| Summary: | 碩士 === 國立清華大學 === 電機工程學系 === 101 === Abstract
The objective of this thesis is to develop an automatic and accurate phalangeal segmentation system, which can constitute a fully automatic phalanx bone age assessment system by adding feature extraction and analysis/classification stages in the future.
Study shows that generally the result of segmentation can be further improved by a proposed preprocessing of adjusting the gray level distribution of the knuckle images, i.e., EMROI (epiphyseal/metaphyseal bone region of interest), before entering the bone edge detection/segmentation stage. The improvements are more profound in the cases of younger children however, for children with age over 8 and elder the effects of the proposed preprocessing become less effective and even deteriorate the segmentation results. Therefore this thesis proposes an age-dependent preprocessing scheme before entering the bone edge detection/segmentation stage. Observing that the density of carpal area increases with age, we propose a method utilizing such growth characteristics of carpal to quickly determine the prior knowledge of age for the hand radiogram under segmentation.
A knuckle segmentation process is proposed. First, the input X-ray hand-image is processed and nine knuckle images of the index finger, middle finger, ring finger (i.e., 9 EMROI’s) are segmented. Then the prior knowledge of age is determined by using the carpal area density characteristics and the age-dependent preprocessing based on the prior knowledge of age is applied to the 9 EMROI’s. Finally, image segmentation is applied to detect the bone edges and/or contours in those knuckle images.
Four image segmentation methods, namely GVF snake, round-average deduction method, adaptive two-means clustering algorithm and the level set evolution are adopted in our experiments. Six error measures: ME (misclassification error), RFAE (relative foreground area error), NU (non-uniformity), MHD (modified Hausdorff distances), EMM (edge mismatch), and Mean Errors are used to assess the effectiveness of the proposed phalanx image segmentation process. The experimental results show that the error measures for the cases of incorporating prior knowledge of age and proposed age-dependent preprocessing are generally better than those cases without using prior knowledge of age and proposed preprocessing. For example, the values of mean errors are improved from 28% to 33% for the four different segmentation methods, respectively.
|
|---|
