Introduction

Breast cancer is one of the most common cancers in women in the world. In 2015, an estimated 60,290 new cases of breast carcinoma were diagnosed in situ, 83% of which were ductal carcinoma in situ (DCIS) and 12% lobular carcinoma in situ (LCIS) [1-2]. Cancer begins when genes in a cell become abnormal and the cell starts to grow and divide out of control. Cancerous cells replicate much faster than normal healthy cells. It divides and multiply to form a tumour that may be benign (non-cancerous) and malignant (cancerous) [3].

Histopathological studies were still most reliable and effective technique in cancer research. Till now, analysis of histopathology images has been done manually via observing dysplastic appearances such as minute structures, distribution, finding of tubules, nuclei, regularities of cell shapes and size across the tissues by the pathologist to decide whether it is benign or malignant. The distortion in the shape of cells and change in the density of cluster of cells are the signatures of the occurrence of malignancy in body tissue [4- 6]. Pathologists face several problems while observing the histopathological image due to overlapping, blurriness, artifacts, weak boundary detection and uneven dying. Moreover, it is found that it was very time consuming and tedious process, and depend on perceptions and level of expertise of pathologists.  For cancer detection, morphological feature extraction is the main tool for analysing the cellular organization, abnormality, and changes in the physiological state of the cells [7-9].  Analysis of the cells based on their morphological differences was applied to study the differentiation of benign or malignant cells. A computer aided diagnosis system is proposed in this paper as a qualitative and quantitative tool for analysis and classification [10-11].  Several researches have analysed histopathology images that relates image analysis of cells morphology to the malignancy detection. A. Madabhushi observed the challenges in digital imaging has led to improvement in image analysis techniques resulting in improved opportunities to the pathologist for treatment of benign tissues [12]. A. D. Belsare et. al., worked on the tissue structure and presented cell distribution in a tissue, they described irregularities of the shapes of cells to determine the level of malignancy and benign in a histopathology images [13]. Bhattacharjee et al. presented a review of computer-aided diagnosis system to detect cancer from histopathology images using image processing method [14]. Demir et. al. presented on both tissue level and cellular level automatic diagnosis of biopsy image using image processing techniques, feature extraction and classification techniques [15]. S. Petushi obtained the intensity of the pixels that are registered and calculate the mean of the neighboring pixels [16]. Bergmeir.et. al. proposed a model to extract the various texture features are contrast, correlation, energy, homogeneity, gray level, and HSV by using local histograms and GLCM [17].

The aim of present paper work is to investigate robust and accurate image analysis algorithm for the purpose of detection of cancer cells using morphological and texture features (GLCM) extracted from the segmented histopathology images. In this work, diverse image processing techniques on histopathological images, breast cancer have been analysed. Differentiations of benign and malignant cells have been done in three steps:  pre-processing, segmentation and feature extraction.

The organization of this paper is as follows. Section 2 discusses methodology and proposed algorithm. Section 3 describes the results and Section 4 describes discussions, and Finally Section 5 draws the conclusion of the work presented in this paper.

Materials and Methods

Images collection

Histopathology breast cancer cell datasets used in present work have been taken from www.bioimage.ucsb.edu (Centre for Bio-image Informatics, University of California, Santabarbara (UCSB) for analysis. Microphotographs of breast cancer histopathology of total 58 images were taken, 26 out of which were malignant and 32 are benign. With the help of cropping histopathology images have been fragmented into single and group cells. A dataset of single cells consisting of 218 benign and 233 malignant and a dataset of group of cells consisting of 72 benign and 73 malignant were framed. Structural, intensity and textures based 30 features were used to distinguish between benign and malignant cells. The images which were acquired from histopathology breast cancer (UCSB) datasets were already stained to visualize various parts, cellular structures such as cells, nuclei and cytoplasm of the tissue certain special stains are used to bind selectively to particular components.The nuclei were stained blue with haematoxylin while cytoplasm and extra-cellular components were in pink due to eosin staining.

Experimental set up – Experiments have been implemented on a 3.40 GHz CPU with 4 GB RAM, 64 bits, Windows 7 operating system, with MATLAB has been used for the implementation. Figure 1 represents the flow chart of the proposed system and basic steps involved in the cell morphological analysis.

Figure 1: Schematic flowchart of the proposed method   Click here to View figure

A brief summary of the steps involved in the presented flow chart is given below.

Image pre-processing using median filter

The main purpose of the pre-processing stage was to reduce the background noise and to enhance the image to improve the image quality. In this paper, median filtering was implemented to preprocess the images to eliminate graininess. Basic fundamental of median filtering is that every output pixel comprises the median value in the 5-by-5 neighborhood around the equivalent pixel in the input image. The image was padded with zeros on the edges, so the median values for the points of 3 pixels of the edges may appear distorted. After that, the contrast is enhanced between the cytoplasm, nucleus and extracellular components using unsharp masking. The filter was applied to the image by subtracting the multiplied scaled factor, Gaussian filtered from the input image. A rotationally symmetric Gaussian low pass filter with a standard deviation of 50 pixels was used, with a total filter size of 15-by-15 pixels. The scaling factor was 0.35.

Segmentation

Segmentation is the process where an image is divided into the different regions on some similarity basis. The basic purpose of segmentation was extraction of important features from the image, from which information can easily be perceived.  The morphological appearance of structures like size, shape, and color intensity, are important factors for the identification of the cancer cells. To analyze all these indicators, images firstly should be segmented. In this paper for segmentation, band thresholding was implemented to group pixels lying in the cellular region. Basic morphological operations such as filling with holes, opening, closing dilation, erosion were done to plot the boundary of the cells [18-21]. This procedure provides user to see different outlined cells.  For implementing dilation, arbitrary sized structuring element has been used. Further, for erosion implemented disk sized structuring element has been used. The region of interest (ROI) i.e. the segmented cells were then considered for feature manipulation. Un-weighted centroid and the weighted centroid are marked by blue and red color boundary respectively. Standard deviation is then measured. After that, it is converted to gray level image, having one bounding box marked by yellow color [22-25].  Single cells and group of cells have been taken into account for segmentation and analysis. Figure 2 depicts the results obtained by implementing the steps discussed above.

Figure 2: Histopathology breast cancer images (a) benign cells (b) malignant cells. Selected ROI of cells in RGB (c)  benign single cell (d) malignant single cell (e) benign group cells (f) malignant group cells; (g), (h), (i), (j) Converted into gray scale image respectively. (k), (l), (m), (n), after band thresholding. (o), (p), (q), (r) distinct cells. (s), (t), (u), (v) Weighted (red) unweighted (blue) marked centroid. (W), (x), (y), (z) Cells in the bounding box. Click here to View figure

Extraction of morphological features

 The most significant portion of this work is the computation of features. To do the same, the total features of the particular ROI (region of interest) are extracted to distinguish different types of cells such as benign and malignant based on their structural, intensity, and texture features in single cells and group of cells were computed from the segmented cell images as shown in Table 1. Further, 30 features have been computed for the cells present in the image.

Table 1: The distribution of various features extracted from images and their ranges Click here to View table

Structure features

Structural features give information regarding the size and the shape of cells.  Features of benign and malignant cells are given in Table 2.

Table 2:Feature of cell in benign and malignant cells.   Click here to View figure

The quantification of these features help to differentiate the malignant cells from benign cells. Moreover, the statistics computed on these properties is used to identify cancer in a tissue. Structure based features used in this paper are the area, convex area, perimeter, major axis length, minor axis length, circularity, eccentricity and solidity  are explained in Table 3.

Table 3: Structure features   Click here to View figure

 Intensity features

Pixel based features provide information on the intensity (gray-level or color) histogram of the pixels located in cells. These features were extracted from the gray-level or color histogram of the image. This includes max intensity, min intensity, mean intensity and standard deviation are explained in Table 4. These types of features do not provide any information about the spatial division of the pixels.

Table 4: Intensity features

Texture features

The texture features provide information about the variation in the intensity of a surface and quantify properties such as regularity, coarseness, and smoothness. The texture is a connected set of pixels that repeatedly occur in an image. The texture analysis techniques based on the gray level co-occurrence matrix is applied to histopathological images analysis. It is an estimate of image properties related to second order statistics. The gray level co-occurrence matrix GLCM quantifies the various textural features such as autocorrelation, contrast, correlation, cluster prominence, dissimilarity, energy, entropy, homogeneity, maximum probability, sum of squares, sum of average, sum of  variance, sum of entropy, difference variance, difference entropy,  information measure of correlation 2, inverse difference normalized (INN) and inverse difference moment normalize etc. Some of them are described as below in Table 5.

Table 5: Texture features   Click here to View figure

Results

These features such as area, convex area, perimeter, major axis, minor axis, circularity, eccentricity, max intensity, mean intensity, solidity, autocorrelation, cluster prominence, sum of squares, sum of average, sum of variance, contrast, sum of entropy, and information measure of correlation 2 yielded significant differentiation between benign and malignant cells into single cells and group cells.  The reasons for choosing group of cells over single cells are to produce accurate result. The variations of values of various features for single cells and group cells to differentiate benign cells and malignant cells are shown in Figure 3 to Figure 6. These features result shows that malignant cells are having greater magnitude of shape based features in comparison to benign cells, and there was variation in other features values. All the malignant cells in the single cells and group were having increase size (area, convex area, perimeter, major axis, minor axis) elongated shape (circularity, eccentricity) and greater magnitude of the maximum and mean intensity. These size, shape and intensity based feature were significant for the differentiation point of view for single cells and group cells. Some of the features have an insignificant relation and minor difference such as standard deviation, minimum intensity and correlation features are insignificant for the differentiation point of view in both cases in single cells and group of cells as they are having almost analogous values, as presented in the table 6. Dissimilarity, energy, entropy, homogeneity, maximum probability difference variance, difference entropy, inverse difference normalized (INN) and inverse difference moment normalizes features are significant in single cells only and insignificant in group cells. Texture feature of group cells does not belong to each single cell belong to the group it takes as a whole image. Cluster prominence feature is insignificant in single cells and significant in group cells.

Figure 3: Variations of values of various features for (a) single cell (b) group cells for breast cancer.   Click here to View figure

Figure 4: Variations of values of various features for (a) single cell (b) group cells for breast cancer.     Click here to View figure

Figure 5: Variations of values of various features for (a) single cell (b) group cells.   Click here to View figure

Figure 6: Variations of values of various features for (a) single cell (b) group cells.   Click here to View figure

Table 6: Comparative parameter of single cells and group cells of benign and malignant cells of breast cancer image.

The results presented here are expressed as Mean ± S.D. Statistical analysis has been performed using Graph Pad Prism software (version 5.1). To perform unpaired, two-tailed students t-tests, p-value < 0.05 was used for significance.

Discussion

In this work, morphological features of breast cancer cells have been calculated in benign and malignant cells. Structure based features of malignant cells show greater magnitude such as area, perimeter, major axis, and minor axis etc. in comparison to benign cells as shown in figures 3 to 6. Main reasons for this outcomes that benign cells grow and divide when they receive signals from the surrounding cells and does not exhibit contact inhibition phenomenon while malignant cells have uncontrolled cell division and grow faster. Benign cells undergo through ageing and senescence process, as well as repair their physiological and chromosomal abnormalities (e.g. apoptosis) while malignant cells show neither repair nor induce apoptosis. Benign cells become specialized or mature so that they are able to carry out their function in the body. While malignant cells often reproduce very quickly and do not exhibit mature phenotypes.

Further, shape based two feature circularity and eccentricity of the cells, has been taken into consideration. When shape factor circularity is taken which lies between 0 and 1. As we know that the value is 1 that the object is a perfect circle. In our case, for benign cells, it is found to be nearly 1 i.e. 0.94 shows that, it circular in structure as compare to malignant cell nearly to 0 i.e., 0.84 have not circular structure. The eccentricity of an ellipse gives a measure of just how squashed it is. If the eccentricity is 0, it is not squashed at all and so remain a circle. If it is 1 it is completely squashed and look like a line. As per consideration of eccentricity, it is found to be nearly 1 i.e. 0.7 shows that malignant cell have elongated structure and in concern to benign it is about 0.5 that shows circular structure as shown in Table 6. The main cause of the results obtained as  malignant cells images have generally elongated, distorted or blebs shape of cells that become physiologically non functional such types of shape is useful for a malignant cells to exhibit random migration i.e. metastasis. In normal tissues, the cells stay together adheres to each other through specific microstructures that assist in governing the cellular function.

Our report is in agreement with several authors  Kasmin et al. extracted the features of microscopic biopsy images including area, perimeter, convex area, solidity, major axis length, eccentricity, ratio of cell and nucleus area, circularity, and mean intensity of cytoplasm [26]. Basavanhally et al. quantification of the morphological features and the classify their structure in a histopathological slide image leading to discrimination of a cell into a particular class for the purpose of diagnosis has been shown [27]. Sinha et al. extracted some features of histopathology images contain area of cells, area ratio, eccentricity, compactness, average values of color components, energy, correlation, and entropy [28].

In concern to pixel-based features, max intensity and mean intensity pixel values were found to be higher and diverse in malignant cells as compared to benign where max intensity pixel values found to be almost identical to normal cells and as shown in the table1. Intensity based some of features such as standard deviation and minimum intensity have been found insignificant in both case benign and malignant. The possible reason for this observation is that the presence of high amount of DNA (deoxyribose nucleic acids) or  increase in the amount of nucleoprotein synthesis in the malignant cells, resulting in larger nucleolus and dark-staining nuclei referred as hyperchromatism as seen under a microscope. Thiran, et. al. and Zhao et. al. authors also worked on the pixel of the benign and malignant nucleus in comparable to them [29-30].  C. Demir et al., the intensity based approach is employed to calculate the intensity value of pixels to define the features in a histopathological slide image [14].

Texture based feature are also helpful in distinguishing between benign and malignant cells [31-33]. Hamilton et. al. employed texture analysis to develop criteria for the automatic identification of colorectal dysplasia from a background through focal areas of histologically normal tissue [34]. Mouelhi et al. classify the cancerous cells from microscopic biopsy images by using Haralick’s textures features, color component and histogram of oriented gradients (HOG), based statistical moments (CCSM) feature selection and extraction approaches [35]. In our implementation computed texture features can also depicts the difference between benign and malignant cells as give in Figure 5 and 6.

Conclusion and Future works

In this paper, histopathological cellular image of suspected breast cancer have been analyzed using structure, intensity and texture based morphological features. The developed algorithm for automated analysis and evaluation of histopathology images will assist the pathologists and result in reduction in human error. Such automated cancer diagnosis facilitates objective mathematical judgment complementary to pathologist. The future work would be to include more features in the algorithm for efficient differentiation between benign and malignant cancer cells so that suitable classifiers may be designed.

Conflict of Interests

 The authors declare that there is no conflict of interests regarding the publication of this paper.

 Acknowledgments

 The first author gratefully acknowledge financial assistance in the form of Rajiv Gandhi National Fellowship.

References

1. Chen, J. M., Qu, A. P., Wang, L. W., Yuan, J. P., Yang, F., Xiang, Q. M. and Li, Y., 2015. New breast cancer prognostic factors identified by computer-aided image analysis of HE stained histopathology images. Scientific reports, 5.
2.  Siegel, R.L., Miller, K.D. and Jemal, A., 2015. Cancer statistics, 2015. CA: a cancer journal for clinicians, 65(1), pp.5-29.
3. Rubin, R., Strayer, D.S. and Rubin E. 2008 Rubin′s Pathology, Clinicopathologic Foundations of Medicine. Philadelphia: Lippincott Williams and Wilkins.
4. Veta, M., Pluim, J.P., van Diest, P.J. and Viergever, M.A., 2014. Breast cancer histopathology image analysis: A review. Biomedical Engineering, IEEE Transactions on, 61(5), pp.1400-1411.
5. Chen, S., Zhao, M., Wu, G., Yao, C. and Zhang, J., 2012. Recent advances in morphological cell image analysis. Computational and Mathematical Methods in Medicine.
6. Liu, B., Yin, C., Liu, Z., Zhang, Z., Gao, J., Zhu, M., Gu, J. and Xu, K., 2007. Microscopic image analysis and recognition on pathological cells. Proceeding of Electrical and Computer Engineering, Canada, 22-26, pp.1022-1025.
7. Zhang, X., Liu, W., Dundar, M., Badve, S. and Zhang, S., 2015. Towards large-scale histopathological image analysis: Hashing-based image retrieval. Medical Imaging, IEEE Transactions on, 34(2), pp.496-506.
8. Zhang, X., Su, H., Yang, L. and Zhang, S., 2015. Fine-grained histopathological image analysis via robust segmentation and large-scale retrieval. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; pp. 5361-5368.
9. Gurcan, M.N., Boucheron, L.E., Can, A., Madabhushi, A., Rajpoot, N.M. and Yener, B., 2009. Histopathological image analysis: A review. Biomedical Engineering, IEEE Reviews in, 2, pp.147-171.
10. Cui, Y., Jin, J.S., Park, M., Luo, S., Xu, M., Peng, Y., Wong, W.F. and Santos, L.D., 2010. Computer aided abnormality detection for microscopy images of cervical tissue. In Complex Medical Engineering (CME), 2010 IEEE/ICME International Conference on (pp. 63-68). IEEE.
11. Mulrane, L., Rexhepaj, E., Penney, S., Callanan, J. J., Gallagher, W. M., 2008. Automated image analysis in histopathology: a valuable tool in medical diagnostics.
12. Madabhushi A. 2009. Digital pathology image analysis: opportunities and challenges, Imaging in medicine, 1:1pp.7-10.
13. Belsare, A. D. and Mushrif, M. M., 2012. Histopathological image analysis using image processing techniques: An overview. Signal, Image Processing, 3(4): 23.
14. Bhattacharjee, S., Mukherjee, J., Nag, S., Maitra, I. K. and Bandyopadhyay, S. K., 2014. Review on Histopathological Slide Analysis using Digital Microscopy. International Journal of Advanced Science and Technology, 62: pp.65-96.
15. Demir C. and Yener B., 2005. Automated cancer diagnosis based on histopathological images: a systematic survey. Rensselaer Polytechnic Institute, Tech. Rep.
16. Petushi, S., Garcia, F.U., Haber, M.M., Katsinis, C. and Tozeren, A., 2006. Large-scale computations on histology images reveal grade-differentiating parameters for breast cancer. BMC Medical Imaging, 6(1), pp.14.
17. Bergmeir, C. Silvente, M. G. and Ben´ıtez, J. M., 2012. Segmentation of cervical cell nuclei in high-resolution microscopic images: a new algorithm and a web-based software framework,Computer Methods and Programs in Biomedicine, vol. 107, no. 3, pp. 497–512.
18. Sharma, N., Ray, A. K., Sharma, S., Shukla, K. K., Aggarwal, and L., Pradhan, S., 2009. Segmentation of medical images using simulated annealing based fuzzy C Means algorithm. International Journal of Biomedical Engineering and Technology,2(3):pp. 260-278.
19. Xu, J., Agner, S. C., and Madabhushi, A., 2013. Spectral embedding based active contour (SEAC) for lesion segmentation on breast dynamic contrast enhanced magnetic resonance imaging. Medical physics, 40 (3), 032305.
20. Naik, S., Doyle, S., Agner, S., Madabhushi, A., Feldman, M. and Tomaszewski, J., 2008. Automated gland and nuclei segmentation for grading of prostate and breast cancer histopathology. In Biomedical Imaging: From Nano to Macro, 2008. ISBI 2008. 5th IEEE International Symposium on (pp. 284-287). IEEE.
21. Vahadane, Abhishek, and Sethi, A., 2013. Towards generalized nuclear segmentation in histological images. Bioinformatics and Bioengineering (BIBE), 2013 IEEE 13th International Conference on. IEEE.
22. Chaddad, A., Tanougast, C., Dandache, A., and Bouridane, A., 2011. Classification of cancer cells based on morphological features from segmented multispectral bio-images. In 4th International Conference on Biomedical Electronics and Biomedical Informatics (pp. 92-97).
23. Zhao, M., Chen, L., Bian, L., Zhang, J., Yao, C. and Zhang, J., 2015. Feature Quantification and Abnormal Detection on Cervical Squamous Epithelial Cells. Computational and mathematical methods in medicine.
24. Esgiar, A.N., Naguib, R.N., Sharif, B.S., Bennett, M.K. and Murray, A., 1998. Microscopic image analysis for quantitative measurement and feature identification of normal and cancerous colonic mucosa. Information Technology in Biomedicine, IEEE Transactions on, 2(3), pp.197-203.
25. Liu, B., Yin, C., Liu, Z., Zhang, Z., Gao, J., Zhu, M., Gu, J. and Xu, K., 2007. Microscopic image analysis and recognition on pathological cells. Proceeding of Electrical and Computer Engineering, Canada, 22-26, 1022-1025.
26. F. Kasmin, A. S. Prabuwono, and A. Abdullah., 2012. Detection of leukemia in human blood sample based on microscopic images: a study. Journal of Theoretical & Applied Information Technology, vol. 46, no. 2.
27. Basavanhally, A.N., Ganesan, S., Agner, S., Monaco, J.P., Feldman, M.D., Tomaszewski, J.E., Bhanot, G. and Madabhushi, A., 2010. Computerized image-based detection and grading of lymphocytic infiltration in HER2+ breast cancer histopathology. Biomedical Engineering, IEEE Transactions on, 57(3), pp.642-653.
28. Sinha N., and Ramkrishan, A. G., 2003. Automation of differential blood count, in Proceedings of the Conference on Convergent Technologies for Asia-Pacific Region (TINCON ’03), pp. 547–551, Bangalore, India.
29. Thiran, J. P., and Macq, B., 1996. Morphological feature extraction for the classification of digital images of cancerous tissues. Biomedical Engineering, IEEE Transactions on, 43(10), 1011-1020.
30. Zhao, T., and Murphy, R. F., 2007. Automated learning of generative models for subcellular location: building blocks for systems biology. Cytometry Part A, 71(12), 978-990.
31. Chaddad, A., Tanougast, C.A.M.E.L., Dandache, A. and Bouridane, A.H.M.E.D., 2011. Extracted haralick’s texture features and morphological parameters from segmented multispectrale texture bio-images for classification of colon cancer cells. WSEAS Transactions on Biology and Biomedicine, 8(2), pp.39-50.
32. R. M. Haralick, K. Shanmugam, and I. Dinstein., 1973.Textural features for image classification, IEEE Transactions on Systems, Man and Cybernetics, vol. 3, no. 6, pp. 610–621.
33. Doyle, S., Agner, S., Madabhushi, A., Feldman, M. and Tomaszewski, J., 2008. Automated grading of breast cancer histopathology using spectral clustering with textural and architectural image features. In Biomedical Imaging: From Nano to Macro, 2008. ISBI 2008. 5th IEEE International Symposium on pp. 496-499, IEEE.
34. Hamilton, P., Wang, Y., Crookes, D., Diamond, J., and Turner, R., 2007. Segmentation of squamous epithelium from ultra-large cervical histological virtual slides. In Engineering in Medicine and Biology Society, 2007. EMBS 2007. 29th Annual International Conference of the IEEE (pp. 775-778). IEEE
35. Mouelhi, M., Sayadi, F., Fnaiech, K. M., and K. B. Romdhane., 2013. Automatic image segmentation of nuclear stained breast tissue sections using color active contour model and an improved watershed method. Biomedical Signal Processing and Control, vol. 8, no. 5, pp. 421–436.