Revolutionizing Medical Imaging through Deep Learning Techniques:An Overview. | ||||
International Journal of Intelligent Computing and Information Sciences | ||||
Volume 23, Issue 3, September 2023, Page 59-72 PDF (645.23 K) | ||||
Document Type: Original Article | ||||
DOI: 10.21608/ijicis.2023.211266.1274 | ||||
View on SCiNiTO | ||||
Authors | ||||
Salma M Elgayar 1; Safwat Hamad2; El-Sayed M. El-Horbaty3 | ||||
1Computer Science, Faculty of Computer and Information Sciences, Ain shams university, Cairo, Egypt. | ||||
2Business Analytics Department School of Economic and Business Administration (SEBA), Saint Mary’s College of California, Moraga CA-USA | ||||
3Scientific Computing, Faculty of Computer and Information Sciences, Ain shams university, Cairo, Egypt. | ||||
Abstract | ||||
Medical imaging is a crucial tool for various clinical applications, including examination of medical issues, including early identification, monitoring, diagnosis, and therapy. To analyse medical images using computer vision, it is crucial to comprehend the ideas behind artificial neural networks and deep learning. In this particular article, we present recent principles of deep learning models and the different forms of widely used activation functions. Utilising Deep Learning Approach (DLA) has expanded quickly in the study of medical images, particularly in detecting either being present or not diseases. This study explores artificial neural networks development and provides a comprehensive analysis of DLA and potential uses for medical imaging. The majority of DLA implementations focus on pictures from digital histopathology, computer tomography, mammography, and X-rays. A thorough overview of the literature on the classification, detection, and segmentation of medical pictures using DLA is provided in the paper, which might help researchers decide what changes should be made to medical image analysis. | ||||
Keywords | ||||
Keywords:Convolutional neural network; Medical imagery; Deep learning; Classification Segmentation; and Detection | ||||
Statistics Article View: 146 PDF Download: 130 |
||||