Affiliations: Department of Medicine, University of Ottawa, Ottawa,
Canada | Department of Mechanical and Industrial Engineering,
Ryerson University, Toronto, Canada
Abstract: Today's imaging diagnosis needs to adapt modern techniques of
quality engineering to maintain and improve its accuracy and reliability in
health care system. One of the main factors that influences diagnostic accuracy
of plain film X-ray on detecting pathology is the level of film exposure. If
the level of film exposure is not adequate, a normal body structure may be
interpretated as pathology and vice versa. This not only influences the patient
management but also has an impact on health care cost and patient's quality of
life. Therefore, providing an accurate and high quality image is the first step
toward an excellent patient management in any health care system. In this
paper, we study these techniques and also present a fuzzy intelligent quality
monitoring model, which can be used to keep variables from degrading the image
quality. The variables derived from chemical activity, cleaning procedures,
maintenance, and monitoring may not be sensed, measured, or calculated
precisely due to uncertain situations. Therefore, the
γ-level fuzzy Bayesian model for quality monitoring of
an image processing is proposed. In order to apply the Bayesian concept, the
fuzzy quality characteristics are assumed as fuzzy random variables. Using the
fuzzy quality characteristics, the newly developed model calculates the
degradation risk for image processing. A numerical example is also presented to
demonstrate the application of the model.
