摘要
在定量细胞学研究中,细胞核内DNA物质含量的准确测量是癌症筛查与病理诊断的必要前题与最重要依据。由于算法、设备、环境等因素的影响,在对细胞核的数字显微图像进行处理与分析、测量DNA物质含量时会产生较大的误差。本文提出了一种基于数学形态学和k近邻回归算法的DNA物质含量校正新方法。该方法首先利用膨涨算法对细胞核分割掩码进行处理,从而对DNA物质含量的测量进行空间校正;然后采用k近邻回归算法,充分利用细胞核的形态、纹理等特征参数所蕴含的信息,从而对DNA物质含量进行光学回归校正。实验表明,该方法能够显著提高DNA物质含量测量的准确性和可信度,对提高病理诊断的特异性与敏感性都有积极的意义。
In the study of quantitative cytology, the measurement of the DNA contents in cell nuclei is the most important basis and necessary premise of cancer screening and diagnosis. Due to some unavoidable factors, certain errors may occur in the measurement of the DNA contents through processing and analysis of the cell nuclei image. A new calibration approach based on morphology and the k -NN regression algorithm is proposed. Through spatial and optical calibration, the approach sufficiently utilizes the information hidden in the image and features of the cell nuclei. The experiment shows that the approach increases the measurement accuracy significantly, and shows positive significance in improving the specificity and sensitivity of the pathological diagnosis.
出处
《计算机工程与科学》
CSCD
北大核心
2009年第10期45-48,共4页
Computer Engineering & Science
基金
国家自然科学基金资助项目(60873127)
关键词
定量细胞学
医学图像处理
计算机视觉
k近邻回归
quantitative cytology
medical image processing
computer vision
k nearest-neighbor regression