Detecting Disease in Radiographs with Intuitive Confidence
Author
Source
Issue
Vol. 2015, Issue 2015 (31 Dec. 2015), pp.1-9, 9 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2015-10-01
Country of Publication
Egypt
No. of Pages
9
Main Subjects
Medicine
Information Technology and Computer Science
Abstract EN
This paper argues in favor of a specific type of confidence for use in computer-aided diagnosis and disease classification, namely, sine/cosine values of angles represented by points on the unit circle.
The paper shows how this confidence is motivated by Chinese medicine and how sine/cosine values are directly related with the two forces Yin and Yang.
The angle for which sine and cosine are equal (45°) represents the state of equilibrium between Yin and Yang, which is a state of nonduality that indicates neither normality nor abnormality in terms of disease classification.
The paper claims that the proposed confidence is intuitive and can be readily understood by physicians.
The paper underpins this thesis with theoretical results in neural signal processing, stating that a sine/cosine relationship between the actual input signal and the perceived (learned) input is key to neural learning processes.
As a practical example, the paper shows how to use the proposed confidence values to highlight manifestations of tuberculosis in frontal chest X-rays.
American Psychological Association (APA)
Jaeger, Stefan. 2015. Detecting Disease in Radiographs with Intuitive Confidence. The Scientific World Journal،Vol. 2015, no. 2015, pp.1-9.
https://search.emarefa.net/detail/BIM-1079312
Modern Language Association (MLA)
Jaeger, Stefan. Detecting Disease in Radiographs with Intuitive Confidence. The Scientific World Journal No. 2015 (2015), pp.1-9.
https://search.emarefa.net/detail/BIM-1079312
American Medical Association (AMA)
Jaeger, Stefan. Detecting Disease in Radiographs with Intuitive Confidence. The Scientific World Journal. 2015. Vol. 2015, no. 2015, pp.1-9.
https://search.emarefa.net/detail/BIM-1079312
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1079312