基于全场光学相干层析图像的人体肝组织癌变定量特征分析研究

A Study of FFOCT En Face Image-based Quantitative Characterization of Human Liver Cancer

利用实验室搭建的全场光学相干层析(FFOCT)系统对人体正常与癌变肝组织分别进行成像,获得了高分辨率的层析图像。针对人眼识别FFOCT图像时难以区分正常与早期癌变肝组织的问题,提取两者FFOCT图像的灰度特征并进行统计学分析,以实现在参数特征上区分两者的目的。结果表明,在正常与癌变肝组织初步提取的均值、方差和峰度等五个特征参数中,有四个显示出了明显的数值差异,可用于鉴别肝组织是否癌变。该研究结果为进一步研究如何利用FFOCT图像中所提取的特征参数作为判断实际临床诊断中生物组织癌变与否的诊断标准打下了基础。

The high-resolution en face tomographic images of normal and cancerous human liver tissues were obtained by using a full field optical coherence tomography(FFOCT)system built in our laboratory.To solve the problem that it is difficult to distinguish between the normal and early cancerous liver tissues with unaided human eye from the FFOCT images,the grayscale features of the two kinds of the FFOCT images were extracted and statistical analysis was made to identify the differences between them in the values of parameters characterizing their features.The results showed that four of the five characteristic parameters,including mean,variance and kurtosis etc.,showed significant differences between normal and cancerous liver tissues,which can be used to identify whether the liver tissues were cancerous.The results of this study lay a foundation for further study on how to use the feature parameters extracted from the FFOCT images as the pathological indicators of cancerous tissues in the actual clinical diagnosis.