4.3 Article

Optimization of chest X-ray exposure factors using machine learning algorithm

Journal

Publisher

ELSEVIER
DOI: 10.1016/j.jrras.2022.100518

Keywords

Exposure factors; Body mass index; Chest X-ray; Machine learning

Ask authors/readers for more resources

A better quality radiographic image aids in proper disease diagnosis by the radiologist. This study analyzes chest X-ray exposure factors for 178 patients with different body mass index (BMI) values using the Python Machine Learning algorithm. The results reveal specific exposure factors for each patient based on their BMI, which can have detrimental effects on patient health if exceeded. The findings provide detailed information on the relationship between BMI and optimal chest X-ray exposure factors without compromising image quality.
A better quality radiographic image helps the radiologist to make a proper diagnosis of the disease. In general, the use of more radiation provides a better quality image, but it gives the patient a higher radiation dose, which shows the need for optimization of imaging conditions to minimize the risk to patients from excessive radiation exposure. In this study, the chest X-ray exposure factors for 178 patients with different body mass index (BMI) values have been analyzed using the Python Machine Learning algorithm. Patient data were collected from the King Abdullah bin Abdulaziz University Hospital, Saudi Arabia. The role of BMI in the selection of radiation exposure factors (kVp, mAs) was evaluated. It has been found that the BMI of each patient has specific exposure factors, and that if it gets higher than the specific value it could harm the patient's health. The obtained results provide detailed information about the relation between BMI and optimal chest X-ray exposure factors without affecting the quality of the X-ray image.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.3
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available