Affiliation:
1. Applied AI Research Lab., Department of Computer Science, The University of South Dakota, Vermillion, SD 57069, USA
Abstract
The presence of non-biomedical foreign objects (NBFO), such as coins, buttons and jewelry, and biomedical foreign objects (BFO), such as medical tubes and devices in chest X-rays (CXRs), make accurate interpretation difficult, as they do not indicate known biological abnormalities like excess fluids, tuberculosis (TB) or cysts. Such foreign objects need to be detected, localized, categorized as either NBFO or BFO, and removed from CXR or highlighted in CXR for effective abnormality analysis. Very specifically, NBFOs can adversely impact the process, as typical machine learning algorithms would consider these objects to be biological abnormalities producing false-positive cases. It holds true for BFOs in CXRs. This paper examines detailed discussions on numerous clinical reports in addition to computer-aided detection (CADe) with diagnosis (CADx) tools, where both shallow learning and deep learning algorithms are applied. Our discussion reflects the importance of accurately detecting, isolating, classifying, and either removing or highlighting NBFOs and BFOs in CXRs by taking 29 peer-reviewed research reports and articles into account.
Funder
Applied AI research lab, University of South Dakota
Subject
Health Information Management,Health Informatics,Health Policy,Leadership and Management
Reference48 articles.
1. Interpretation of plain chest roentgenogram;Raoof;Chest,2012
2. Zohora, F.T., and Santosh, K. (2016, January 16–17). Circular foreign object detection in chest x-ray images. Proceedings of the International Conference on Recent Trends in Image Processing and Pattern Recognition, Bidar, India.
3. Computer-aided diagnosis systems for lung cancer: Challenges and methodologies;Beache;Int. J. Biomed. Imaging,2013
4. (2022, July 25). Tuberculosis (TB). Available online: https://www.who.int/news-room/fact-sheets/detail/tuberculosis.
5. (2022, July 25). Cancer. Available online: https://www.who.int/health-topics/cancer#tab=tab_1.
Cited by
5 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献