Segmentation of epidermal tissue with histopathological damage in images of haematoxylin and eosin stained human skin

BMC Medical Imaging

Elaine B Martin²  Chris J O’Malley²  Anne Dickinson³  Xiao N Wang³  Juliana M Haggerty¹ 

[1] Alcyomics Ltd. Framlington Place, Newcastle-upon-Tyne, UK;Biopharmaceutical Bioprocessing Technology Centre, Chemical Engineering and Advanced Materials, Newcastle University, Newcastle-upon-Tyne, UK;Institute of Cellular Medicine, Newcastle University, Newcastle-upon-Tyne, UK

关键词: Design of experiments;    Classification;    Mathematical morphology;    Colour space;    Epidermis;    Segmentation;    Histopathological damage;    Histopathology;   

Others  :  849132
DOI  :  10.1186/1471-2342-14-7

 received in 2013-09-24, accepted in 2014-02-03,  发布年份 2014

【 摘 要 】

Background

Digital image analysis has the potential to address issues surrounding traditional histological techniques including a lack of objectivity and high variability, through the application of quantitative analysis. A key initial step in image analysis is the identification of regions of interest. A widely applied methodology is that of segmentation. This paper proposes the application of image analysis techniques to segment skin tissue with varying degrees of histopathological damage. The segmentation of human tissue is challenging as a consequence of the complexity of the tissue structures and inconsistencies in tissue preparation, hence there is a need for a new robust method with the capability to handle the additional challenges materialising from histopathological damage.

Methods

A new algorithm has been developed which combines enhanced colour information, created following a transformation to the L*a*b* colourspace, with general image intensity information. A colour normalisation step is included to enhance the algorithm’s robustness to variations in the lighting and staining of the input images. The resulting optimised image is subjected to thresholding and the segmentation is fine-tuned using a combination of morphological processing and object classification rules. The segmentation algorithm was tested on 40 digital images of haematoxylin & eosin (H&E) stained skin biopsies. Accuracy, sensitivity and specificity of the algorithmic procedure were assessed through the comparison of the proposed methodology against manual methods.

Results

Experimental results show the proposed fully automated methodology segments the epidermis with a mean specificity of 97.7%, a mean sensitivity of 89.4% and a mean accuracy of 96.5%. When a simple user interaction step is included, the specificity increases to 98.0%, the sensitivity to 91.0% and the accuracy to 96.8%. The algorithm segments effectively for different severities of tissue damage.

Conclusions

Epidermal segmentation is a crucial first step in a range of applications including melanoma detection and the assessment of histopathological damage in skin. The proposed methodology is able to segment the epidermis with different levels of histological damage. The basic method framework could be applied to segmentation of other epithelial tissues.

【 授权许可】

   
2014 Haggerty et al.; licensee BioMed Central Ltd.

【 图 表 】

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Figure 7.

Figure 8.

Figure 9.

Figure 10.

Figure 11.

Figure 12.

【 参考文献 】

• [1]Rubin R, Strayer D, Rubin E, McDonald J: Rubin’s Pathology: Clinicopathologic Foundations of Medicine. 5th edition. Baltimore: Lippincott Williams & Wilkins; 2007.
• [2]Ismail SM, Colclough AB, Dinnen JS, Eakins D, Evans DMD, Gradwell E, O’Sullivan JP, Summerell JM, Newcombe R: Reporting cervical intra-epithelial neoplasia (CIN): intra- and interpathologist variation and factors associated with disagreement. Histopathology 1990, 16(4):371-376.
• [3]Allsbrook WC Jr, Mangold KA, Johnson MH, Lane RB, Lane CG, Epstein JI: Interobserver reproducibility of Gleason grading of prostatic carcinoma: general pathologist. Hum Pathol 2001, 32(1):81-88.
• [4]Brochez L, Verhaeghe E, Grosshans E, Haneke E, Pierard G, Ruiter D, Naeyaert JM: Inter-observer variation in the histopathological diagnosis of clinically suspicious pigmented skin lesions. J Pathol 2002, 196(4):459-466.
• [5]Melia J, Moseley R, Ball RY, Griffiths DF, Grigor K, Harnden P, Jarmulowicz M, McWilliam LJ, Montironi R, Waller M, Moss S, Parkinson MC: A UK-based investigation of inter- and intra-observer reproducibility of Gleason grading of prostatic biopsies. Histopathology 2006, 48(6):644-654.
• [6]Gurcan MN, Boucheron LE, Can A, Madabhushi A, Rajpoot NM, Yener B: Histopathological image analysis: a review. IEEE Rev Biomed Eng 2009, 2:147-171.
• [7]Naik J, Doyle S, Basavanhally A, Ganesan S, Feldman MD, Tomaszewski JE, Madabhushi A: A boosted distance metric: application to content based image retrieval and classification of digitized histopathology. In Medical Imaging 2009: Computer-Aided Diagnosis, Volume 7260. Edited by Karssemeijer N, Giger ML. Lake Buena Vista, FL, USA: SPIE; 2009:72603F.
• [8]Magee D, Treanor D, Crellin D, Shires M, Smith K, Mohee K, Quirke P: Colour Normalisation in Digital Histopathology Images. In Proc Optical Tissue Image analysis in Microscopy, Histopathology and Endoscopy (MICCAI Workshop). London: Daniel Elson; 2009:100-111.
• [9]Hafiane A, Bunyak F, Palaniappan K: Fuzzy clustering and active contours for histopathology image segmentation and nuclei detection. In 10th International Conference on Advanced Concepts for Intelligent Vision Systems: 2008. Juan-les-Pins, France: Springer Berlin Heidelberg; 2008:903-914.
• [10]Naik S, Doyle S, Agner S, Madabhushi A, Feldman M, Tomaszewski J: Automated gland and nuclei segmentation for grading of prostate and breast cancer histopathology. IEEE International Symposium on Biomedical Imaging: From Nano to Macro (IBSI 2008, 284-287.
• [11]Gerger A, Smolle J: Diagnostic tissue elements in melanocytic skin tumors in automated image analysis. Am J Dermatopathol 2003, 25(2):100-106.
• [12]Jondet M, Agoli-Agbo R, Dehennin L: Automatic measurement of epithelium differentiation and classification of cervical intraneoplasia by computerized image analysis. Diagn Pathol 2010, 5:7. BioMed Central Full Text
• [13]Glotsos D, Spyridonos P, Cavouras D, Ravazoula P, Dadioti PA, Nikiforidis G: Automated segmentation of routinely hematoxylin-eosin-stained microscopic images by combining support vector machine clustering and active contour models. Anal Quant Cytol Histol 2004, 26(6):331-340.
• [14]Kong H, Gurcan M, Belkacem-Boussaid K: Partitioning histopathological images: an integrated framework for supervised color-texture segmentation and cell splitting. IEEE Trans Med Imaging 2011, 30(9):1661-1677.
• [15]Boucheron LE, Bi Z, Harvey NR, Manjunath B, Rimm DL: Utility of multispectral imaging for nuclear classification of routine clinical histopathology imagery. BMC cell biology 2007, 8(Suppl 1):S8. BioMed Central Full Text
• [16]Sahoo PK, Soltani S, Wong AKC: A survey of thresholding techniques. Comput Vision Graphics Image Proc 1988, 41(2):233-260.
• [17]Sezgin M, Sankur B: Survey over image thresholding techniques and quantitative performance evaluation. J Electron Imaging 2004, 13(1):146-168.
• [18]Canny J: A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 1986, PAMI-8(6):679-698.
• [19]Kass M, Witkin A, Terzopoulos D: Snakes: active contour models. Int J Comp Vision 1988, 1(4):321-331.
• [20]Prewitt JMS, Mendelsohn ML: The analysis of cell images. Ann N Y Acad Sci 1966, 128(3):1035-1053.
• [21]Ridler TW, Calvard S: Picture thresholding using an iterative slection method. IEEE Trans Systems, Man Cybernetics 1978, SMC-8(8):630-632.
• [22]Trussell HJ: Comments on “Picture thresholding using an iterative selection method”. Syst Man Cyb, IEEE T 1979, 9(5):311-311.
• [23]Otsu O: A threshold selection method from gray-level histogram. IEEE Trans Syst Man Cybern 1979, 9(1):62-66.
• [24]Petushi S, Katsinis C, Coward C, Garcia F, Tozeren A: Automated identification of microstructures on histology slides. IEEE Int Sym Biomed Imaging From Nano to Macro 2004, 1:424-427.
• [25]Wang Y, Crookes D, Diamond J, Hamilton P, Turner R: Segmentation of squamous epithelium from ultra-large cervical histological virtual slides. Conf Proc IEEE Eng Med Biol Soc 2007, 2007:775-778.
• [26]Datar M, Padfield D, Cline H: Color and texture based segmentation of molecular pathology images using HSOMS. IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI): 2008 2008, 292-295.
• [27]Eramian M, Daley M, Neilson D, Daley T: Segmentation of epithelium in H&E stained odontogenic cysts. J Microsc 2011, 244(3):273-292.
• [28]Sviland L, Hromadnikova I, Sedlacek P, Cermakova M, Stechova K, Holler E, Eissner G, Schulz U, Kolb HJ, Jackson G, Wang XN, Dickinson AM: Histological correlation between different centers using the skin explant model to predict graft-versus-host disease following bone marrow transplantation. Hum Immunol 2001, 62(11):1277-1281.
• [29]Haralick RM, Sternberg SR, Zhuang X: Image analysis using mathematical morphology. IEEE Tran on Pat Anal Mach Intell 1987, PAMI-9(4):532-550.
• [30]Matheron G: Random Sets and Integral Geometry. New York: Wiley; 1975.
• [31]Sviland L, Dickinson AM: A human skin explant model for predicting graft-versus-host disease following bone marrow transplantation. Clin Pathol 1999, 52:910-913.
• [32]Soille P: Morphological Image Analysis: Principles and Applications. New York: Springer-Verlag; 1999.