Hue-saturation-density (HSD) model for stain recognition in digital images from transmitted light microscopy.

BACKGROUND Transmitted light microscopy is used in pathology to examine stained tissues. Digital image analysis is gaining importance as a means to quantify alterations in tissues. A prerequisite for accurate and reproducible quantification is the possibility to recognise stains in a standardised manner, independently of variations in the staining density. METHODS The usefulness of three colour models was studied using data from computer simulations and experimental data from an immuno-doublestained tissue section. Direct use of the three intensities obtained by a colour camera results in the red-green-blue (RGB) model. By decoupling the intensity from the RGB data, the hue-saturation-intensity (HSI) model is obtained. However, the major part of the variation in perceived intensities in transmitted light microscopy is caused by variations in staining density. Therefore, the hue-saturation-density (HSD) transform was defined as the RGB to HSI transform, applied to optical density values rather than intensities for the individual RGB channels. RESULTS In the RGB model, the mixture of chromatic and intensity information hampers standardisation of stain recognition. In the HSI model, mixtures of stains that could be distinguished from other stains in the RGB model could not be separated. The HSD model enabled all possible distinctions in a two-dimensional, standardised data space. CONCLUSIONS In the RGB model, standardised recognition is only possible by using complex and time-consuming algorithms. The HSI model is not suitable for stain recognition in transmitted light microscopy. The newly derived HSD model was found superior to the existing models for this purpose.

[1]  R. S. Longhurst Geometrical and Physical Optics , 1967 .

[2]  R. K. Aggarwal,et al.  A multi-spectral approach for scene analysis of cervical cytology smears. , 1977, The journal of histochemistry and cytochemistry : official journal of the Histochemistry Society.

[3]  Rafael C. González,et al.  Local Determination of a Moving Contrast Edge , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Jake K. Aggarwal,et al.  Segmentation of chromatic images , 1981, Pattern Recognit..

[5]  C Garbay,et al.  Application of colored image analysis to bone marrow cell recognition. , 1981, Analytical and quantitative cytology.

[6]  G Brugal,et al.  Image analysis of microscopic preparations. , 1984, Methods and achievements in experimental pathology.

[7]  H. Harms,et al.  Segmentation of stained blood cell images measured at high scanning density with high magnification and high numerical aperture optics. , 1986, Cytometry.

[8]  C MacAulay,et al.  Adaptive color basis transformation. An aid in image segmentation. , 1989, Analytical and quantitative cytology and histology.

[9]  P H Bartels,et al.  Image analysis in quantitative cytopathology and histopathology. , 1989, Human pathology.

[10]  Mehmet Celenk,et al.  A color clustering technique for image segmentation , 1990, Comput. Vis. Graph. Image Process..

[11]  I T Young,et al.  Towards a quantitative grading of bladder tumors. , 1991, Cytometry.

[12]  J. Figge,et al.  Image analysis quantitation of immunoreactive retinoblastoma protein in human thyroid neoplasms with a streptavidin-biotin-peroxidase staining technique. , 1991, The American journal of pathology.

[13]  M A Gerber,et al.  Colour thresholding and objective quantification in bioimaging , 1992, Journal of microscopy.

[14]  J M Lamaziere,et al.  Semiquantitative study of the distribution of two cellular antigens by computer-directed color analysis. , 1993, Laboratory investigation; a journal of technical methods and pathology.

[15]  F. Willemse,et al.  Image analysis in immunohistochemistry. Factors with a possible influence on the performance of VIDAS version 2.0, a commercially available true color image analysis system. , 1993, Analytical and quantitative cytology and histology.

[16]  M. Barbareschi,et al.  Quantitative growth fraction evaluation with MIB1 and Ki67 antibodies in breast carcinomas. , 1994, American journal of clinical pathology.

[17]  Immunohistochemical determination of nuclear antigens by colour image analysis: application for labelling index, estrogen and progesterone receptor status in breast cancer. , 1994, Analytical cellular pathology : the journal of the European Society for Analytical Cellular Pathology.

[18]  Dario Cabib,et al.  Spectral Karyotyping , 1997, Microscopy and Microanalysis.

[19]  MIB1, A PROMISING MARKER FOR THE CLASSIFICATION OF CERVICAL INTRAEPITHELIAL NEOPLASIA , 1996, The Journal of pathology.

[20]  H. Heinzl,et al.  Quantitative immunohistochemistry of factor VIII-related antigen in breast carcinoma: a comparison of computer-assisted image analysis with established counting methods. , 1996, American journal of clinical pathology.

[21]  J. L. Au,et al.  Application of automatic thresholding in image analysis scoring of cells in human solid tumors labeled for proliferation markers. , 1997, Cytometry.

[22]  P N Furness,et al.  The use of digital images in pathology , 1997, The Journal of pathology.

[23]  Ruifrok Ac QUANTIFICATION OF IMMUNOHISTOCHEMICAL STAINING BY COLOR TRANSLATION AND AUTOMATED THRESHOLDING , 1997 .

[24]  J. A. van der Laak,et al.  Quantitative analysis of microvascular changes in diffuse astrocytic neoplasms with increasing grade of malignancy. , 1998, Human pathology.

[25]  D J Ruiter,et al.  An improved procedure to quantify tumour vascularity using true colour image analysis. Comparison with the manual hot‐spot procedure in a human melanoma xenograft model , 1998, The Journal of pathology.