Multiclass Convolution Neural Network for Classification of COVID-19 CT Images

Ching, Serena Low Woan; Lai, Khin Wee; Chuah, Joon Huang; Hasikin‬, Khairunnisa; Khalil, Azira; Qian, Pengjiang; Xia, Kaijian; Jiang, Yizhang; Zhang, Yuanpeng; Dhanalakshmi, Samiappan

doi:10.1155/2022/9167707

Cited by 10 publications

(3 citation statements)

References 10 publications

(4 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the best Resnet101 model still performed as well as the best machine-learning model. [23][24][25][26][27] The optimization scheme of deep learning during image training cannot be directly used in the multi-modal decision fusion of clinical and image data. Data enhancement is a more suitable model optimization scheme.…”

Section: Discussionmentioning

confidence: 99%

A Deep Learning Model for the Diagnosis and Discrimination of Gram-Positive and Gram-Negative Bacterial Pneumonia for Children Using Chest Radiography Images and Clinical Information

Wen¹,

Xu²,

Cai³

et al. 2023

IDR

View full text Add to dashboard Cite

Purpose This study aimed to develop a deep learning model based on chest radiography (CXR) images and clinical data to accurately classify gram-positive and gram-negative bacterial pneumonia in children to guide the use of antibiotics. Methods We retrospectively collected CXR images along with clinical information for gram-positive (n=447) and gram-negative (n=395) bacterial pneumonia in children from January 1, 2016, to June 30, 2021. Four types of machine learning models based on clinical data and six types of deep learning algorithm models based on image data were constructed, and multi-modal decision fusion was performed. Results In the machine learning models, CatBoost, which only used clinical data, had the best performance; its area under the receiver operating characteristic curve (AUC) was significantly higher than that of the other models (P<0.05). The incorporation of clinical information improved the performance of deep learning models that relied solely on image-based classification. Consequently, AUC and F1 increased by 5.6% and 10.2% on average, respectively. The best quality was achieved with ResNet101 (model accuracy: 0.75, recall rate: 0.84, AUC: 0.803, F1: 0.782). Conclusion Our study established a pediatric bacterial pneumonia model that utilizes CXR and clinical data to accurately classify cases of gram-negative and gram-positive bacterial pneumonia. The results confirmed that the addition of image data to the convolutional neural network model significantly improved its performance. While the CatBoost-based classifier had greater advantages owing to a smaller dataset, the quality of the Resnet101 model trained using multi-modal data was comparable to that of the CatBoost model, even with a limited number of samples.

show abstract

Section: Discussionmentioning

confidence: 99%

A Deep Learning Model for the Diagnosis and Discrimination of Gram-Positive and Gram-Negative Bacterial Pneumonia for Children Using Chest Radiography Images and Clinical Information

Wen¹,

Xu²,

Cai³

et al. 2023

IDR

View full text Add to dashboard Cite

show abstract

“…AI is crucial because it is one of the foundational technologies in the age of data and digitalization, especially in IR4.0. AI is frequently employed in the field and research of medical and environmental sustainability research ( Jamaludin et al, 2022 ; Mammoottil et al, 2022 ; Teoh et al, 2022 ; Woan Ching et al, 2022 ; Wong et al, 2022a ; Wong et al, 2022b ; Yeoh et al, 2021 ). As smart cities emerge, this article proposed the viability of AI in providing technological solutions to urban environmental problems, particularly the forecasting and control of urban air quality.…”

Section: Literature Reviewsmentioning

confidence: 99%

Artificial intelligence-assisted air quality monitoring for smart city management

Neo

Hasikin‬

Lai

et al. 2023

PeerJ Computer Science

Self Cite

View full text Add to dashboard Cite

Background The environment has been significantly impacted by rapid urbanization, leading to a need for changes in climate change and pollution indicators. The 4IR offers a potential solution to efficiently manage these impacts. Smart city ecosystems can provide well-designed, sustainable, and safe cities that enable holistic climate change and global warming solutions through various community-centred initiatives. These include smart planning techniques, smart environment monitoring, and smart governance. An air quality intelligence platform, which operates as a complete measurement site for monitoring and governing air quality, has shown promising results in providing actionable insights. This article aims to highlight the potential of machine learning models in predicting air quality, providing data-driven strategic and sustainable solutions for smart cities. Methods This study proposed an end-to-end air quality predictive model for smart city applications, utilizing four machine learning techniques and two deep learning techniques. These include Ada Boost, SVR, RF, KNN, MLP regressor and LSTM. The study was conducted in four different urban cities in Selangor, Malaysia, including Petaling Jaya, Banting, Klang, and Shah Alam. The model considered the air quality data of various pollution markers such as PM2.5, PM10, O3, and CO. Additionally, meteorological data including wind speed and wind direction were also considered, and their interactions with the pollutant markers were quantified. The study aimed to determine the correlation variance of the dependent variable in predicting air pollution and proposed a feature optimization process to reduce dimensionality and remove irrelevant features to enhance the prediction of PM2.5, improving the existing LSTM model. The study estimates the concentration of pollutants in the air based on training and highlights the contribution of feature optimization in air quality predictions through feature dimension reductions. Results In this section, the results of predicting the concentration of pollutants (PM2.5, PM10, O3, and CO) in the air are presented in R2 and RMSE. In predicting the PM10 and PM2.5concentration, LSTM performed the best overall high R2values in the four study areas with the R2 values of 0.998, 0.995, 0.918, and 0.993 in Banting, Petaling, Klang and Shah Alam stations, respectively. The study indicated that among the studied pollution markers, PM2.5,PM10, NO2, wind speed and humidity are the most important elements to monitor. By reducing the number of features used in the model the proposed feature optimization process can make the model more interpretable and provide insights into the most critical factor affecting air quality. Findings from this study can aid policymakers in understanding the underlying causes of air pollution and develop more effective smart strategies for reducing pollution levels.

show abstract

“…The suggested method was then tested on two open X-ray COVID-19 data sets, and it showed great performance and low computing complexity. Serena Low Woan Ching, S.L., et al in[29], Proposed the concept of transfer learning to use a deterministic algorithm in all binary classi cation models to evaluate CNN performance and applied the proposed model to 746 CT scans images of people with and without COVID-19 for training, validation, and testing. They did and in this model, they used different augmentation techniques to increase the number of data sets except for testing images, then retrained the images using CNN to obtain a binary class.…”

mentioning

confidence: 99%

A robust innovative pipeline-based machine learning framework for predicting COVID-19 in Mexican patients

Farnoosh,

Abnoosian

2024

Int J Syst Assur Eng Manag

View full text Add to dashboard Cite

One of the infectious diseases that were rst identi ed in late 2019 in Wuhan, China, is COVID-19, which has killed many people around the world. Understanding the available COVID-19 data sets can help healthcare professionals identify some cases at an early stage. This paper proposes an innovative pipeline-based framework to predict death or survival from the COVID-19 disease on the Covid-19MPD dataset. Preprocessing, in the proposed framework, is an important part of achieving a high-quality result. Various machine learning models with optimal hyper parameters are implemented in the proposed framework. Using the same experimental conditions and data set, multiple experiments were performed with different combinations of preprocessing and models to maximize the AUC for predicting COVID-19 disease. Because the dimensions of the data were relatively large, and however, must nd features that have an impact on death or survival from COVID-19. Feature dimensions' reduction methods such as PCA, ICA, and feature selection methods such as maximum relevance minimum redundancy, and permutation feature importance were used. Finding the feathers that have a great impact on the death or survival of the patient can help experts in the treatment of this disease and be able to control and ultimately treat this disease more e ciently. After various experiments of the proposed framework with standardized data and AUC with four components with the k-nearest neighbor algorithm, compared to other experiments, it was able to attain the optimal result in terms of AUC (100%).Because of the optimal nature of this framework in predicting COVID-19, it can be used in the smart systems of medical centers.

show abstract

Multiclass Convolution Neural Network for Classification of COVID-19 CT Images

Cited by 10 publications

References 10 publications

A Deep Learning Model for the Diagnosis and Discrimination of Gram-Positive and Gram-Negative Bacterial Pneumonia for Children Using Chest Radiography Images and Clinical Information

A Deep Learning Model for the Diagnosis and Discrimination of Gram-Positive and Gram-Negative Bacterial Pneumonia for Children Using Chest Radiography Images and Clinical Information

Artificial intelligence-assisted air quality monitoring for smart city management

A robust innovative pipeline-based machine learning framework for predicting COVID-19 in Mexican patients

Contact Info

Product

Resources

About