眼前节图像采集、分析、归档系统的研究与实现

【作者】 谢杰镇；

【导师】 王博亮；

【作者基本信息】 厦门大学 ， 计算机应用， 2002， 硕士

【摘要】 眼睛是我们认识世界、从事各项工作的重要工具。眼睛健康与否，眼前节生物数据是一个重要指标。随着数字图像处理技术的发展，使得利用计算机对眼前节图像进行采集、分析和归档成为可能。通过采集眼前节图像并自动分析眼前节生物数据，对临床各种眼部疾病的诊断、拟定治疗方案和评估治疗效果等方面，有着重要的现实意义。本文的目标是研究并实现眼前节图像采集、分析和归档系统。首先对通用的裂隙灯显微镜进行改造，采集裂隙扫描眼前节图像；然后对利用直接焦点照明法采集得到图像进行自动分析提取眼前节的各种生理、病理参数；进一步结合DICOM标准，把采集和分析得到的结果以DICOM格式存储和归档。本文对其中的几个关键技术和方法研究做出了独立贡献：1． 改造了裂隙灯显微镜的硬件，包括光路设计和增加图像采集设备。2． 设计并实现了眼前节图像采集和回放子系统。3． 在分析对比一些经典的边缘提取算法的基础上，根据眼前节图像的特点，改进了Canny算法；4． 设计了分割角膜和虹膜反光带边缘以及曲线拟合的算法，实现了眼前节生物数据的自动提取。5． 分析DICOM标准，实现了把得到眼前节图像转换成为DICOM格式。实验证明本系统可以实现采集裂隙扫描眼前节图像，自动分析眼前节生物数据，并把采集和分析后的图像以DICOM格式存储，为眼科医生临床诊断提供了重要的诊疗设备。系统操作方便、交互性良好，具有一定的实用价值；但由于现有系统硬件的限制，提出的方法仍有待临床应用检验，故还需进一步完善。更多还原

【Abstract】 Eyes are very important to our lives. Biologic parameters of anterior segment are criterions of determining whether the eye is sick or not. With the development of digital image processing, it is possible to capture, analyze and archive the anterior segment image by computer. Capturing the image and automatic analyzing of biologic parameters is useful for diagnosing illness, planning for cure and estimating the result, etc.The object of this paper is to design a system of capturing, analyzing and archiving the anterior segment image. Firstly, some modifications were made on the slit lamp in order to capture slit light micrographs of the human eyes. Secondly, the anterior segment image, which was acquired by the method of direct focal illumination, was analyzed automatically to give some physiological and pathological parameters. Then the slit light micrographs were transformed according to the DICOM standard. In this paper, some special work has been done in the aspects as follow: Some modifications were made on the slit lamp, including designing the photic channel and adding equipments for capturing image. Completed a sub-system to capture and review the anterior segment image. Based on the comparison of some classical edge detection operators, an improvement was made on the Canny’s optimal edge detection operator for the image as the character of them. Designed a method to distinguish edges of the outside, intestine surface of the corneal and the anterior surface of the iris in the image. Some biologic parameters of anterior segment were given automatically by curve fitting. Studied on the storage standard of DICOM. And transformed the anterior segment image into the format of DICOM standard.The system, which had been designed, can be provided as an important diagnostic tool for the doctor in the clinic. It is convenient and practicable with good intercommunion. Because of the limitation of the hardware, the method needs to be proved in the practice more, the system must be perfected gradually before it can be used in the clinic application.更多还原