Abstract
The thesis aims at developing an algorithm and its Matlab program to identify phalangeal ROI and to accurately segment the phanlangeal bone from the soft tissue and background in a left-hand X-ray image, so that the segmentation result can be utilized in subsequent feature extraction, analysis, and classification modules in a fully automatic computer assisted bone age assessment system. When inputting the cropped left-hand X-ray image from DICOM, the developed program can automatically process the image, remove the background to obtain the hand mask, locate the five phalangeal ROI’s, and segment the phanlangeal bone from the soft tissue and background of the distal, middle, and proximal phalanx without further human intervention and parameter adjustments. Three major steps are employed in the developed program. First, the background portion of the left-hand X-ray image is removed by using the histogram mode with triangular algorithm to find a proper threshold to remove the background and to obtain the proper hand mask. Then using the centroid of the palm portion of the hand mask as a starting point with scan method, the locations of five fingers are determined and the corresponding phalangeal ROI’s are extracted. Finally, for each extracted distal, middle, and proximal ROI, the phalanx is segmented from tissue and other unnecessary background region by using a trapezoid algorithm, round-average deduction algorithms, and Matlab filling tool. 40 left hand X-ray images and 200 left hand images from more than 700 different subjects with ages covering 0 to 19 for both genders are processed and segmented by the proposed algorithm. The results statistics showed that, it only takes less than 10 seconds by the proposed Matlab program from reading-in a left-hand image to producing the segmented result, and most of the images can produce successfully extracted middle, distal, and proximal phalanx ROI’s, which are the three most important phalanx regions in clinical bone age research. Meanwhile, for comparison purpose, adaptive two-means segmentation algorithm is also implemented and the segmentation results of the proposed round-average deduction method and adaptive two-means on extracting phalanx bone region are evaluated by using five error measures: ME, RFAE, EMM, MHD, and NU. The experimental result statistics showed that, the proposed round-average deduction method performs better than adaptive two-means method on ME、RFAE、EMM and NU, but is worse on MHD. However, the round-average deduction method executes much faster than adaptive two-means.