Cell nuclei extraction from breast cancer histopathologyimages using colour, texture, scale and shape information
© Veillard et al; licensee BioMed Central Ltd. 2013
Published: 30 September 2013
Standard cancer diagnosis and prognosis procedures such as the Nottingham Grading System for breast cancer incorporate a criterion based on cell morphology known as cytonuclear atypia. Therefore, algorithms able to precisely extract the cell nuclei are a requirement in computer-aided diagnosis applications.
Materials and methods
We propose a method based on the creation of a new image modality consisting in a grayscale map where the value of each pixel indicates its probability of belonging to a cell nuclei. This probability map is calculated from texture and scale information in addition to simple pixel color intensities. The resulting modality has a strong object-background contrast and evens out the irregularities within the nuclei or the background. The actual extraction is performed using an AC model with a nuclei shape prior included to deal with overlapping nuclei.
First, a color deconvolution  is applied in order to separate the immunohistochemical stains from which 3 grayscale images are produced: a haematoxilin image, an eosin image and a third residual component orthogonal in RGB space. Next, local features based on Laws’ texture measures  are computed for each pixel of the 3 obtained images. 5 different 1-dimensional convolution kernels (L5 = (1, 4, 6, 4, 1), E 5 = (–1, –2, 0, 2, 1), W 5 = (–1, 2, 0, –2, 1), S 5 = (–1, 0, 2, 0, –1) and R 5 = (1, –4, 6, –4, 1)) are used to compute 25 different 5 × 5 kernels by convolving avertical 1-dimensional kernel with a horizontal one. The 5 × 5 kernels are applied at every pixel to extract 25 features which are then combined into 15 rotationally invariant features after normalizing by the output of the L 5 T × L 5 kernel and smoothing with a Gaussian kernel of standard deviation σ = 1.5 pixels.
The same process is repeated at 4 different scales after locally re-sampling the image using Lanczos-3 sinc kernels. Re-sampled images are locally computed around each pixel to allow the computation of the 15 texture features for the same pixel at different scales. Local texture features are computed at 1:1, 1:2, 1:4 and 1:8 scales for every pixel.
The resulting probability map exhibits strong contrast between the objects and the background. Moreover, nuclei and background appear more homogeneous than in the original image. A post processing step is also applied to fill small holes still remaining in nuclei (larger holes are not removed to prevent the unintended deletion of interstices between different nuclei).
AC model including shape prior
The actual extraction of cell nuclei is performed from the probability map with an AC model with shape prior information. The total energy E(γ) associated to a contour γ is a weighted sum of an image term E i (γ) and a shape term E s (γ). The latter is itself the weighted sum of a smoothing term E sm (γ) and a shape prior term E sp (γ).
The shape prior term allows to control the perturbations δr(t) of a contour around a circle at different frequencies k of the Fourier components by adjusting the coefficients f k . Detailed formulas and explanations for this and the other energy terms can be found in the work of Kulikova et al. . The shape prior information allows to properly extract overlapping nuclei according to their expected shape without arbitrarily discarding the overlapping parts.
The detection of nuclei is performed by a marked point process model the details about which the interested reader can find in . An empirical study in  shows that this particular combination of MPP and AC over-performs other state-of-the-art methods for nuclei detection and extraction.
Results and discussion
The training set used for the LDA consists of 6 1024×1024 images where the nuclei have been manually delineated by a pathologist. Object and background parameters used in the AC model are also calculated from the training set. Weight parameters for the energy terms in the AC model are adjusted with a grid search. Images used for training are distinct from the images used for validation.
- Ruifrok AC, Johnston DA: Quantification of histochemical staining by color deconvolution. Analytical and Quantitative Cytology and Histology. 2001, 23: 291-299.PubMedGoogle Scholar
- Laws K: Textured image segmentation. PhD thesis. 1980, University of Southern CaliforniaGoogle Scholar
- Kulikova M, Jermyn I, Descombes X, Zhizhina E, Zerubia J: A marked point process model with strong prior shape information for extraction of multiple, arbitrarily-shaped objects. Proc. Signal-Image Technology and Internet-Based Systems. 2009Google Scholar
- Descombes X, Minlos R, Zhizhina E: Object extractionusing a stochastic birth-and-death dynamics in continuum. J. Math. Imaging Vis. 2009, 33 (3): 347-359. 10.1007/s10851-008-0117-y.View ArticleGoogle Scholar
- Kulikova MS, Veillard A, Roux L, Racoceanu D: Nuclei extraction from histopathological images using a marked point process approach. Proc. SPIE Medical Imaging, San Diego, California, USA. 2012Google Scholar
- Dalle J, Li H, Huang CH, Leow W, Racoceanu D, Putti TC: Nuclear pleomorphism scoring by selective cell nuclei detection. Proc. Workshop on Applications of Computer Vision. 2009Google Scholar
This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.