Colour model analysis for microscopic image processing

Colour consistency in light microscopy based histology is an increasingly important problem with the advent of Gigapixel digital slide scanners and automatic image analysis. This paper presents an evaluation of two novel colour normalisation approaches against the previously utilised method of linear normalisation in lαβ colourspace. These approaches map the colour distribution of an over/under stained image to that of a well stained target image. The first novel approach presented is a multi-modal extension to linear normalisation in lαβ colourspace using an automatic image segmentation method and defining separate transforms for each class. The second approach normalises in a representation space obtained using stain specific colour deconvolution. Additionally, we present a method for estimation of the required colour deconvolution vectors directly from the image data. Our evaluation demonstrates the inherent variability in the original data, the known theoretical problems with linear normalisation in lαβ colourspace, and that a multi-modal colour deconvolution based approach overcomes these problems. The segmentation based approach, while producing good results on the majority of images, is less successful than the colour deconvolution method for a significant minority of images as robust segmentation is required to avoid introducing artifacts.

— Automated image processing has become very popular in the field of digital histopathology. Digital histopathology is an upcoming area of research where diagnosis decisions are made by quantitative analysis of image content. The problem of color variation is a serious issue in this field. Color variation is a result of inconsistencies in staining procedure or due to the use of different scanners. Color normalization aims at bringing a histological image into a different color appearance of another image which standardizes the color representation of both the images. This literature gives a description of various color normalization approaches used to address the problem of color variation in histopathology images. It focuses mainly on methods used in normalization of breast cancer images.

Micron (Oxford, England : 1993), 2018

Histopathology images are used for the diagnosis of the cancerous disease by the examination of tissue with the help of Whole Slide Imaging (WSI) scanner. A decision support system works well by the analysis of the histopathology images but a lot of problems arise in its decision. Color variation in the histopathology images is occurring due to use of the different scanner, use of various equipments, different stain coloring and reactivity from a different manufacturer. In this paper, detailed study and performance evaluation of color normalization methods on histopathology image datasets are presented. Color normalization of the source image by transferring the mean color of the target image in the source image and also to separate stain present in the source image. Stain separation and color normalization of the histopathology images can be helped for both pathology and computerized decision support system. Quality performances of different color normalization methods are evaluate...

Applied Immunohistochemistry & Molecular Morphology, 2003

We tested a recently developed flexible method of separation and quantification of immunohistochemical staining by means of color image analysis. An algorithm was recently developed to deconvolve the color information acquired with RGB cameras, to calculate the contribution of each of the applied stains, based on the stain-specific RGB absorption. The algorithm was tested using a set of lung-tumor samples labeled for the detection of Ki-67, an antigen expressed in proliferating cells, covering a wide range of staining levels. Quantification of the labeling was compared with HSI-based segmentation and manual analysis of the same samples. The recently developed deconvolution method performed significantly better than the HSI based system when compared to manual counting as gold standard. The deconvolution system showed significantly reduced variability in the LI determination, especially of highly labeled control samples. This resulted in significant increase in sensitivity of classification of samples with increased KI-67 labeling without changing the specificity, when compared to the HSI based method.

Optical Review, 2005

Pathological images are color images of stained tissue slides, the color of which varies depending on staining conditions. For reliable diagnosis, the color variation must be corrected in these images. This paper proposes a color correction method for hematoxylin and eosin (H&E) stained pathological images in which the amounts of H&E dyes are estimated based on multispectral imaging technique and Beer Lambert law, and the color image is generated corresponding to the adjusted amount of dyes. This enables us to correct an image to an arbitrary or specified optimal staining-condition image. Through experiments using H&E stained human liver slide images, the effectiveness of the proposed method was confirmed.

Journal of Computer Science, 2009

Problem statement: A new color model for digital image was discussed; this model can be used to separate low and high frequencies in the image without loosing any information from the image. Approach: A comparative study between different color models (RGB, HSI) applied to a very large microscopic image analysis and the proposed model was presented. Such analysis of different color models is needed in order to carry out a successful detection and therefore a classification of different Regions of Interest (ROIs) within the image. Results: This, in turn, allows both distinguishing possible ROIs and retrieving their proper color for further ROI analysis. This analysis was not commonly done in many biomedical applications that deal with color images. Other important aspects were the computational cost of the different processing algorithms according to the color model. The proposed model took these aspects into consideration and the experimental results showed the advantages of proposed model compared with HSI model by decreasing the computational time for various image-processing operations. Conclusion: The proposed model can be used in different application such as separating low and high frequencies from the image.

Songklanakarin Journal of Science and Technology

This paper describes a simple yet effective algorithm for automatically counting stained breast cancer cell imagesbased on color contents. The procedure for the approach consists of four steps. First, the cancer cell image in red-greenblue(RGB) color space is transformed with Haar wavelet. Second, the wavelet transformed image is changed to gray-scaleimage. Next, the gray-scale image is segmented with global thresholding using Otsu’s method and morphological operationsusing opening, region filling, border clearing, and watershed segmentation. Third, the wavelet transformed image is changedto CIEL*a*b* color space. The feature, i.e. average value of b* of each isolated cell, is extracted. Finally, the classification isapplied by using the extracted feature. If the average value of b* is positive that indicates yellow, the cancer cell is a positivecell. In addition, if the average value of b* is negative that indicates blue, the cancer cell is a negative cell. Results show thatthe cla...

2008 IEEE International Conference on Automation, Quality and Testing, Robotics, 2008

In the context of he round table the following topics related to image colour processing will be discussed: Historical point of view. Studies of Aguilonius, Gerritsen, Newton and Maxwell. CIE Standard (Commission International de l'Eclaraige). Colour Models. RGB, HIS, etc. Colour segmentation based on HSI model. Industrial applications. Summary and discussion. At the end, video images showing the robustness of colour in front of B/W images will be presented.

Automated image processing and quantification are increasingly gaining attention in the field of digital pathology. However, a common problem that encumbers computerized analysis is the color variation in histology, due to the use of different microscopes/scanners, or inconsistencies in tissue preparation. In this paper, we present a novel color normalization technique to bring a histological image (source image) into a different color appearance of a second image (target image), which therefore standardizes the color representation of both images. In particular, by incorporating biological stainsparse regularized stain separation, our color normalization technique preserves the structural information of the source image after color normalization, which is very important for subsequent image analysis. Both qualitative and quantitative validation demonstrates the superior performance of our stain separation and color normalization techniques.

Diagnostic Pathology, 2013