An Automatic Quality Figure Evaluator of Contrast-Detail Phantom Image Using in Radiography

• Main Authors: Shih-Rong Wang, 王詩榕
• Other Authors: 詹永寬
• Format: Others
• Language: en_US
• Published: 2012
• Online Access: http://ndltd.ncl.edu.tw/handle/44842666885492301977

碩士 === 國立中興大學 === 資訊管理學系所 === 100 === In radiology, it is significantly important to produce adequate diagnostic information for affecting the patient with the lowest amount of dose. A contrast-detail phantom is generally used to study the quality of the image and the amount of radiation dose for a digital X-ray imaging system. For evaluating the quality of a phantom image, the radiologists are required to indicate the location of the holes in each square in the phantom image. Then, the image quality figure (IQF) of the image can be calculated. However, evaluation by the human eye is subjective and time-consuming. In this paper, an image processing based IQF evaluation method is proposed to automatically measure the quality of a phantom image.The IQF evaluation method consists of four stages — square segmentation, mean-difference gradient, run length enhancer, and square pattern recognition. The experimental results tell that the proposed method is more sensitive in estimating the IQF of a phantom image than the observation of radiologists. Moreover, a genetic algorithm is provided to compute the most suitable values of the parameters to be used in the IQF evaluation method.