期刊名称：International Journal of Early Childhood Special Education
电子版ISSN：1308-5581
出版年度：2022
卷号：14
期号：5
页码：1460-1467
DOI：10.9756/INTJECSE/V14I5.146
语种：English
出版社：International Journal of Early Childhood Special Education
摘要：Convolutional neural networks (CNNs) in particular have achieved successful outcomes in the categorization and analysis of medical image data using artificial intelligence (AI) approaches. This research proposes a deep CNN architecture for the classification of chest X-ray images in the diagnosis of COVID-19.An efficient and precise CNN classification was difficult since there was no chest X-ray picture dataset of a size and quality that was enough.The dataset has been preprocessed in different stages using different techniques to achieve an effective training dataset for the proposed CNN model to achieve its best performance. To deal with these complexities, such as the availability of a very-small-sized, imbalanced dataset with image-quality issues, the preprocessing stages of the datasets performed in this study include dataset balancing, medical experts' image analysis, and data augmentation.Experimental findings revealed an overall accuracy of up to 99.5%, showing the proposed CNN model's strong suit in the current application domain.) Two different scenarios were used to evaluate the CNN model.In the first case, the model was tested using 100 X-ray pictures from the original, properly processed dataset, and it was 100% accurate.The model has been tested in the second scenario using an independent dataset of COVID-19 X-ray pictures.Up to 99.5 percent of the test scenario's performance was achieved.An examination of the suggested model's performance in comparison to other models has been conducted using several machine learning methods.)When the proposed model was tested using an independent testing set, it outperformed all other models both generally and specifically.
关键词：Convolutional neural networks (CNNs) in particular have achieved successful outcomes in the categorization and analysis of medical image data using artificial intelligence (AI) approaches
