COVID-19 diagnosis on CT images with Bayes optimization-based deep neural networks and machine learning algorithms

Canayaz, Murat; Şehrïbanoğlu, Sanem; Ozdag, Recep O.; Demir, Murat

doi:10.1007/s00521-022-07052-4

Cited by 22 publications

(15 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep neural networks have demonstrated outstanding performance in a wide range of machine learning tasks, including classification and clustering [ 39 , 40 ], for real-life applications of soft computing techniques in different fields [ 41 , 42 ]. Developing an appropriate architecture for a Deep Convolutional Neural Network (DCNN) has remained an extremely intriguing, demanding, and topical issue to date.…”

Section: Discussionmentioning

confidence: 99%

Topology optimization search of deep convolution neural networks for CT and X-ray image classification

Louati

Bechikh

et al. 2022

BMC Med Imaging

View full text Add to dashboard Cite

Covid-19 is a disease that can lead to pneumonia, respiratory syndrome, septic shock, multiple organ failure, and death. This pandemic is viewed as a critical component of the fight against an enormous threat to the human population. Deep convolutional neural networks have recently proved their ability to perform well in classification and dimension reduction tasks. Selecting hyper-parameters is critical for these networks. This is because the search space expands exponentially in size as the number of layers increases. All existing approaches utilize a pre-trained or designed architecture as an input. None of them takes design and pruning into account throughout the process. In fact, there exists a convolutional topology for any architecture, and each block of a CNN corresponds to an optimization problem with a large search space. However, there are no guidelines for designing a specific architecture for a specific purpose; thus, such design is highly subjective and heavily reliant on data scientists’ knowledge and expertise. Motivated by this observation, we propose a topology optimization method for designing a convolutional neural network capable of classifying radiography images and detecting probable chest anomalies and infections, including COVID-19. Our method has been validated in a number of comparative studies against relevant state-of-the-art architectures.

show abstract

Section: Discussionmentioning

confidence: 99%

Topology optimization search of deep convolution neural networks for CT and X-ray image classification

Louati

Bechikh

et al. 2022

BMC Med Imaging

View full text Add to dashboard Cite

show abstract

“…and Bayesian optimization concepts. Recently, the maximum accuracy has reached 99.3% by (46). In contrast, the suggested framework obtained a high degree of accuracy, as shown in Table 12.…”

Section: 4mentioning

confidence: 96%

COVID-19 classification using chest X-ray images based on fusion-assisted deep Bayesian optimization and Grad-CAM visualization

Hamza

Khan

Wang

et al. 2022

Front. Public Health

View full text Add to dashboard Cite

The COVID-19 virus's rapid global spread has caused millions of illnesses and deaths. As a result, it has disastrous consequences for people's lives, public health, and the global economy. Clinical studies have revealed a link between the severity of COVID-19 cases and the amount of virus present in infected people's lungs. Imaging techniques such as computed tomography (CT) and chest x-rays can detect COVID-19 (CXR). Manual inspection of these images is a difficult process, so computerized techniques are widely used. Deep convolutional neural networks (DCNNs) are a type of machine learning that is frequently used in computer vision applications, particularly in medical imaging, to detect and classify infected regions. These techniques can assist medical personnel in the detection of patients with COVID-19. In this article, a Bayesian optimized DCNN and explainable AI-based framework is proposed for the classification of COVID-19 from the chest X-ray images. The proposed method starts with a multi-filter contrast enhancement technique that increases the visibility of the infected part. Two pre-trained deep models, namely, EfficientNet-B0 and MobileNet-V2, are fine-tuned according to the target classes and then trained by employing Bayesian optimization (BO). Through BO, hyperparameters have been selected instead of static initialization. Features are extracted from the trained model and fused using a slicing-based serial fusion approach. The fused features are classified using machine learning classifiers for the final classification. Moreover, visualization is performed using a Grad-CAM that highlights the infected part in the image. Three publically available COVID-19 datasets are used for the experimental process to obtain improved accuracies of 98.8, 97.9, and 99.4%, respectively.

show abstract

“…Since optimization algorithms are random and offer various ways in each execution, accordingly to the power of analysis, For each data set presented in table (4), the optimization algorithm was performed 30 times, and the results were recorded. Table (4) and figure (8) shows the Min, Max and average answers in the precision evaluation index for 30 independent executations of the proposed algorithm. The results show that in the precision evaluation index, the proposed method had the best diagnosis of Covid-19 disease in the D2 dataset with a precision of 0.99 and the worst diagnosis in the D3 dataset with 0.90%.…”

Section: ) Analysis Of Findingsmentioning

confidence: 99%

“…But the mass volume of patients brought restrictions on the use of such technology in some countries. Meanwhile, the use of medical imaging technology for patients is not without complications [7,8]. It should also be kept in mind that due to the infectious nature of the Covid-19 disease, medical imaging devices should be disinfected after each use [9].…”

Section: ( Introductionmentioning

confidence: 99%

Improving the accuracy of Covid-19 disease diagnosis with an improved fuzzy chaotic forest algorithm, optimal feature selection and decision tree

Motedayen

Yaghoobi

Kheirabadi

2023

Preprint

View full text Add to dashboard Cite

Covid-19 is a new viral disease that spread in 2019 and turned into a pandemic over time. Due to its unknown nature, this disease caused a lot of human and financial losses in the current world. Several approaches were proposed to diagnose and apply medical care; One of the approaches that were more welcomed according to the results was the methods based on artificial intelligence. In the methods of artificial intelligence, various methods such as image processing, machine learning, etc. are used. Considering that in pandemic diseases, the number of patients is high and medical imaging is not without complications; Therefore, the use of clinical data and data mining techniques can be a suitable method in this field. But it should be kept in mind that in using data mining approaches, the lack of proper selection of features can hurt the analysis. Feature selection can be defined as the process of identifying relevant features and removing irrelevant and repetitive features to observe a subset of features that describe the problem well and with minimal loss of efficiency, and its purpose is to optimally select a subset of features with minimal redundancy and the maximum resolution ability. Therefore, the data mining process should pay attention to feature selection. In this article, a new method based on feature selection was proposed to increase the precision of the diagnosis of covid-19 disease. In the proposed method, we have used the fuzzy-chaotic forest optimization algorithm to select features that are effective on the covid-19 disease. This article has used four data sets collected by researchers of other scientific articles to evaluate the proposed method of diagnosing the disease of covid-19. The results of the evaluation in the important indicators of machine learning (precision, accuracy, recall and F1) show that in Comparing with similar algorithms, the proposed method provides better results and by increasing the accuracy of diagnosis, it can better diagnose the disease of Covid-19 In such a way, it improves the precision of diagnosis by 2% and reduces the dimensions of the diagnosis problem by 46%.

show abstract

COVID-19 diagnosis on CT images with Bayes optimization-based deep neural networks and machine learning algorithms

Cited by 22 publications

References 49 publications

Topology optimization search of deep convolution neural networks for CT and X-ray image classification

Topology optimization search of deep convolution neural networks for CT and X-ray image classification

COVID-19 classification using chest X-ray images based on fusion-assisted deep Bayesian optimization and Grad-CAM visualization

Improving the accuracy of Covid-19 disease diagnosis with an improved fuzzy chaotic forest algorithm, optimal feature selection and decision tree

Contact Info

Product

Resources

About