骨龄测定系统

【作者】 付秀丽；

【导师】 罗炳伟；

【作者基本信息】 电子科技大学 ， 生物医学工程， 2003， 硕士

【摘要】 微机骨龄测定系统是华西附属第二医院提出的应用课题，它在文艺，体育部门选材，儿童保健咨询及生长预测，小儿身高异常及内分泌疾病的诊断，治疗监护和疗效观察以及法医学鉴定等方面有重要意义。该系统主要由图像处理和骨龄计算两部分组成，本课题主要对图象处理部分展开研究，取得了一定的成果，推进了骨龄测定系统微机化的研究。本文深入分析了目前存在的各种图像分割方法及其特点，针对医学图像及所研究对象的要求和特征，以及目前骨龄测定系统存在的优缺点，拟定了微机骨龄测定系统图像分割部分的总体方案，具有一定的创新性。随后，笔者重点研究了小波技术在微机骨龄诊断系统中的应用，初步解决了目前骨龄系统中存在的局部分割问题，抛弃传统的链长观念，提出了链的百分比概念，国内外文献未见有相关报道；针对分割结果的不封闭性，采用边缘点生长的方法，有效地解决了区域的封闭性。最后通过寻找大区域解决了高细节区的分割问题。 最后，笔者用Matlab语言在计算机上完成了本方案的仿真，包括图像的预处理、分割和后继处理。方案通过计算机实现，与理论分析设计具有比较好的一致性，取得了较满意的结果。更多还原

【Abstract】 The microcomputer-based bone-age recognition system is an application project by the second hospital pertaining to huaxi medical university. It has significance in the areas of selecting talents of art and sports, the healthcare consultation and growth forecast of children, the abnormity of children’s stature and the diagnosis of incretion illness, the monitoring and observation of the treatment effect and the identification in medical jurisprudence. The system is composed of two parts: the image segmentation and bone-age computation. This project mainly carried out exploration in image segmentation and some good results are derived which advances the research of the micro-computer based bone-age recognition system. In this paper the in-depth analysis is made for the extant image segmentation approaches and their characteristics. Aiming at the demand , analyzing the characteristic of the medical image and its investigation subject as well as the advantages and drawbacks of the extant bone-age recognition system, the overall scheme is designed for the image-segmentation for the micro-computer based bone-age recognition system ,which is a creative work.In this paper emphasis is put on the application of the wavelet technique into the system and the local segmentation problem preliminarily solved existing in the extant bone-age recognition system..the traditional chain-length concept is dixcarded and the percentage concept of the chain is proposed. No related reports can be found in the literature. The chain is proposed. No related reports can be found in the literature. The edge-growth method is adopted to get the good closed image. Lastly the image segmentation is implemented by finding large regions.Finally the simulation is implemented with matlat including the preprocessing ,the segmentation and the after-effect processing. The scheme is realized with computer and a fairly good consistency is <WP=5>obtained with the theory analysis and design. The result is satisfactory according to the clinical demand.更多还原