Evaluation of Texture Attributes of Neoplastic Nuclei for the Classification of Histological Images of Lymphoma

• Thaína A. A. Tosta UFABC
• Paulo R. de Faria UFU
• Leandro A. Neves UNESP
• Marcelo Z. do Nascimento UFABC / UFU

DOI: https://doi.org/10.5753/sbcas.2017.3728

Abstract

Through the use of image processing techniques, it is possible to develop computer-aided diagnosis systems so the analysis of histological samples can be more objective. Then, this paper presents an algorithm to classify histological images of follicular lymphoma and chronic lymphocytic leukemia. For identification of neoplastic nuclei, the R channel extraction from RGB model was performed, followed by the application of histogram equalization, Gaussian filter, fuzzy 3-partition entropy with differential evolution, valley-emphasis and morphological operations. Texture features obtained through ranklet and wavelet transforms were evaluated using the classification by support vector machines. The segmentation of neoplastic nuclei of the considered lesions has reached an average of 80.49% of accuracy in comparison with the manual segmentation of a specialist. The classification of these images using the ranklet transform has reached 98.65% of accuracy, indicating the good performance of this technique for texture analysis of lymphoma images.

References

Abbas, Q. (2017). Segmentation of differential structures on computed tomography images for diagnosis lung-related diseases. Biomedical Signal Processing and Control, 33:325–334.

Angelini, E., Campanini, R., Iampieri, E., Lanconelli, N., Masotti, M., Petkov, T., and Roffilli, M. (2006). A ranklet-based cad for digital mammography. In International Workshop on Digital Mammography, pages 340–346. Springer.

Codella, N., Moradi, M., Matasar, M., Syeda-Mahmood, T., and Smith, J. R. (2016). Lymphoma diagnosis in histopathology using a multi-stage visual learning approach. In SPIE Medical Imaging, pages 97910H–97910H. International Society for Optics and Photonics.

Cuevas, E., Zaldívar, D., and Perez-Cisneros, M. (2016). Image segmentation based on differential evolution optimization. In Applications of Evolutionary Computation in Image Processing and Pattern Recognition, pages 9–22. Springer.

di Ruberto, C., Fodde, G., and Putzu, L. (2015). On different colour spaces for medical colour image classification. In International Conference on Computer Analysis of Images and Patterns, pages 477–488. Springer.

Dimitropoulos, K., Barmpoutis, P., Koletsa, T., Kostopoulos, I., and Grammalidis, N. (2016). Automated detection and classification of nuclei in pax5 and h&e-stained tissue sections of follicular lymphoma. Signal, Image and Video Processing, 11(1):145–153.

do Nascimento, M. Z., Neves, L., Duarte, S. C., Duarte, Y. A. S., and Batista, V. R. (2015). Classification of histological images based on the stationary wavelet transform. In Journal of Physics: Conference Series, volume 574, page 012133. IOP Publishing.

Fiallos, C. B., Pérez, M. G., Conci, A., and Andaluz, V. H. (2015). Automatic detection of injuries in mammograms using image analysis techniques. In International Conference on Systems, Signals and Image Processing (IWSSIP), pages 245–248. IEEE.

Gonzalez, R. C. and Woods, R. E. (2000). Processamento de Imagens Digitais. Edgard Blucher.

Hammouche, K., Diaf, M., and Siarry, P. (2008). A multilevel automatic thresholding method based on a genetic algorithm for a fast image segmentation. Computer Vision and Image Understanding, 109(2):163–175.

Lahmiri, S. (2016). Image characterization by fractal descriptors in variational mode decomposition domain: Application to brain magnetic resonance. Physica A: Statistical Mechanics and its Applications, 456:235–243.

Lo, C. M., Chang, R. F., Huang, C. S., and Moon, W. K. (2015). Computer-aided diagnosis of breast tumors using textures from intensity transformed sonographic images. In Global Conference on Biomedical Engineering & Asian-Pacific Conference on Medical and Biological Engineering, pages 124–127. Springer.

Masotti, M. and Campanini, R. (2008). Texture classification using invariant ranklet features. Pattern Recognition Letters, 29(14):1980–1986.

Meng, T., Lin, L., Shyu, M., and Chen, S. (2010). Histology image classification using supervised classification and multimodal fusion. In Multimedia (ISM), 2010 IEEE International Symposium on, pages 145–152. IEEE.

Ng, H. (2006). Automatic thresholding for defect detection. Pattern recognition letters, 27(14):1644–1649.

Orlov, N. V., Chen, W. W., Eckley, D. M., Macura, T. J., Shamir, L., Jaffe, E. S., and Goldberg, I. G. (2010). Automatic classification of lymphoma images with transform-based global features. IEEE Transactions on Information Technology in Biomedicine, 14(4):1003–1013.

Oswal, V., Belle, A., Diegelmann, R., and Najarian, K. (2013). An entropy-based automated cell nuclei segmentation and quantification: Application in analysis of wound healing process. Computational and mathematical methods in medicine, 2013.

Saha, M., Chowdhury, S. R., and Roy, K. (2011). Ranklets: A qualitative review. In National Conference on Electronics, Communication and Signal Processing, pages 68–73.

Sarkar, S., Das, S., and Chaudhuri, S. S. (2016). Hyper-spectral image ssegmentation using rényi entropy based multi-level thresholding aided with differential evolution. Expert Systems with Applications, 50:120–129.

Sertel, O., Lozanski, G., Shana’ah, A., and Gurcan, M. N. (2010). Computer-aided detection of centroblasts for follicular lymphoma grading using adaptive likelihood-based cell segmentation. IEEE Transactions on Biomedical Engineering, 57(10):2613–2616.

Shamir, L., Orlov, N., Eckley, D. M., Macura, T. J., and Goldberg, I. G. (2008). Iicbu 2008: A proposed benchmark suite for biological image analysis. Medical & Biological Engineering & Computing, 46(9):943–947.

Smeraldi, F. (2009). Fast algorithms for the computation of ranklets. In IEEE International Conference on Image Processing (ICIP), pages 3969–3972. IEEE.

Tuzel, O., Yang, L., Meer, P., and Foran, D. J. (2007). Classification of hematologic malignancies using texton signatures. Pattern Analysis and Applications, 10(4):277–290.

Wang, P., Hu, X., Li, Y., Liu, Q., and Zhu, X. (2016). Automatic cell nuclei segmentation and classification of breast cancer histopathology images. Signal Processing, 122:1–13.

Xi, X., Xu, H., Shi, H., Zhang, C., Ding, H. Y., Zhang, G., Tang, Y., and Yin, Y. (2017). Robust texture analysis of multi-modal images using local structure preserving ranklet and multi-task learning for breast tumor diagnosis. Neurocomputing.

Yadav, A. R., Anand, R. S., Dewal, M. L., and Gupta, S. (2015). Performance analysis of discrete wavelet transform based first-order statistical texture features for hardwood species classification. In International Conference on Recent Trends in Computing, volume 57, pages 214–221. Elsevier.

Yin, S., Zhao, X., Wang, W., and Gong, M. (2014). Efficient multilevel image segmentation through fuzzy entropy maximization and graph cut optimization. Pattern Recognition, 47(9):2894–2907.

Zorman, M., Kokol, P., Lenic, M., de la Rosa, J. L. S., Sigut, J. F., and Alayon, S. (2007). Symbol-based machine learning approach for supervised segmentation of follicular lymphoma images. In IEEE International Symposium on Computer-Based Medical Systems, pages 115–120. IEEE.