The structure/function relationship is fundamental to our understanding of biological systems at all levels, and drives most, if not all, techniques for detecting, diagnosing, and treating disease. However, at the tissue level of biological complexity we encounter a gap in the structure/function relationship: having accumulated an extraordinary amount of detailed information about biological tissues at the cellular and subcellular level, we cannot assemble it in a way that explains the correspondingly complex biological functions these structures perform. To help close this information gap we define here several quantitative temperospatial features that link tissue structure to its corresponding biological function. Both histological images of human tissue samples and fluorescence images of three-dimensional cultures of human cells are used to compare the accuracy of in vitro culture models with their corresponding human tissues. To the best of our knowledge, there is no prior work on a quantitative comparison of histology and in vitro samples. Features are calculated from graph theoretical representations of tissue structures and the data are analyzed in the form of matrices and higher-order tensors using matrix and tensor factorization methods, with a goal of differentiating between cancerous and healthy states of brain, breast, and bone tissues. We also show that our techniques can differentiate between the structural organization of native tissues and their corresponding in vitro engineered cell culture models.
References
[1]
Gunduz C, Yener B, Gultekin SH (2004) The cell graphs of cancer. Bioinformatics 20: i145–i151.
[2]
Street WN, Wolberg WH, Mangasarian OL (1993) Nuclear feature extraction for breast tumor diagnosis. IS&T/SPIE 1993 International Symposium on Electronic Imaging: Science and Technology. 1905:861–870, San Jose, CA.
[3]
Wolberg WH, Street WN, Heisey DM, Mangasarian OL (1995) Computer-derived nuclear features distinguish malignant from benign breast cytology. Human Pathology 26(7): 792–796.
[4]
Thiran JP, Macq B (1996) Morphological feature extraction for the classification of digital images of cancerous tissues. IEEE Transactions on Biomedical Engineering 43(10): 1011–1020.
[5]
Blekas K, Stafylopatis A, Kontoravdis D, Likas A, Karakitsos P (1998) Cytological diagnosis based on fuzzy neural networks. Journal of Intelligent Systems 8: 55–79.
[6]
Spyridonos P, Ravazoula P, Cavouras P, Berberidis K, Nikiforidis G (2001) Computer-based grading of haematoxylin-eosin stained tissue sections of urinary bladder carcinomas. Medical Informatics & The Internet in Medicine 26(3): 179–190.
[7]
Choi HK, Jarkrans T, Bengtsson E, Vasko J, Wester K, et al. (1997) Image analysis based grading of bladder carcinoma. Comparison of object, texture and graph based methods and their reproducibility. Analytical Cellular Pathology 15: 1–18.
[8]
Weyn B, van de Wouwer G, Kumar-Singh S, van Daele A, Scheunders P, et al. (1999) Computer-assisted differential diagnosis of malignant mesothelioma based on syntactic structure analysis. Cytometry 35: 23–29.
[9]
Wiltgen M, Gerger A, Smolle J (2003) Tissue counter analysis of benign common nevi and malignant melanoma. International Journal of Medical Informatics 69(1): 17–28.
[10]
Schnorrenberg F, Pattichis CS, Schizas CN, Kyriacou K, Vassiliou M (1996) Computer-aided classification of breast cancer nuclei. Technology and Health Care 4(2): 147–161.
[11]
Zhou ZH, Jiang Y, Yang YB, Chen SF (2002) Lung cancer cell identification based on artificial neural network ensembles. Artificial Intelligence in Medicine 24(1): 25–36.
[12]
Tasoulis DK, Spyridonos P, Pavlidis NG, Cavouras D, Ravazoula P, et al. (2003) Urinary bladder tumor grade diagnosis using on-line trained neural networks. Proceedings of Knowledge-Based Intelligent Information Engineering Systems 2773: 199–206.
[13]
Esgiar AN, Naguib RNG, Sharif BS, Bennett MK, Murray A (1998) Microscopic image analysis for quantitative measurement and feature identification of normal and cancerous colonic mucosa. IEEE Transactions on Information Technology in Biomedicine 2(3): 197–203.
[14]
Esgiar AN, Naguib RNG, Sharif BS, Bennett MK, Murray A (2002) Fractal analysis in the detection of colonic cancer images. IEEE Transactions on Information Technology in Biomedicine 6(1): 54–58.
[15]
Hamilton PW, Bartels PH, Thompson D, Anderson NH, Montironi R, et al. (1997) Automated location of dysplastic fields in colorectal histology using image texture analysis. Journal of Pathology 182(1): 68–75.
[16]
Smolle J (2000) Computer recognition of skin structures using discriminant and cluster analysis. Skin Research and Technology 6(2): 58–63.
Keenan SJ, Diamond J, McCluggage WG, Bharucha H, Thompson D, et al. (2000) An automated machine vision system for the histological grading of cervical intraepithelial neoplasia (CIN). Journal of Pathology 192(3): 351–362.
[19]
Demir C, Gultekin SH, Yener B (2005) Spectral analysis of cell-graphs for automated cancer diagnosis. pp. 153–159. Proc. of the 4th Conference on Modeling and Simulation in Biology, Medicine and Biomedical Engineering.
[20]
Demir C, Gultekin SH, Yener B (2005) Augmented cell-graphs for automated cancer diagnosis. Bioinformatics 21: Suppl 2ii7–ii12.
[21]
Demir C, Gultekin SH, Yener B (2005) Learning the topological properties of brain tumors. IEEE/ACM Transactions on Computational Biology and Bioinformatics 2(3): 262–270.
[22]
Bilgin C, Demir C, Nagi C, Yener B (2007) Cell-Graph Mining for Breast Tissue Modeling and Analysis. pp. 5311–5314. Proc. of 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS 2007).
[23]
Bilgin CC, Bullough P, Plopper GE, Yener B (2010) ECM-Aware cell-graph mining for bone tissue modeling and classification. Journal of Data Mining and Knowledge Discovery 20(3): 416–438.
[24]
Oztan B, Kong H, Gurcan M, Yener B (2012) Follicular Lymphoma Grading using Cell-Graphs and Multi-Scale Feature Analysis. Proc of SPIE Medical Imaging. In press.
[25]
Lund AW, Bilgin CC, Hasan MA, McKeen LM, Stegemann JP, et al. (2009) Quantification of spatial parameters in 3D cellular constructs using graph theory. Journal of Biomedicine and Biotechnology Article 928286..
[26]
Bilgin CC, Lund AW, Can A, Plopper GE, Yener B (2010) Quantification of Three-Dimensional Cell-Mediated Collagen Remodeling Using Graph Theory. PLoS ONE 5(9): e12783.
[27]
McKeen-Polizzotti L, Henderson KM, Oztan B, Bilgin CC, Yener B, et al. (2011) Quantitative metric profiles capture three-dimensional temporospatial architecture to discriminate cellular functional states. BMC Medical Imaging 11: 11.
[28]
Bilgin CC, Ray S, Daley WP, Baydil B, Sequeira SJ, et al. (2010) Cell-graph modeling of salivary gland morphology. pp. 1427–1430. 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Micro.
[29]
Golub G, van Loan C (1996) Matrix Computations, Third Edition. Baltimore, MD: The Johns Hopkins University Press.
[30]
Eldén L (2007) Matrix Methods in Data Mining and Pattern Recognition. Philadelphia, PA: SIAM. 216 p.
[31]
Harshman RA (1970) Foundations of the PARAFAC Procedure: Models and Conditions for an ‘Explanatory’ Multi-modal Factor Analysis. UCLA working papers in phonetics 16: 1–84.
[32]
Carroll JD, Chang J (1970) Analysis of Individual Differences in Multidimensional Scaling via an N-way Generalization of ‘Eckart-Young’ Decomposition. Psychometrika 35: 218–319.
[33]
Acar E, Yener B (2009) Unsupervised Multiway Data Analysis: A Literature Survey. IEEE Transactions on Knowledge and Data Engineering 21(1): 6–20.
Acar E, Kolda TG, Dunlavy D (2011) All-at-once Optimization for Coupled Matrix and Tensor Factorizations. Proceedings of KDD Workshop on Mining and Learning with Graphs.
[36]
Bro R, Kiers HAL (2003) A New Efficient Method for Determining the Number of Components in PARAFAC models. Journal of Chemometrics 17(5): 274–286.
[37]
Gurcan M, Boucheron LE, Can A, Madabhushi A, Rajpoot N, et al. (2009) Histopathological image analysis: A review. IEEE Reviews in Biomedical Engineering 2: 147–171.
