Research Article
A Chest X-Ray Image Based Model for Classification and Detection of Diseases
@INPROCEEDINGS{10.1007/978-3-031-48888-7_36, author={Srinivas Yallapu and Aravind Kumar Madam}, title={A Chest X-Ray Image Based Model for Classification and Detection of Diseases}, proceedings={Cognitive Computing and Cyber Physical Systems. 4th EAI International Conference, IC4S 2023, Bhimavaram, Andhra Pradesh, India, August 4-6, 2023, Proceedings, Part I}, proceedings_a={IC4S}, year={2024}, month={1}, keywords={Radiography Deep-Learning Convolutional Neural Networks (ConvNet or CNN) Artificial Intelligence (AI) Machine Learning (ML)}, doi={10.1007/978-3-031-48888-7_36} }- Srinivas Yallapu
Aravind Kumar Madam
Year: 2024
A Chest X-Ray Image Based Model for Classification and Detection of Diseases
IC4S
Springer
DOI: 10.1007/978-3-031-48888-7_36
Abstract
Radiography holds significant importance in the medical field, allowing for efficient and widespread access, primarily due to the predominant utilization of thoracic imaging equipments within healthcare infrastructure. However, radiologist’s ability to understand radiography images is constrained by their inability to recognize the fine visual details present in the images. There have been numerous studies published in the literature describe machine learning (ML) recent advance models that use support vector machines do differentiate between COVID-19 and non COVID-19 cases by means of open-access chest radiograph databases. The AI can be familiar with characteristics observed in chest X-rays tasks that are typically beyond the scope of a radiologist. They did, however, produce poor categorization performance. Deep - learning techniques in artificial intelligence (AI) are high-performance classifiers engage in recreation a most important significance in the identification of the disease through analysis of chest radiograph metaphors. The major goal of this learning is to examine the enhancement of pre-trained ConvNet (CNNs) as XCOVNet for COVID-19 classification by means of chest radiograph, considering the abundance of newly developed deep learning models specifically designed for this task with more accuracy of 99.51% than previous methods.
