Histologic classification of colonic polyps based on fractal dimension analysis: comparison of results using support vector machine and logistic regression


  • Abdelrahim N. Esgiar
  • Mussa Mabrok
  • Abdullah H. Abdullah
  • Ahmad Almhdie




Histologic classification, colonic polyps, fractal dimension analysis, support vector machine, logistic regression


The aim of this study was to evaluate fractal analysis as a tool for differentiating between normal tissue and adenomatous polyp lesions. Images of colon samples from 140 patients were analyzed. There were 70 subjects in each of the normal and polyp groups. Two texture features based on fractal analysis were studied: fractal dimension (FD) and lacunarity (Lac), extracted using the overlapping box-counting method. The proposed classification models based on fractal analysis of normal colon and abnormal polyp images were performed using two classification methods: the support vector machine (SVM) and the logistic regression (LR). Several widely-recalled statistical metrics (accuracy, sensitivity, specificity and precision) were used to evaluate the global model performance. To avoid any overfitting problems, all models were evaluated using a 10-fold cross-validation. The SVM method showed better performance in detecting normal colon images than the LR method. As a result, the SVM method provided results with higher accuracy (ACC) and specificity than the LR method (ACCSVM=0.90 vs. ACCLR=0.75). These results give confidence for developing a practical automated analysis technique for detecting colon polyps.


R. L. Siegel et al., « Colorectal cancer statistics, 2020 », CA Cancer J Clin, vol. 70, no. 3, p. 145‑164, mai 2020, doi: 10.3322/caac.21601.

Y. Tang, A. D. Polydorides, S. Anandasabapathy, et R. R. Richards-Kortum, « Quantitative analysis of in vivo high-resolution microendoscopic images for the detection of neoplastic colorectal polyps », JBO, vol. 23, no. 11, p. 116003, nov. 2018, doi: 10.1117/1.JBO.23.11.116003.

K. N. Manjunath, P. C. Siddalingaswamy, et G. K. Prabhu, « Domain-Based Analysis of Colon Polyp in CT Colonography Using Image-Processing Techniques », Asian Pac J Cancer Prev, vol. 20, no. 2, p. 629‑637, févr. 2019, doi: 10.31557/APJCP.2019.20.2.629.

M. Bibbo et al., « Karyometric marker features in normal-appearing glands adjacent to human colonic adenocarcinoma », Cancer Res, vol. 50, no. 1, p. 147‑151, janv. 1990.

P. W. Hamilton, P. H. Bartels, D. Thompson, N. H. Anderson, R. Montironi, et J. M. Sloan, « Automated location of dysplastic fields in colorectal histology using image texture analysis », J Pathol, vol. 182, no. 1, p. 68‑75, mai 1997, doi: 10.1002/(SICI)1096-9896(199705)182:1<68::AID-PATH811>3.0.CO;2-N.

P. W. Hamilton, D. C. Allen, P. C. Watt, C. C. Patterson, et J. D. Biggart, « Classification of normal colorectal mucosa and adenocarcinoma by morphometry », Histopathology, vol. 11, no. 9, p. 901‑911, sept. 1987, doi: 10.1111/j.1365-2559.1987.tb01897.x.

M. F. McNitt-Gray, H. K. Huang, et J. W. Sayre, « Feature selection in the pattern classification problem of digital chest radiograph segmentation », IEEE Trans Med Imaging, vol. 14, no. 3, p. 537‑547, 1995, doi: 10.1109/42.414619.

D. Thompson, P. H. Bartels, H. G. Bartels, P. W. Hamilton, et J. M. Sloan, « Knowledge-guided segmentation of colorectal histopathologic imagery », Anal Quant Cytol Histol, vol. 15, no. 4, p. 236‑246, août 1993.

S. S. Cross, J. P. Bury, P. B. Silcocks, T. J. Stephenson, et D. W. Cotton, « Fractal geometric analysis of colorectal polyps », J Pathol, vol. 172, no. 4, p. 317‑323, avr. 1994, doi: 10.1002/path.1711720406.

R. Cicchi et al., « Scoring of collagen organization in healthy and diseased human dermis by multiphoton microscopy », J Biophotonics, vol. 3, no. 1‑2, p. 34‑43, janv. 2010, doi: 10.1002/jbio.200910062.

A. N. Esgiar, R. N. Naguib, B. S. Sharif, M. K. Bennett, et A. Murray, « Microscopic image analysis for quantitative measurement and feature identification of normal and cancerous colonic mucosa », IEEE Trans Inf Technol Biomed, vol. 2, no. 3, p. 197‑203, sept. 1998, doi: 10.1109/4233.735785.

L. Jiao, Q. Chen, S. Li, et Y. Xu, « Colon Cancer Detection Using Whole Slide Histopathological Images », in World Congress on Medical Physics and Biomedical Engineering May 26-31, 2012, Beijing, China, Berlin, Heidelberg, 2013, p. 1283‑1286. doi: 10.1007/978-3-642-29305-4_336.

K. Masood et N. Rajpoot, « Texture based classification of hyperspectral colon biopsy samples using CLBP », in 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, juin 2009, p. 1011‑1014. doi: 10.1109/ISBI.2009.5193226.

J. K. Shuttleworth, A. G. Todman, R. N. G. Naguib, B. M. Newman, et M. K. Bennett, « Colour texture analysis using co-occurrence matrices for classification of colon cancer images », in IEEE CCECE2002. Canadian Conference on Electrical and Computer Engineering. Conference Proceedings (Cat. No.02CH37373), mai 2002, vol. 2, p. 1134‑1139 vol.2. doi: 10.1109/CCECE.2002.1013107.

A. N. Esgiar, R. N. G. Naguib, B. S. Sharif, M. K. Bennett, et A. Murray, « Fractal analysis in the detection of colonic cancer images », IEEE Trans Inf Technol Biomed, vol. 6, no. 1, p. 54‑58, mars 2002, doi: 10.1109/4233.992163.

V. Goh, B. Sanghera, D. M. Wellsted, J. Sundin, et S. Halligan, « Assessment of the spatial pattern of colorectal tumour perfusion estimated at perfusion CT using two-dimensional fractal analysis », Eur Radiol, vol. 19, no. 6, p. 1358‑1365, juin 2009, doi: 10.1007/s00330-009-1304-y.

J. Qin, L. Puckett, et X. Qian, « Image Based Fractal Analysis for Detection of Cancer Cells », déc. 2020, p. 1482‑1486. doi: 10.1109/BIBM49941.2020.9313176.

L. Streba et al., « A pilot study on the role of fractal analysis in the microscopic evaluation of colorectal cancers », Rom J Morphol Embryol, vol. 56, no. 1, p. 191‑196, 2015.

L. A. Gan Lim, R. Naguib, E. P. Dadios, et J. M. C. Avila, « Image classification of microscopic colonic images using textural properties and KSOM », International Journal of Biomedical Engineering and Technology, vol. 3, no. 3‑4, p. 308‑318, 2010, doi: 10.1504/IJBET.2010.032698.

K. A. Marghani, S. S. Dlay, B. S. Sharif, et A. J. Sims, « Morphological and texture features for cancer tissues microscopic images », in Medical Imaging 2003: Image Processing, mai 2003, vol. 5032, p. 1757‑1764. doi: 10.1117/12.481322.

M. N. B. Filho et F. J. A. Sobreira, « Accuracy of Lacunarity Algorithms in Texture Classification of High Spatial Resolution Images from Urban Areas », International archives of photogrammetry, remote sensing and spatial information sciences, p. 417‑422, 2008.

J. Theiler, « Lacunarity in a best estimator of fractal dimension », Physics Letters A, vol. 133, no. 4, p. 195‑200, nov. 1988, doi: 10.1016/0375-9601(88)91016-X.

A. Karperien, H. Ahammer, et H. F. Jelinek, « Quantitating the subtleties of microglial morphology with fractal analysis », Front Cell Neurosci, vol. 7, p. 3, 2013, doi: 10.3389/fncel.2013.00003.

null Allain et null Cloitre, « Characterizing the lacunarity of random and deterministic fractal sets », Phys Rev A, vol. 44, no. 6, p. 3552‑3558, sept. 1991, doi: 10.1103/physreva.44.3552.

A. Karperien, « FracLac for imageJ – FracLac advanced user’s manual, Charles Sturt University Australia », 2004. https://imagej.nih.gov/ij/plugins/fraclac/fraclac-manual.pdf

A. A. Miranda, T. A. Chowdhury, O. Ghita, et P. Whelan, « Shape Classification of Colorectal Polyps at CT Colonography using Support Vector Machines », undefined, 2006, Consulté le: déc. 06, 2021. [En ligne]. Disponible sur: https://www.semanticscholar.org/paper/Shape-Classification-of-Colorectal-Polyps-at-CT-Miranda-Chowdhury/96b0ed70d5238ee8017e3329ccc2e1cca5890d73

J. Weston, « Leave-one-out support vector machines », in Proceedings of the 16th international joint conference on Artificial intelligence - Volume 2, San Francisco, CA, USA, juill. 1999, p. 727‑731.

M. Kumar et S. K. Rath, « Chapter 15 - Feature Selection and Classification of Microarray Data Using Machine Learning Techniques », in Emerging Trends in Applications and Infrastructures for Computational Biology, Bioinformatics, and Systems Biology, Q. N. Tran et H. R. Arabnia, Éd. Boston: Morgan Kaufmann, 2016, p. 213‑242. doi: 10.1016/B978-0-12-804203-8.00015-8.

V. F. van Ravesteijn et al., « Computer-Aided Detection of Polyps in CT Colonography Using Logistic Regression », IEEE Transactions on Medical Imaging, vol. 29, no. 1, p. 120‑131, janv. 2010, doi: 10.1109/TMI.2009.2028576.




How to Cite

N. Esgiar, A., Mabrok, M., H. Abdullah, A., & Almhdie, A. (2023). Histologic classification of colonic polyps based on fractal dimension analysis: comparison of results using support vector machine and logistic regression. International Journal of Engineering Research, 1(1), 67–76. https://doi.org/10.37375/ijer.v1i1.968