An automated classification of HEp-2 cellular shapes using Bag-of-keypoint features and Ant Colony Optimization

• Autorzy: Devanathan Kanchana , Ganesan Kavitha , Swaminathan Ramakrishnan

Identyfikatory

DOI

10.1016/j.bbe.2021.02.004

• Języki publikacji: EN

Abstrakty

EN

In this study, an attempt has been made to differentiate HEp-2 cellular shapes using Bag-of keypoint features and optimization. For this, the images are considered from a publicly available database. To increase the cell structure visibility, the images are pre-processed using edge-sensitive local contrast enhancement. Further, the Speeded-up Robust Feature (SURF) keypoints are extracted and Bag-of-keypoints for each shape are generated. These features are subjected to Ant Colony Optimization (ACO) algorithm for feature selection. The optimal features obtained are then fed to Support Vector Machine (SVM) and k-Nearest Neighbour (kNN) classifiers. Results show that the ACO algorithm can identify the optimal features that characterize the cellular shapes. SVM and kNN are able to differentiate between the shapes with an average classification accuracy of 93.6% and 94.8% respectively. Since differential diagnosis of HEp-2 cellular shapes is significant in the disease-specific prognosis and treatment, this study seems to be clinically relevant.

Słowa kluczowe

EN

Autoimmune disease; speeded-up robust feature; bag-of-keypoints; ant colony optimization; support vector machine; k-nearest neighbor

PL

choroba autoimmunologiczna; optymalizacja kolonii mrówek; maszyna wektorów wsparcia; metoda k najbliższych sąsiadów

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2021
• Tom: Vol. 41, no. 2
• Strony: 376--390
• Opis fizyczny: Bibliogr. 60 poz., rys., tab., wykr.

Twórcy

autor

Devanathan Kanchana

• Department of Medical Electronics, Saveetha Engineering College, Saveetha Nagar, Thandalam, Chennai 602105, India

autor

Ganesan Kavitha

• Department of Electronics Engineering, Madras Institute of Technology, Anna University, Chennai, India

autor

Swaminathan Ramakrishnan

• Non-Invasive Imaging and Diagnostics Laboratory, Biomedical Engineering Group, Department of Applied Mechanics, Indian Institute of Technology Madras, Chennai, India

Bibliografia

• [1] Marrack P, Kappler J, Kotzin BL. Autoimmune disease: why and where it occurs. Nat Med 2001;7:899–905. https://doi.org/10.1038/90935.
• [2] Lerner A, Jeremias P, Matthias T. The world incidence and prevalence of autoimmune diseases is increasing. Int J Celiac Dis 2015;3(4):151–5. https://doi.org/10.12691/ijcd-3-4-8.
• [3] Vermeersch P, Bossuyt X. Prevalence and clinical significance of rare antinuclear antibody patterns. Autoimmun Rev 2013;12(10):998–1003. https://doi.org/10.1016/j.autrev.2013.03.014.
• [4] Dellavance A, Andrade LEC. Detection of autoantibodies by indirect immunofluorescence cytochemistry on hep-2 cells. Autoantibod 2019:19–46. https://doi.org/10.1007/978-1-4939-8949-2_3.
• [5] Majtner T, Bajić B, Lindblad J, Sladoje N, Blanes-Vidal V, Nadimi ES. On the effectiveness of generative adversarial networks as HEp-2 image augmentation tool. Scandinavian Conference on Image Analysis 2019:439–51. https://doi.org/10.1007/978-3-030-20205-7_36.
• [6] Wei Q, Jiang Y, Xie J, Yang M, Zhang Y, Wu Z, et al. Investigation and analysis of HEp 2 indirect immunofluorescence titers and patterns in various liver diseases. Clin Rheumatol 2020. https://doi.org/10.1007/s10067-020-04950-7.
• [7] Cascio D, Taormina V, Raso G. An automatic HEp-2 specimen analysis system based on an active contours model and an SVM classification. Appl Sci 2019;9(2):307. https://doi.org/10.3390/app9020307.
• [8] Kumar D, Maji P. Selection of relevant texture descriptors for recognition of HEp - 2 cell staining patterns. Int J Mach Learn Cybern 2020. https://doi.org/10.1007/s13042-020-01106-6.
• [9] Vununu C, Lee SH, Kwon KR. A strictly unsupervised deep learning method for HEp-2 cell image classification. Sensors 2020;20(9):2717. https://doi.org/10.3390/s20092717.
• [10] Islam UI, Ullah K, Afaq M, Iqbal J, Ali A. Towards the automatic segmentation of HEp-2 cells in indirect immunofluorescence images using an efficient filtering based approach. Multimed Tools Appl 2020. https://doi.org/10.1007/s11042-020-08651-w.
• [11] Xie H, He Y, Lei H, Kuo JY, Lei B. Segmentation guided HEp-2 cell classification with adversarial networks. Comput Commun IoT Appl 2019:374–9. https://doi.org/10.1109/ComComAp46287.2019.9018850.
• [12] Foggia P, Percannella G, Soda P, Vento M. Benchmarking HEp-2 cells classification methods. IEEE T Med Imaging 2013;32:1878–89. https://doi.org/10.1109/TMI.2013.2268163.
• [13] Domsic RT, Medsger TA. Autoantibodies and their role in scleroderma clinical care. Curr Treat Options Rheumatol 2016;2:239–51. https://doi.org/10.1007/s40674-016-0050-y.
• [14] Cutolo M, Soldano S, Smith V. Pathophysiology of systemic sclerosis: current understanding and new insights. Expert Rev Clin Immu 2019;15(7):753–64. https://doi.org/10.1080/1744666X.2019.1614915.
• [15] Birtane M. Diagnostic role of anti-nuclear antibodies in rheumatic diseases. Turkish J Rheumatol 2012;27:79–89. https://doi.org/10.5606/tjr.2012.013.
• [16] Damoiseaux J, Eduardo L, Andrade C, Carballo OG, Conrad K, Luiz P, et al. Clinical relevance of HEp-2 indirect immunofluorescent patterns: the International consensus on ANA patterns (ICAP) perspective. Ann Rheum Dis 2019;78:879–89. https://doi.org/10.1136/annrheumdis-2018-214436.
• [17] Sarrafzadeh O, Rabbani H, Mehri Dehnavi A, Talebi A. Analyzing features by SWLDA for the classification of HEp-2 cell images using GMM. Pattern Recognit Lett 2016;82:44–55. https://doi.org/10.1016/j.patrec.2016.03.023.
• [18] Wermuth PJ, Piera-Velazquez S, Rosenbloom J, Jimenez SA. Existing and novel biomarkers for precision medicine in systemic sclerosis. Nat Rev Rheumatol 2018;14(7):421–32. https://doi.org/10.1038/s41584-018-0021-9.
• [19] Li Y, Shen L. HEp-Net: a smaller and better deep-learning network for HEp-2 cell classification. Comput Methods Biomech Biomed Eng Imaging Vis 2019;7(3):266–72. https://doi.org/10.1080/21681163.2018.1449140.
• [20] Perner P, Perner H, Müller B. Mining knowledge for HEp-2 cell image classification. Artif Intell Med 2002;26:161–73. https://doi.org/10.1016/S0933-3657(02)00057-X.
• [21] Rodrigues LF, Naldi MC, Mari JF. Comparing convolutional neural networks and preprocessing techniques for HEp-2 cell classification in immunofluorescence images. Comput Biol Med 2020;116. https://doi.org/10.1016/j.compbiomed.2019.103542 103542.
• [22] Lu Z, Long B, Li K, Lu F. Effective guided image filtering for contrast enhancement. IEEE Signal Process Lett 2018;25 (10):1585–9. https://doi.org/10.1109/LSP.2018.2867896.
• [23] Xu X, Wu X, Lin F. Cellular image classification. 2017. Springer. 10.1007/978-3-319-47629-2.
• [24] Manivannan S, Li W, Akbar S, Wang R, Zhang J, McKenna SJ. An automated pattern recognition system for classifying indirect immunofluorescence images of HEp-2 cells and specimens. Pattern Recognit 2016;51:12–26. https://doi.org/10.1016/j.patcog.2015.09.015.
• [25] Hobson P, Lovell BC, Percannella G, Vento M, Wiliem A. Benchmarking human epithelial type 2 interphase cells classification methods on a very large dataset. Artif Intell Med 2015;65:239–50. https://doi.org/10.1016/j.artmed.2015.08.001.
• [26] Celik C, Bilge HS. Content based image retrieval with sparse representations and local feature descriptors: a comparative study. Pattern Recognit 2017;68:1–13. https://doi.org/10.1016/j.patcog.2017.03.006.
• [27] Ensafi S, Lu S, Kassim AA, Tan CL. Accurate HEp-2 cell classification based on sparse bag of words coding. Comput Med Imaging Graph 2017;57:40–9. https://doi.org/10.1016/j.compmedimag.2016.08.002.
• [28] Aghdam MH, Ghasem-aghaee N, Basiri ME. Text feature selection using ant colony optimization. Expert Syst Appl 2009;36:6843–53. https://doi.org/10.1016/j.eswa.2008.08.022.
• [29] Kanan HR, Faez K, Taheri SM. Feature selection using ant colony optimization (ACO): a new method and comparative study in the in the application of face recognition system. In: Perner, P. (eds) Advances in data mining: Theoretical aspects and applications. ICDM 2007. LNCS (LNAI). 4597:63-76. 10.1007/978-3-540-73435-2_6.
• [30] Chen L, Chen B, Chen Y. Image feature selection based on ant colony optimization. In:Wang D., Reynolds M. (eds) Advances in Artificial Intelligence. AI 2011. LNCS. 7106:580-589. 10.1007/978-3-642-25832-9_59.
• [31] Peng H, Ying C, Tan S, Hu B. An improved feature selection algorithm based on ant colony optimization. IEEE Access 2018;6:69203–9. https://doi.org/10.1109/ACCESS.2018.2879583.
• [32] Kavitha G, Ramakrishnan S. An approach to identify optic disc in human retinal images using ant colony optimization method. J Med Syst 2010;34:809–13. https://doi.org/10.1007/s10916-009-9295-4.
• [33] Stoklasa R, Majtner T, Svoboda D. Efficient k-NN based HEp-2 cells classifier. Pattern Recogn 2014;47:2409–18. https://doi.org/10.1016/j.patcog.2013.09.021.
• [34] Lovell BC, Percannella G, Saggese A, Vento M, Wiliem A. International contest on pattern recognition techniques for indirect immunofluorescence images analysis. In: 23rd International Conference on Pattern Recognition (ICPR). p. 74–6. https://doi.org/10.1109/ICPR.2016.7899610.
• [35] Li X, Gu Y, Hu S, Martin RR. Mixed-domain edge-aware image manipulation. IEEE T Image Process 2013;22:1915–25. https://doi.org/10.1109/TIP.2013.2237922.
• [36] Tabakhi S, Moradi P, Akhlaghian F. An unsupervised feature selection algorithm based on ant colony optimization. Eng Appl Artif Intell 2014;32:112–23. https://doi.org/10.1016/j.engappai.2014.03.007.
• [37] Fallahzadeh O, Dehghani-bidgoli Z. Raman spectral feature selection using ant colony optimization for breast cancer diagnosis. Lasers Med Sci 2018;33(8):799–806. https://doi.org/10.1007/s10103-018-2544-3.
• [38] Donato C, Marco C, Giuseppe R, Degli U, Vincenzo T, Maria VS. HEp-2 cell classification with heterogeneous classes-processes based on K-nearest neighbours. In: 2014 1st Workshop on Pattern Recognition Techniques for Indirect Immunofluorescence Images. p. 10–5. https://doi.org/10.1109/I3A.2014.17.
• [39] Qi X, Zhao G, Chen J, Pietikäinen M. HEp-2 cell classification: The role of gaussian scale space theory as a pre-processing approach. arXiv preprint 2016; arXiv:1509.02320. 10.1016/j.patrec.2015.12.011.
• [40] Divya BS, Subramaniam K, Nanjundaswamy HR. HEp-2 cell classification using Binary Decision Tree approach. In: IEEE EMBS Conference on Biomedical Engineering and Sciences (IECBES). p. 507–12. https://doi.org/10.1109/IECBES.2016.7843503.
• [41] Li H, Hao H, Zheng WS, Xiaohua X, Zhang J. HEp-2 specimen classification via deep CNNs and pattern histogram. In: 23rd International Conference on Pattern Recognition (ICPR). p. 2145–9. https://doi.org/10.1109/ICPR.2016.7899953.
• [42] Al-dulaimi K, Chandran V, Nguyen K, Banks J. Benchmarking HEp-2 specimen cells classification using linear discriminant analysis on higher order spectra features of cell shape. Pattern Recognit Lett 2019;125:534–41. https://doi.org/10.1016/j.patrec.2019.06.020.
• [43] Cascio D, Taormina V, Raso G. Deep convolutional neural network for HEp-2 fluorescence intensity classification. Appl Sci 2019;9(3):408. https://doi.org/10.3390/app9030408.
• [44] Daves M, Blecken J, Matthias T, Frey A, Perkmann V, Dall A, et al. New automated indirect immunofluorescent antinuclear antibody testing compares well with established manual immunofluorescent screening and titration for antinuclear antibody on HEp-2 cells. Immunol Res 2017;65 (1):370–4. https://doi.org/10.1007/s12026-016-8874-y.
• [45] Rahman S,Wang L, Sun C, Zhou L. Deep learning based HEp-2 image classification: a comprehensive review. Med Image Anal 2020. https://doi.org/10.1016/j.media.2020.101764101764.
• [46] Shen L, Lin J, Wu S, Yu S. HEp-2 image classification using intensity order pooling based features and bag of words. Pattern Recogn 2014;47(7):2419–27. https://doi.org/10.1016/j.patcog.2013.09.020.
• [47] Devanathan K, Ganapathy N, Swaminathan R. Binary Grey Wolf optimizer based feature selection for nucleolar and centromere staining pattern classification in indirect immunofluorescence images. In: 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). p. 7040–3. https://doi.org/10.1109/EMBC.2019.8856872.
• [48] Shen L, Jia X, Li Y. Deep cross residual network for HEp-2 cell staining pattern classification. Pattern Recogn 2018;82:68–78. https://doi.org/10.1016/j.patcog.2018.05.005.
• [49] Gupta K, Bhavsar A, Sao AK. Identification of HEp-2 specimen images with mitotic cell patterns. Biocybern Biomed Eng 2020;40(3):1233–49. https://doi.org/10.1016/j.bbe.2020.07.003.
• [50] Hegde RB, Prasad K, Hebbar H, Singh BMK. Comparison of traditional image processing and deep learning approaches for classification of white blood cells in peripheral blood smear images. Biocybern Biomed Eng 2019;39(2):382–92. https://doi.org/10.1016/j.bbe.2019.01.005.
• [51] Li Y, Shen L, Zhou X, Yu S. HEp-2 specimen classification with fully convolutional network. In: 23rd International Conference on Pattern Recognition (ICPR). p. 96–100. https://doi.org/10.1109/ICPR.2016.7899615.
• [52] Oraibi ZA, Yousif H, Hafiane A, Seetharaman G, Palaniappan K. Learning local and deep features for efficient cell image classification using random forests. In: 25th IEEE International Conference on Image Processing (ICIP). p. 2446–50. https://doi.org/10.1109/ICIP.2018.8451287.
• [53] Matos CEF, Souza JC, Diniz JOB, et al. Diagnosis of breast tissue in mammography images based local feature descriptors. Multimed Tools Appl 2018;78(10):1–26. https://doi.org/10.1007/s11042-018-6390-x.
• [54] Merone M, Sansone C, Soda P. A computer-aided diagnosis system for HEp-2 fluorescence intensity classification. Artif Intell Med 2019;97:71–8. https://doi.org/10.1016/j.artmed.2018.11.002.
• [55] Iannello G, Onofri L, Soda P. Centromere and cytoplasmic staining pattern recognition: a local approach. Med Biol Eng Compu 2013;51(12):1305–14. https://doi.org/10.1007/s11517-013-1102-1.
• [56] Hesselstrand R, Scheja A, Shen GQ, Wiik A, Ðkesson A. The association of antinuclear antibodies with organ involvement and survival in systemic sclerosis. Rheumatology 2003;42(4):534–40. https://doi.org/10.1093/rheumatology/keg170.
• [57] Li Y, Shen L, Yu S. HEp-2 specimen image segmentation and classification using very deep fully convolutional network. IEEE Trans Med Imaging 2017;36(7):1561–72. https://doi.org/10.1109/TMI.2017.2672702.
• [58] Foggia, P., Percannella, G., Soda, P., Vento, M. (2010, October). Early experiences in mitotic cells recognition on HEp-2 slides. In 2010 IEEE 23rd International Symposium on Computer-Based Medical Systems (CBMS) (pp. 38-43). IEEE. 10.1109/CBMS.2010.6042611.
• [59] Wiliem, A., Wong, Y., Sanderson, C., Hobson, P., Chen, S., & Lovell, B. C. (2013, January). Classification of human epithelial type 2 cell indirect immunofluoresence images via codebook based descriptors. In 2013 IEEE Workshop on Applications of Computer Vision (WACV) (pp. 95-102). IEEE. 10.1109/WACV.2013.6475005.
• [60] Benammar Elgaaied A, Cascio D, Bruno S, Ciaccio MC, Cipolla M, Fauci A, et al. Computer-assisted classification patterns in autoimmune diagnostics: the AIDA project. Biomed Res Int 2016;2016. https://doi.org/10.1155/2016/2073076.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).