Unsupervised Deep Learning based Variational Autoencoder Model for COVID-19 Diagnosis and Classification

Mansour, Romany F.; Escorcia‐Gutierrez, José; Gamarra, Margarita; Gupta, Deepak; Castillo, Oscar; Kumar, Sachin

doi:10.1016/j.patrec.2021.08.018

Cited by 62 publications

(38 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In terms of directions for future research, further work could incorporate more types of data, such as medical images and quantitative features, and construct directed comorbidity networks [ 69 ] or patient networks [ 70 ] to generate domain knowledge, then extract features from the networks and identify the knowledge embedded in the networks through machine learning algorithms [ 71 , 72 ], so as to effectively predict the health risk of patients.…”

Section: Discussionmentioning

confidence: 99%

Phenotypic Disease Network Analysis to Identify Comorbidity Patterns in Hospitalized Patients with Ischemic Heart Disease Using Large-Scale Administrative Data

et al. 2022

View full text Add to dashboard Cite

Ischemic heart disease (IHD) exhibits elevated comorbidity. However, few studies have systematically analyzed the comorbid status of IHD patients with respect to the entire spectrum of chronic diseases. This study applied network analysis to provide a complete picture of physical and mental comorbidities in hospitalized patients with IHD using large-scale administrative data. Hospital discharge records from a provincial healthcare database of IHD inpatients (n = 1,035,338) and one-to-one matched controls were included in this retrospective analysis. We constructed the phenotypic disease networks in IHD and control patients and further assessed differences in comorbidity patterns. The community detection method was applied to cluster diagnoses within the comorbidity network. Age- and sex-specific patterns of IHD comorbidities were also analyzed. IHD inpatients showed 50% larger comorbid burden when compared to controls. The IHD comorbidity network consisted of 1941 significant associations between 71 chronic conditions. Notably, the more densely connected comorbidities in IHD patients were not within the highly prevalent ones but the rarely prevalent ones. Two highly interlinked communities were detected in the IHD comorbidity network, where one included hypertension with heart and multi-organ failures, and another included cerebrovascular diseases, cerebrovascular risk factors and anxiety. Males exhibited higher comorbid burden than females, and thus more complex comorbidity relationships were found in males. Sex-specific disease pairs were detected, e.g., 106 and 30 disease pairs separately dominated in males and females. Aging accounts for the majority of comorbid burden, and the complexity of the comorbidity network increased with age. The network-based approach improves our understanding of IHD-related comorbidities and enhances the integrated management of patients with IHD.

show abstract

Section: Discussionmentioning

confidence: 99%

Phenotypic Disease Network Analysis to Identify Comorbidity Patterns in Hospitalized Patients with Ischemic Heart Disease Using Large-Scale Administrative Data

et al. 2022

View full text Add to dashboard Cite

show abstract

“…DL techniques used in COVID-19 have also been categorized into seven main distinct categories as long short-term memory networks (LSTM), self-organizing maps (SOMs), conventional neural networks (CNNs), generative adversarial networks (GANs), recurrent neural networks (RNNs), autoencoders, and hybrid approaches [ 33 , 34 ]. The research work in [ 35 ] introduces a novel unsupervised DL-based variational autoencoder (UDL-VAE) model for COVID-19 detection and classification. Autoencoders are used for feature selection to uncover existing nonlinear relationships between features.…”

Section: Discussionmentioning

confidence: 99%

Classification of COVID-19 from tuberculosis and pneumonia using deep learning techniques

Venkataramana¹,

Prasad²,

Saraswathi³

et al. 2022

Med Biol Eng Comput

View full text Add to dashboard Cite

Deep learning provides the healthcare industry with the ability to analyse data at exceptional speeds without compromising on accuracy. These techniques are applicable to healthcare domain for accurate and timely prediction. Convolutional neural network is a class of deep learning methods which has become dominant in various computer vision tasks and is attracting interest across a variety of domains, including radiology. Lung diseases such as tuberculosis (TB), bacterial and viral pneumonias, and COVID-19 are not predicted accurately due to availability of very few samples for either of the lung diseases. The disease could be easily diagnosed using X-ray or CT scan images. But the number of images available for each of the disease is not as equally as other resulting in imbalance nature of input data. Conventional supervised machine learning methods do not achieve higher accuracy when trained using a lesser amount of COVID-19 data samples. Image data augmentation is a technique that can be used to artificially expand the size of a training dataset by creating modified versions of images in the dataset. Data augmentation helped reduce overfitting when training a deep neural network. The SMOTE (Synthetic Minority Oversampling Technique) algorithm is used for the purpose of balancing the classes. The novelty in this research work is to apply combined data augmentation and class balance techniques before classification of tuberculosis, pneumonia, and COVID-19. The classification accuracy obtained with the proposed multi-level classification after training the model is recorded as 97.4% for TB and pneumonia and 88% for bacterial, viral, and COVID-19 classifications. The proposed multi-level classification method produced is ~8 to ~10% improvement in classification accuracy when compared with the existing methods in this area of research. The results reveal the fact that the proposed system is scalable to growing medical data and classifies lung diseases and its sub-types in less time with higher accuracy. Graphical Abstract

show abstract

“…Hence, the support tensor selected by the fuzzy support tensor machine is not equivalent to that selected by the support tensor machine. To address this problem, fuzzy support tensor machines introduce the concept of a fuzzy affiliation function [ 17 ]. Each training sample is assigned a corresponding fuzzy affiliation according to its influence on the prediction result, with smaller affiliations for incorrect or biased samples and larger affiliations for correct samples, by which the problem that traditional support tensor machines are easily misled by isolated points is solved and the noise immunity of the model is improved.…”

Section: Fuzzy Support Tensor Machine Adaptive Image Classification F...mentioning

confidence: 99%

Fuzzy Support Tensor Product Adaptive Image Classification for the Internet of Things

Shi

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Computer vision is one of the hottest research directions in artificial intelligence at present, and its research goal is to give computers the ability to perceive and cognize their surroundings from a single image. Image recognition is an important research direction in the field of computer vision, which has important research significance and application value in industrial applications such as video surveillance, biometric identification, unmanned vehicles, human-computer interaction, and medical image recognition. In this article, we propose an end-to-end, pixel-to-pixel IoT-oriented fuzzy support tensor product adaptive image classification method. Considering the problem that traditional support tensor product classification methods are difficult to directly produce pixel-to-pixel classification results, the research is based on the idea of inverse convolution network design, which directly outputs dense pixel-by-pixel classification results for images to be classified of arbitrary size to achieve true end-to-end and pixel-to-pixel high-score image classification and improve the efficiency of support tensor product models for high-score image classification on a pixel-by-pixel basis. Moreover, considering that network supervised classification training using deep learning requires a large amount of labeled data as true values and obtaining a large number of labeled data sources is a difficult problem in the field of image classification, this article proposes using a large amount of unlabeled high-resolution remote sensing images for learning generic structured features through unsupervised to assist the labeled high-resolution remote sensing images for better-supervised feature extraction and classification training. By finding a balance between generic structural feature learning of images and differentiated feature learning related to the target class, the dependence of supervised classification on the number of labeled samples is reduced, and the network robustness of the support tensor product algorithm is improved under a small number of labeled training samples.

show abstract

Unsupervised Deep Learning based Variational Autoencoder Model for COVID-19 Diagnosis and Classification

Cited by 62 publications

References 35 publications

Phenotypic Disease Network Analysis to Identify Comorbidity Patterns in Hospitalized Patients with Ischemic Heart Disease Using Large-Scale Administrative Data

Phenotypic Disease Network Analysis to Identify Comorbidity Patterns in Hospitalized Patients with Ischemic Heart Disease Using Large-Scale Administrative Data

Classification of COVID-19 from tuberculosis and pneumonia using deep learning techniques

Fuzzy Support Tensor Product Adaptive Image Classification for the Internet of Things

Contact Info

Product

Resources

About