Depth Maps From Stereo Images Of The Optic Disc

描述(申请人提供)：青光眼是一种慢性疾病，其病因 都没有被很好地理解。据估计，有300万美国人 到2000年，全世界将有6700万人患有青光眼。 至少一半的人不知道自己患有青光眼，因为青光眼通常没有任何症状。 在早期阶段。如果不治疗，青光眼是不可逆转的主要原因 失明。当前研究的一个重要目标是开发早期诊断方法。 诊断要在疾病的早期阶段发现，当治疗最多时 有效减少不可逆转的视力损失。目前，身份识别 视神经头(ONH)的早期病理改变对 青光眼的诊断。目前衡量这些变化的黄金标准是 通过对ONH的临床立体观察。来自美国学院 Ophthology(AAO)2000的研究发现，以前的研究发现， ONH立体照片定性评价精度的研究 有经验的临床观察者比目前任何其他可用的人都要好 视盘评估方法“(识别早期青光眼的变化， 沃尔斯坦，健康，2000年AAO)。 立体评价的主要缺点是评价的主观性 创造了观察者之间和观察者内部的读者可变性。一种新的检测方法 需要对立体照片进行评估，以进行一致的分析 视神经头的变化。这可以通过使用 定量分析ONH的变化。一期工程将用于 一种改进的基于一对视差图的视差图计算方法 立体图像。这项技术已经被证明取得了良好的效果， 尽管它需要针对此特定应用程序进行调整。曾经的地形 可以使用基本的图像处理算法来定位光盘并 杯子的边界并计算杯子的体积。算法将是 并与几个预诊病例进行比较，以检验其准确性。这将是 导致第二阶段项目，该项目将使用数字化的立体图像 用于纵向测量的视神经头。这些测量结果将 包括杯和盘的尺寸在一年内的三维变化 一段时间。测量将根据预先诊断的图像进行计算，以 比较和专家阅读器。来自爱荷华大学的合作者 圣安东尼奥的德克萨斯大学医学中心将提供这些 分析。

DESCRIPTION (provided by applicant): Glaucoma is a chronic disease whose causes are not well understood. It is estimated that three million Americans have glaucoma, and 67 million people worldwide will have glaucoma by the year 2000. At least half do not know they have it because glaucoma usually has no symptoms in the early stages. Untreated, glaucoma is a leading cause of irreversible blindness. An important goal of current research is to develop methods of early diagnosis to detect the disease in the early stages, when treatment is most effective in minimizing irreversible vision loss. Currently, the identification of early pathologic changes at the optic nerve head (ONH) is crucial to the diagnosis of glaucoma. The current gold standard for measuring these changes is through clinical stereoscopic observation of the ONH. From the American Academy of Ophthology (AAO) 2000, "Previous studies have found that the diagnostic precision of qualitative evaluation of stereoscopic ONH photographs by experienced clinical observers is superior to any other currently available method of optic disc assessment." (Identifying Early Glaucomatous Changes, Wollstein, Health, 2000 AAO). The major drawback to the stereoscopic evaluation is the subjectivity which creating inter and intra-observer reader variability. A new method for evaluation to stereoscopic photographs is needed for consistent analysis of the changes on the optic nerve head. This can be brought about by the use quantitative analysis of the ONH changes. The phase I project will be used to improve a technique for calculating disparity maps based on a pair of stereoscopic images. This technique has already proven to give good results, though it needs to be tuned for this specific application. Once the topography is found, basic image processing algorithms can be used to locate the disc and cup boundaries and calculate the volume of the cup. The algorithm will be compared to several pre-diagnosed cases for testing the accuracy. This will lead to the Phase II project, which will use digitized stereoscopic image of the optic nerve head for longitudinal measurements. These measurements will include three-dimensional changes in the dimensions of the cup and disk over a period of time. The measurements will be calculated on pre-diagnosed images for comparison with and expert reader. Collaborators from the University of Iowa and the University of Texas Medical Center in San Antonio will provide these analyses.