Reis Luana A, Garcia Ana P V, Gomes Egleidson F A, Longford Francis G J, Frey Jeremy G, Cassali Geovanni D, de Paula Ana M
Departamento de Física, Instituto de Ciências Exatas, Universidade Federal de Minas Gerais, 31270-901 Belo Horizonte-MG, Brazil.
Laboratório de Patologia Comparada, Instituto de Ciências Biológicas, Universidade Federal de Minas Gerais, 31270-901 Belo Horizonte-MG, Brazil.
Biomed Opt Express. 2020 Oct 16;11(11):6413-6427. doi: 10.1364/BOE.400871. eCollection 2020 Nov 1.
We present nonlinear microscopy imaging results and analysis from canine mammary cancer biopsies. Second harmonic generation imaging allows information of the collagen structure in the extracellular matrix that together with the fluorescence of the cell regions of the biopsies form a base for comprehensive image analysis. We demonstrate an automated image analysis method to classify the histological type of canine mammary cancer using a range of parameters extracted from the images. The software developed for image processing and analysis allows for the extraction of the collagen fibre network and the cell regions of the images. Thus, the tissue properties are obtained after the segmentation of the image and the metrics are measured specifically for the collagen and the cell regions. A linear discriminant analysis including all the extracted metrics allowed to clearly separate between the healthy and cancerous tissue with a 91%-accuracy. Also, a 61%-accuracy was achieved for a comparison of healthy and three histological cancer subtypes studied.
我们展示了犬类乳腺癌活检的非线性显微镜成像结果及分析。二次谐波产生成像可提供细胞外基质中胶原蛋白结构的信息，该信息与活检组织细胞区域的荧光一起构成了全面图像分析的基础。我们展示了一种自动图像分析方法，利用从图像中提取的一系列参数对犬类乳腺癌的组织学类型进行分类。为图像处理和分析开发的软件能够提取图像中的胶原纤维网络和细胞区域。因此，在对图像进行分割后可获得组织特性，并专门针对胶原蛋白和细胞区域测量指标。包含所有提取指标的线性判别分析能够以91%的准确率清晰区分健康组织和癌组织。此外，在比较健康组织和所研究的三种组织学癌症亚型时，准确率达到了61%。
