Colour normalisation of histopathological images

Abstract

Colour transfer is a prime area of research in image processing in recent years. In many real-life image applications, colour transfer of the image is required. A few methods have been developed to alter the colour appearance of the images as per the colour information of the reference image. Histopathological image analysis is one of the application areas where colour transfer method can be used to reduce the effect of varying staining and illuminance. This paper proposes a hybrid method of colour normalisation using modified non-negative matrix factorisation (NMF) and novel colour transfer method. The NMF method has been initialised using Lab colour space which provides fast and reliable results. Uncorrelated color space has been used to transfer the colour of target image to source image. The results show that the proposed method outperforms the considered existing methods and can successfully be applied for the colour normalisation of histopathological images.

A Complete Color Normalization Approach to Histopathology Images Using Color Cues Computed From Saturation-Weighted Statistics

“…In Eqn. (18) and Eqn. (19), saturation values are used as filter parameters and resulting representative colors bias saturated image colors.…”

“…For accurate estimation, spectra of chemical stains were detected using dedicated hardware [20], [13]; whereas dependence on devices limited their adoption. Later, NMF was used for spectral estimation [24], [18]. Since both works don't address an inconsistent convergence issue, stain decomposition may converge to any local minima, leading to wrong estimation.…”

“…For one thing, manual segmentation of images in large datasets is infeasible; For another, segmentation achieved by hard pixel classification is not reliable because one pixel in a histo-pathology image may belong to multiple objects due to histological component overlap. Hence, soft pixel classification by stain decomposition was proposed to precede color transfer [11], [18]. An improved normalization method based on work [11] was proposed in [12].…”

A hybrid approach for stain normalisation in digital histopathological images

“…The effectiveness of NMF in analyzing real-life non-negative data has sparked a substantial amount of research in image analysis. In image analysis, NMF and related techniques have been applied to different kinds of imaging(such as remote sensed images, medical images(such as histology images, CT images, MRI images), and natural images) during feature extraction [80,56,53,92,48], image classification [26,76,99,5], image ranking [82,14], image reconstruction [17,16,7], and image enhancement [43,22,42,100,85,86,54,41,42,73,87]. However, NMF, is less utilised during image enhancement of medical images, in particular histology imaging, which is affected by colour variation problem.…”

Gabased Digital Image Watermarking For Enhanced Robustness and Imperceptibility

“…however, there exist some un compared color models such UCS, etc. [25], [26],which may be used in color image watermarking to increase the durability and resolution by using all the color image components of host images, Saraswat and Arya [26] used UCS for color transfer of images and detected that UCS outperforms the other un corresponded color spaces. In the proposed scheme is combining DWT and SVD with genetic algorithm to find the optimal scaling factor and embed the singular value of watermark in singular value of 3 rd -level DWT approximation matrix of original image.…”