Progression of Using Deep Learning Approaches for Chest X-Ray Diagnoses | ||||
| Journal of Scientific Research in Science | ||||
| Volume 41, Issue 1, 2024, Page 59-77 PDF (661.23 K) | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/jsrs.2024.288876.1130 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
Alaa A. Eldewer  1; A A Soliman2; Haiam A. Abdul-Azim1
| ||||
| 1Physics and Computer Group, Physics Department, Faculty of Women for Arts, Science and Education, Ain Shams University, Cairo, Egypt. | ||||
| 2Solid-State Physics Group, Physics Department, Faculty of Women for Arts, Science and Education, Ain Shams University, Cairo, Egypt. | ||||
| Abstract | ||||
| A Chest X-ray (CXR) scan is one of the most frequently used in diagnosing several thoracic diseases. The conventional interpretation of radiologists for CXRs takes a while and depends on participant variation. In recent years, deep learning approaches have become an attractive method of automating and enhancing the diagnosis of chest X-ray diseases. Also, deep learning could lead to new diagnosis directions, even outside these immediate applications. Although there is a lot of promise for deep learning to improve CXR diagnosis, ethical questions around accessibility and equity in these algorithms also need to be considered. Moreover, the responsible incorporation of deep learning into clinical practice requires close cooperation between radiologists and AI developers. This means it may increase productivity and accuracy while facilitating access to enhanced chest X-ray examinations in regions with limited resources. This work overviews the developments in using deep learning for automatically identifying chest X-ray diseases, including approaches, difficulties, and potential future paths. | ||||
| Keywords | ||||
| Computer Vision; Convolutional Neural Networks (CNNs); and Deep Learning Approaches; Medical Diagnoses | ||||
|
Statistics Article View: 86 PDF Download: 89 |
||||
