, it is important to develop an automatic detection system, as an alternative diagnosis option for Covid-19. Deep Learning techniques can help detect the SARS-CoV-2 virus by analyzing chest radiographic images. Thanks to the high availability of the datasets available, and using convolutional neural networks, the analysis is carried out by classifying images. In this research, two CNN models were created whose outputs are normal or covid19, the same ones that were trained with two datasets from public research repositories. The performance of the models trained in Pytorch were compared with the models trained in Keras under similar conditions of parameters and hyperparameters, obtaining a higher performance with Pytorch however since the two types of models have learned adequately with an accuracy that is above the 90% recommended the use of both models. © 2022 Latin American and Caribbean Consortium of Engineering Institutions. All rights reserved.

Pressure Prediction System in Lung Circuit Using Deep Learning

A massive number of patients infected with SARS-CoV2 and Delta variant of COVID-19 have generated acute respiratory distress syndrome (ARDS) which needs intensive care, which includes mechanical ventilation. But due to the huge no of patients, the workload and stress on healthcare infrastructure and related personnel have grown exponentially. This has resulted in huge demand for innovation in the field of automated health care which can help reduce the stress on the current healthcare infrastructure. This work gives a solution for the issue of pressure prediction in mechanical ventilation. The algorithm suggested by the researchers tries to predict the pressure in the respiratory circuit for various lung conditions. Prediction of pressure in the lungs is a type of sequence prediction problem. Long short-term memory (LSTM) is the most efficient solution to the sequence prediction problem. Due to its ability to selectively remember patterns over the long term, LSTM has an edge over normal RNN. RNN is good for short-term patterns but for sequence prediction problems, LSTM is preferred. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

CoV-TI-Net: Transferred Initialization with Modified End Layer for COVID-19 Diagnosis

This paper proposes transferred initialization with modified fully connected layers for COVID-19 diagnosis. Convolutional neural networks (CNN) achieved a remarkable result in image classification. However, training a high-performing model is a very complicated and time-consuming process because of the complexity of image recognition applications. On the other hand, transfer learning is a relatively new learning method that has been employed in many sectors to achieve good performance with fewer computations. In this research, the PyTorch pre-trained models (VGG19_bn and WideResNet -101) are applied in the MNIST dataset for the first time as initialization and with modified fully connected layers. The employed PyTorch pre-trained models were previously trained in ImageNet. The proposed model is developed and verified in the Kaggle notebook, and it reached the outstanding accuracy of 99.77% without taking a huge computational time during the training process of the network. We also applied the same methodology to the SIIM-FISABIO-RSNA COVID-19 Detection dataset and achieved 80.01% accuracy. In contrast, the previous methods need a huge compactional time during the training process to reach a high-performing model. Codes are available at the following link: github.com/dipuk0506/Spina1Net © 2022 IEEE.

Cloud-based intelligent monitoring system to implement mask violation detection and alert simulation

The importance of wearing a mask in public places came to light when the COVID-19 pandemic has started due to the coronavirus. To strictly control the spread of the virus, wearing a mask is mandatory to avoid getting the virus through others or spreading the virus to others if we are carrying it. Since it’s not possible to check each individual in public places whether he/she is wearing a mask, this paper proposed a face mask detection using Deep Learning (DL) and Convolutional Neural Network (CNN) techniques. A cloud-based approach that adopted DL is used to identify the persons violating the rules. The dataset used in the work is collected from various studies, such as Prajnasb/observations and Kaggle’s Face Mask Detection Dataset that contains images of people wearing and not wearing masks. The faces in the images will be detected and cropped with the help of a trained face detector which will be used for checking whether the face in the image is wearing a mask or not. Face mask detection is done with the help of CNN. The input image is fed into the CNN and the output is binary format, whether person wearing or not wearing a mask. The work uses Max Pooling and Average Pooling layers of CNN. The outcome of the work shows that the proposed method achieves 98 % of accuracy using Max Pooling which is better than the currently available works. © Komal Venugopal V., Lalith M., Arun Kumar T., Jayashree J., Vijayashre J., 2022.

Exploring Classification Models for COVID-19 Novel Coronavirus Disease

Coronavirus disease (COVID-19) is defined as a disease caused by severe acute respiratory syndrome coronavirus (SARS-CoV-2). Coronavirus has been declared a global pandemic in March 2020 by World Health Organization (WHO). The spread of coronavirus can be limited by early detection of the disease, for which RT-PCR and imaging studies are being used. The chest x-rays taken upon the arrival of the patient in the hospital can be used as the input source for early detection of disease with machine and deep learning algorithms. Even though, this is the most regular and supreme imaging modality, chest radiography is question to notable intra-observer variability and has almost minor sensitivity for major clinical findings. With advances in deep learning, convolutional neural networks (CNNs) not only improved chest radiograph evaluation but are also capable of staging radiologist-level performance. In this paper, we are applying CNN with PyTorch to train ResNet18 model as PyTorch is a lower-level application programming interface concentrated on direct work with the use of array expressions. This model implementation will be beneficial in rural areas where RT-PCR test results are delayed due to the geographical location, but portable chest x-ray machines are already installed. Here, we have collated different deep learning-based classification models at hand for identification of novel coronavirus. The results are present in tabular form. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

CNN supported automated recognition of Covid-19 infection in chest X-ray images.

Automatic recognition of lung system is use to identify normal and covid infected lungs from chest X-ray images of the people. In the year 2020, the coronavirus forcefully pushed the entire world into a freakish situation, the foremost challenge is to diagnosis the coronavirus. We have got standard diagnosis test called PCR test which is complex and costlier to check the patient's sample at initial stage. Keeping this in mind, we developed a work to recognize the chest X-ray image automatically and label it as Covid or normal lungs. For this work, we collected the dataset from open-source data repository and then pre-process each X-ray images from each category such as covid X-ray images and non-covid X-ray images using various techniques such as filtering, edge detection, segmentation, etc., and then the pre-processed X-ray images are trained using CNN-Resnet18 network. Using PyTorch python package, the resnet-18 network layer is created which gives more accuracy than any other algorithm. From the acquired knowledge the model is correctly classifies the testing X-ray images. Then the performance of the model is calculated and analyzed with various algorithms and hence gives that the resnet-18 network improves our model performance in terms of specificity and sensitivity with more than 90%.

COVID-19 CT Image Segmentation

COVID-19 was first identified in Wuhan, China. This virus is spreading worldwide, and to date, the number of new infections and their variants is still increasing in many countries. Early detection of this virus is critical to identify whether the patient is infected with COVID-19 or not. So far, RT-PCR is known as the most common method for COVID-19 detection. But compared with lung CT scan, lung CT scan has higher sensitivity, and it is easy to use in COVID-19 infection screening. One of the many steps that are needed in COVID-19 screening is the lung segmentation process. Many segmentation models have been developed by many researchers. And, through this paper, we presented the result of our exploration to the nine segmentation models PyTorch (Unet, Unet++, Manet, Linknet, FPN, PSPNet, PAN, DeepLabV3, and DeepLabV+) and compared each performance and see the result. Based on the experiments, we can conclude that Unet++ performs better than other models. It might be because U-Net++ has a robust network architecture, and it is initially designed for medical image segmentation. U-Net++ is also the largest model that we implemented, which might infer that it has more flexibility because it has more parameters to adjust. It could be the reason for the model to have better performance. © 2021 IEEE.

Detecting Presence of COVID-19 with ResNet-18 using PyTorch

COVID-19 virus can be detected with the help of medical images such as X-Ray and CT Scan of human lungs. The unavailability of proper resources might result in the delay of future proceedings. Henceforth, this paper analyzed and comprehended the medical images for COVID-19 lungs and tried to figure out the practical application of that procedure with the overall ecosystem. The whole paper is split into major categories such as: analyzing medical images, classifying and detecting the presence of COVID-19, and building the ResNet-18 model. The present paper creates a base for these terminologies and presents the implementation of a Classification Model on the Kaggle dataset for the X-Ray images. The current work serves the purpose of identification and detection of the Coronavirus, Pneumonia, and normal lungs with the help of ResNet-18. The model was implemented with the Transfer Learning technique. In brief, the work addresses the identification or detection of the COVID-19 reports and differentiates them from reports having symptoms synonymous with the task at hand. The accuracy obtained was 97.78% with 96.33% average sensitivity rate and 98.21% average specificity rate. The conclusion of this report ideally focuses on delineating the result coherently. ©2021 IEEE

Transfer learning approaches to recognize X-ray Covid-19 images

Covid 19, caused from coronavirus SAR-CoV-2, is currently a dangerous threat to human beings. The rapid development of the Covid 19 pandemic forced all countries to develop fast and reliable methods to detect the coronavirus SAR-CoV-2. Transfer learning with medical images is a suitable such detecting method. Transfer learning, a deep learning technique, has special abilities such as speed of training, fewer requirements of training data set size and reduced demand of expert domain knowledge. Diagnosing Covid 19 using medical images is also considered by some to be more reliable than using traditional laboratory methods. This paper proposes transfer learning methods combined with medical images to detect Covid 19. Using a Covid 19 X-ray data set from Kaggle, this research considers viral pneumonia as a separate class, increasing the performance since viral pneumonia is often wrongly classified as Covid 19, even by radiologists. This paper uses specialized metrics to deal with the imbalanced nature of the data and visualises results using Local Interpretable Model-agnostic Explanations to indicate areas of images associated with Covid 19. The ResNet family of CNNs performed well, with ResNet 34 performing better than the 18 and 50 layer versions. Inception and DenseNet also have good classification performance. © 2021 IEEE.

vid-SAMGRAH: A PyTorch framework for multi-latent space reinforcement learning driven video summarization in ultrasound imaging.

The COVID-19 pandemic has accelerated the need for automatic triaging and summarization of ultrasound videos for fast access to pathologically relevant information in the Emergency Department and lowering resource requirements for telemedicine. In this work, a PyTorch based unsupervised reinforcement learning methodology which incorporates multi feature fusion to output classification labels, segmentation maps and summary videos for lung ultrasound is presented. The use of unsupervised training eliminates tedious manual labeling of key-frames by clinicians opening new frontiers in scalability in training using unlabeled or weakly labeled data. Our approach was benchmarked against expert clinicians from different geographies displaying superior Precision and F1 scores (over 80% and 44%).