Comparison of normalization algorithms for cross-batch color segmentation of histopathological images

Abstract

Automated processing of digital histopathology slides has the potential to streamline patient care and provide new tools for cancer classification and grading. Before automatic analysis is possible, quality control procedures are applied to ensure that each image can be read consistently. One important quality control step is color normalization of the slide image, which adjusts for color variances (batch-effects) caused by differences in stain preparation and image acquisition equipment. Color batch-effects affect color-based features and reduce the performance of supervised color segmentation algorithms on images acquired separately. To identify an optimal normalization technique for histopathological color segmentation applications, five color normalization algorithms were compared in this study using 204 images from four image batches. Among the normalization methods, two global color normalization methods normalized colors from all stain simultaneously and three stain color normalization methods normalized colors from individual stains extracted using color deconvolution. Stain color normalization methods performed significantly better than global color normalization methods in 11 of 12 cross-batch experiments (p<0.05). Specifically, the stain color normalization method using k-means clustering was found to be the best choice because of high stain segmentation accuracy and low computational complexity.

Automatic diagnosis of tuberculosis disease based on Plasmonic ELISA and color-based image classification

“…This challenge was tackled by converting the image into the CIELAB color space and then applying k-means clustering and thresholding algorithms. Hoffman et al (2014) reported that expectation-maximization, k-means, and variational Bayesian inference all have the same performance, however, k-means take the minimum time to produce the result.…”

A robust nonlinear tissue-component discrimination method for computational pathology

“…Nuclei detection in histo-pathological images has been critical and often used in computational pathology approaches to develop prognostic and diagnostic models 7 - 9 , 11 , 12 , 17 , 33 . Currently, color deconvolution (CD) is commonly used to extract a representative nuclei image (corresponding to the hematoxylin dye levels) to apply nuclei detection algorithms 9 , 28 - 30 , 33 , 38 . Here, we show that using the nuclei image derived from the NLTD method improves the detection of nuclei over the color deconvolution approach.…”

“…Due to color appearance difference between images, using the same stain vector across images will introduce variance in the representative image for each dye. Although there are automated methods to determine the stain vector for individual images, the additional processing step leads to significant increase in processing time across large image datasets 30 . Furthermore, color deconvolution only decouples the concentration of dye in the histo-pathological image, and further processing is needed to separate individual tissue components such as blood, nuclei, and extracellular matrix and cytoplasmic rich regions for quantification.…”

Prediction of heart transplant rejection using histopathological whole-slide imaging

“…Color normalization is important image quality assurance step when analyzing digitized WSI as color batch-effects can negatively impact color segmentation, a tool used in this study for feature extraction [8]. These effects can arise from differences in the procedure used to stain each tissue biopsy sample and the image acquisition equipment.…”