Empirical comparison of color normalization methods for epithelial-stromal classification in H and E images.
Empirical comparison of color normalization methods for epithelial-stromal classification in H and E images.
复制标题
DOI：
10.4103/2153-3539.179984
复制
发表时间：
2016
影响因子：
--
通讯作者：
Gann PH
中科院分区：
文献类型：
--
作者：
Sethi A;Sha L;Vahadane AR;Deaton RJ;Kumar N;Macias V;Gann PH
组织学颜色归一化技术尚未对其在计算病理学流程中的实用性进行过实证测试。我们比较了两种实现共同中间目标的当代技术——上皮基质分类。专家注释的上皮和基质区域被视为用于比较原始图像和颜色归一化图像上的分类器的基本事实。上皮和基质区域在 30 个不同外观的 H 和 E 染色前列腺癌组织微阵列核心上进行注释。使用两种颜色归一化技术生成相应的三十幅图像组。比较原始图像和颜色标准化图像的颜色度量。在测试图像上训练和比较单独的上皮基质分类器。主要分析是使用多分辨率分割（MRS）方法进行的；还使用其他两种分类方法（卷积神经网络 [CNN]、Wndchrm）进行了比较分析。对于依赖于超像素分类的主要 MRS 方法，在不影响准确性的情况下使用后向消除减少了所使用的变量数量，并对原始图像和归一化图像的测试曲线下面积 (AUC) 进行了比较。对于 CNN 和 Wndchrm，比较了像素分类测试 AUC。 Khan 方法降低了色彩饱和度，而 Vahadane 则降低了色调方差。与 10-80 变量范围内的原始图像相比，两个归一化图像集的 MRS 超像素级测试 AUC 高出 0.010-0.025（95% 置信区间限制 ± 0.004）。对于颜色归一化图像，CNN 和 Wndchrm 的像素分类精度也有所提高。当基于超像素的分类方法与执行隐式颜色归一化的特征一起使用时，颜色归一化可以带来小的增量好处，而用于对上皮和基质进行分类的基于块的分类方法的增益更高。
Color normalization techniques for histology have not been empirically tested for their utility for computational pathology pipelines. We compared two contemporary techniques for achieving a common intermediate goal – epithelial-stromal classification. Expert-annotated regions of epithelium and stroma were treated as ground truth for comparing classifiers on original and color-normalized images. Epithelial and stromal regions were annotated on thirty diverse-appearing H and E stained prostate cancer tissue microarray cores. Corresponding sets of thirty images each were generated using the two color normalization techniques. Color metrics were compared for original and color-normalized images. Separate epithelial-stromal classifiers were trained and compared on test images. Main analyses were conducted using a multiresolution segmentation (MRS) approach; comparative analyses using two other classification approaches (convolutional neural network [CNN], Wndchrm) were also performed. For the main MRS method, which relied on classification of super-pixels, the number of variables used was reduced using backward elimination without compromising accuracy, and test - area under the curves (AUCs) were compared for original and normalized images. For CNN and Wndchrm, pixel classification test-AUCs were compared. Khan method reduced color saturation while Vahadane reduced hue variance. Super-pixel-level test-AUC for MRS was 0.010–0.025 (95% confidence interval limits ± 0.004) higher for the two normalized image sets compared to the original in the 10–80 variable range. Improvement in pixel classification accuracy was also observed for CNN and Wndchrm for color-normalized images. Color normalization can give a small incremental benefit when a super-pixel-based classification method is used with features that perform implicit color normalization while the gain is higher for patch-based classification methods for classifying epithelium versus stroma.