OBJECTIVE ANALYSIS OF CHROMOSOME BANDING PATTERNS

该项目旨在开发和商业化显着 改进的染色体带型分析计算机软件， 异常检测用于现代计算机染色体分析 工具，这将允许客观表征和 方便显示染色体带型， 染色体与正常和异常原型以及与 对方.这将有助于细胞遗传学家检测和量化亚细胞， 可见波段图案变化，特别是高分辨率 带状。这将大大提高自动化的能力。 染色体分析仪器，用于评估染色体改变 在正常和肿瘤性哺乳动物细胞中。具体来说，我们使用 频域特征分析，图像分析技术 在贝勒医学院研发的， 染色体图像转换成组件，自动选择出 消除时带型的相关特征 反映预备伪影的成分，染色体间 差异和其他不相关的差异。在第一阶段 项目，我们实现了一套特征分析技术， PSII系统，我们开发了一种新的技术，单染色体 特征分析我们证明了改进的染色体分类 准确性和客观的染色体原型生成。在第二阶段 我们将在几个细胞遗传学应用中测试和鉴定这些 的特征分析，使用它：（1）构造正常的原型 染色体，（2）通过显示辅助交互式核型分析 正常染色体原型，（3）改进染色体分类 准确性，（4）构建特定染色体的原型 （5）自动检测特定的异常， 作为易位，（6）指出同源物中的局部差异， (7)确定染色体的凝聚状态，（8） 表征不同的冷凝阶段，和（9）开发 患者组的原型染色体图像， 与基因相关的疾病。我们将成功实施 PSII的PowerGene商用自动核型分析应用 工作站 建议的商业应用一旦申请 开发和合格的日常应用，他们将 整合到PSII的PowerGene产品中，无论是在新系统中， 并作为现有系统的升级。

This project aims to develop and commercialize significantly improved computer software for chromosome band pattern analysis and anomaly detection. Used on modern computerized chromosome analysis instruments, this will allow objective characterization and convenient display of chromosome banding patterns, and quantitative comparison of chromosomes to normal and abnormal prototypes and to each other. This will help cytogeneticists detect and quantify sub- visible band pattern alterations, particularly with high resolution banding. It will significantly increase the ability of automated chromosome analysis instruments to evaluate chromosome alterations in normal and neoplastic mammalian cells. Specifically, we use frequency domain eigenanalysis, an image analysis technique developed at the Baylor College of Medicine, to decompose chromosome images into components, automatically selecting out relevant characteristics of the banding pattern while eliminating components that reflect preparatory artifact, inter-chromosome variation, and other irrelevant differences. During the Phase I project we implemented a set of eigenanalysis techniques on the PSII system, and we developed one new technique, single chromosome eigenanalysis. We demonstrated improved chromosome classification accuracy and objective chromosome prototype generation. In Phase II we will test and qualify these on several cytogenetic applications of eigenanalysis, using it to: (1) construct prototypes of normal chromosomes, (2) assist interactive karyotyping by displaying normal chromosome prototypes, (3) improve chromosome classification accuracy, (4) construct prototypes of specific chromosomal abnormalities, (5) automatically detect specific abnormalities such as translocations, (6) point out localized differences in homologs, (7) determine the condensation state of chromosomes, (8) characterize different condensation stages, and (9) develop prototypical chromosome images for patient groups manifesting genetically linked diseases. We will implement successful applications on PSII's PowerGene commercial automatic karyotyping workstation. PROPOSED COMMERCIAL APPLICATIONS As soon as the applications are developed and qualified for routine application, they will be incorporated into PSII's PowerGene products, both in new systems sold and as an upgrade to existing systems.