基于光学相干断层成像技术量化评估皮肤癌的二维傅里叶分形维数

Quantitative Evaluation of the 2D Fourier-based Fractal Dimension of Skin Cancers with Optical Coherence Tomography

光学相干断层成像技术(optical coherence tomography,OCT)可用于皮肤组织的诊断。从OCT图像提取的定量特征变量能够用作皮肤肿瘤诊断的指标。在这些定量特征变量中,分形维数能够表征皮肤组织的结构变化,从而能够提供有效的方法区分诊断皮肤肿瘤。本研究应用OCT获取了恶性黑色素瘤,基底细胞癌和色素痣OCT图像;基于傅里叶分析,从OCT图像中提取了二维分形维数;应用统计分析方法,分析各皮肤组织的分形维数的差异性。研究结果表明,与恶性黑素瘤相比,基底细胞癌和色素痣中的二维分形维数的显着减少;二维傅里叶分析能够提供一种简单易行的方法从OCT图像中提取分形维数,用以表征恶性黑色素瘤、基底细胞癌和色素痣。

The optical coherence tomography （OCT） technique is currently utilized in the diagnosis of the skin tissue. In general ,quantitative imaging features extracted from OCT images have been already used as indicators to categorize the ly ,the fractal dimension could be capable of providing an efficient method in the analysis of OCT images of the skin tumors. In thepresent paper , the 2D Fourier fractal analysis was performed on OCT images for automatically catcarcinomas and pigment nevi. Our results showed that the significant decrease of the 2D fractal dimension was observed in the basal cell carcinomas and pigment nevi as compared with the melanomas. Our results suggest that the 2D Fourier fractal analysis can provide an easy understandable way to differentiate the basal cell carcinomas and pigment nevi from the melano