Identification of HEp-2 specimen images with mitotic cell patterns

• Autorzy: Gupta Krati , Bhavsar Arnav , Sao Anil K.

Identyfikatory

DOI

10.1016/j.bbe.2020.07.003

• Języki publikacji: EN

Abstrakty

EN

In this paper, we propose and analyze a novel framework to identify the HEp-2 specimen images, consisting of mitotic spindle (MS) pattern cells. It is based on the fact that the cells showing MS patterns will always be present with other interphase type pattern cells, in a whole slide image (WSI) or specimen image, but the number of MS cells will be very small, unlike interphase patterns. Considering this fact, the work contributes in presenting a framework, using different strategies such as cells-based, region-based and complete image-based approaches. For cell-based approach, the distinctive characteristic of MS patterns is represented using morphology and texture-based features, followed by a traditional Support Vector Machine (SVM) based classifier, whereas the region-based approach uses a Convolutional Neural Network (CNN) as feature extractor and baseline classifier. Finally, for the image-based approach, the Faster Region-CNN (Faster-RCNN) based object detection framework has been applied, considering MS patterns as distinct objects. The region and image-based approaches also contribute in avoiding the requirement of DAPI based segmentation masks. Another contribution of this work is to use a novel and clearly specified threshold-based decision-making criteria for patterns declaration of the specimens with MS pattern cells. All the proposed strategies, integrated with decision-making criteria are validated on a publicly available dataset and across various experiments, we demonstrate good performance, i.e., max. MCC 0.92 in one case. Hence, the proposed framework proves to be an effective solution for the problem statement.

Słowa kluczowe

EN

autoimmune disorder; computer aided detection system; HEp-2 specimens; mitotic cell

PL

choroba autoimmunologiczna; diagnoza wspomagana komputerowo; komórka mitotyczna

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2020
• Tom: Vol. 40, no. 3
• Strony: 1233--1249
• Opis fizyczny: Bibliogr. 50 poz., rys., tab., wykr.

Twórcy

autor

Gupta Krati

• MANAS Lab, School of Computing & Electrical Engineering, Indian Institute of Technology Mandi, Mandi, Himachal Pradesh 175005, India

autor

Bhavsar Arnav

• School of Computing & Electrical Engineering, Indian Institute of Technology Mandi, Mandi, Himachal Pradesh, India

autor

Sao Anil K.

• School of Computing & Electrical Engineering, Indian Institute of Technology Mandi, Mandi, Himachal Pradesh, India

Bibliografia

• [1] Foggia P, Percannella G, Soda P, Vento M. Early experiences in mitotic cells recognition on HEp-2 slides. Proc. of IEEE International Symposium on Computer-Based Medical Systems. 2010. pp. 38–43.
• [2] Kumar Y, Bhatia A, Minz RW. Antinuclear antibodies and their detection methods in diagnosis of connective tissue diseases: a journey revisited. Diagn Pathol 2009;4(Part 1):1–10.
• [3] Foggia P, Percannella G, Soda P, Vento M. Benchmarking HEp-2 cells classification methods. IEEE Trans Med Imaging 2013;32(10):1878–89.
• [4] Hobson P, Lovell BC, Percannella G, Saggese A, Vento M, Wiliem A. Computer aided diagnosis for anti-nuclear antibodies HEp-2 images: progress and challenges. Pattern Recognit Lett 2016;82(Part 1):3–11.
• [5] Dellavance A, Andrade LEC. Detection of autoantibodies by indirect immunofluorescence cytochemistry on HEp-2 cells. Proc. of Autoantibodies. 2019. pp. 19–46.
• [6] Damoiseaux J, Andrade LEC, Carballo OG, Conrad K, Francescantonio PLC, Fritzler MJ, et al. Clinical relevance of HEp-2 indirect immunofluorescent patterns: the international consensus on ANA patterns perspective. Ann Rheum Dis 2019;78(7):879–89.
• [7] Gupta K, Bhavsar A, Sao AK. Detecting mitotic cells in HEp-2 images as anomalies via one class classifier. Comput Biol Med 2019;111:103328–40.
• [8] Daves M, Blecken J, Matthias T, Frey A, Perkmann V, Acqua 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 2016;10(65):370–4.
• [9] Cataldo SD, Tonti S, Bottino A, Ficarra E. ANAlyte: a modular image analysis tool for ANA testing with indirect immunofluorescence. Comput Methods Programs Biomed 2016;128:86–99.
• [10] Cascio D, Taormina V, Raso G. Deep convolutional neural network for HEp-2 fluorescence intensity classification. Appl Sci 2019;01(9):10.
• [11] Tonti S, Di Cataldo S, Macii E, Ficarra E. Unsupervised HEp-2 mitosis recognition in indirect immunofluorescence imaging. Proc. of Annual International Conference of the Engineering in Medicine and Biology Society (EMBC). 2015. pp. 8135–8.
• [12] Paul A, Mukherjee DP. Mitosis detection for invasive breast cancer grading in histopathological images. IEEE Trans Image Process 2015;24:4041–54.
• [13] Iannello G, Percannella G, Soda P, Vento M. Mitotic cells recognition in HEp-2 images. Pattern Recognit Lett 2014;45:136–44.
• [14] Sertel O, Catalyurek UV, Shimada H, Gurcan MN. Computer-aided prognosis of neuroblastoma: detection of mitosis and karyorrhexis cells in digitized histological images. Proc. of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2009. pp. 1433–6.
• [15] Hobson P, Lovell BC, Percannella G, Saggese A, Vento M, Wiliem A. HEp-2 staining pattern recognition at cell and specimen levels: datasets, algorithms and results. Pattern Recognit Lett 2016;82(Part 1):12–22.
• [16] Leung T, Malik J. Representing and recognizing the visual appearance of materials using three-dimensional textons. Int J Comput Vis 2001;43(1):29–44.
• [17] Fogel I, Sagi D. Gabor filters as texture discriminator. Biol Cybern 1989;61(2):103–13.
• [18] Hobson P, Lovell BC, Percannella G, Vento M, Wiliem A. Classifying anti-nuclear antibodies HEp-2 images: a benchmarking platform. Proc. of the International Conference on Pattern Recognition. ICPR. 2014. pp. 3233–8.
• [19] Chazotte B. Labeling nuclear DA using DAPI. Cold Spring Harbor Protoc 2011;2011(1). pdb–prot5556.
• [20] Ren S, He K, Girshick R, Sun J. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 2017;39(6):1137–49.
• [21] Miros A, Wiliem A, Holohan K, Ball L, Hobson P, Lovell BC. A benchmarking platform for mitotic cell classification of ANA IIF HEp-2 images. Proc. of International Conference on Digital Image Computing: Techniques and Applications. 2015. pp. 1–6.
• [22] Roullier V, Lézoray O, Thong TV, Elmoataz A. Multi-resolution graph-based analysis of histopathological whole slide images: application to mitotic cell extraction and visualization. Comput Med Imaging Graphics 2011;35(7– 8):603–15.
• [23] Sommer C, Fiaschi L, Hamprecht FA, Gerlich DW. Learning- based mitotic cell detection in histopathological images. Proc. of the International Conference on Pattern Recognition. 2012. pp. 2306–9.
• [24] Iannello G, Percannella G, Soda P, Vento M. Mitotic cells recognition in HEp-2 images. Pattern Recognit Lett 2014;45:136–44.
• [25] Percannella G, Soda P, Vento M. Mitotic HEp-2 cells recognition under class skew. Proc. of International Conference on Image Analysis and Processing. 2011. pp. 353–62.
• [26] Bizzaro N, Antico A, Platzgummer S, Tonutti E, Bassetti D, Pesente F, et al. Automated antinuclear immunofluorescence antibody screening: a comparative study of six computer-aided diagnostic systems. Autoimmun Rev 2014;13(3):292–8.
• [27] Divya B, Subramaniam KHRN. Human epithelial type-2 cell categorization using hybrid descriptor with binary tree. J Ambient Intell Humaniz Comput 2018;02:1–8.
• [28] 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;2016:1–9.
• [29] 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. 307-1–21.
• [30] 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.
• [31] Wiliem A, Hobson P, Lovell BC. Discovering discriminative cell attributes for HEp-2 specimen image classification. Proc. of the IEEE Winter Conference on Applications of Computer Vision. 2014. pp. 423–30.
• [32] Ponomarev GV, Kazanov MD. Classification of ANA HEp-2 slide images using morphological features of stained patterns. Pattern Recognit Lett 2016;82(Part 1):79–84.
• [33] Li H, Huang H, Zheng WS, Xie X, Zhang J. HEp-2 specimen classification via deep CNNs and pattern histogram. Proc. of 23rd International Conference on Pattern Recognition. 2016. pp. 2145–9.
• [34] Li Y, Shen L, Yu S. HEp-2 specimen image segmentation and classification using very deep fully convolutional network. IEEE Trans Med Imaging 2017;99:1561–72.
• [35] Gao Z, Zhang J, Zhou L, Wang L. HEp-2 cell image classification with convolutional neural networks. 2014 1st Workshop on Pattern Recognition Techniques for Indirect Immunofluorescence Images. 2014. pp. 24–8.
• [36] Cascio D, Taormina V, Raso G. Deep CNN for IIF images classification in autoimmune diagnostics. Appl Sci 2019;04:9.
• [37] Gonzalez RC, Woods RE. Digital image processing. Prentice Hall; 2008.
• [38] Maaten LV, Hinton GE. Visualizing high-dimensional data using t-SNE. J Mach Learn Res 2008;9:2579–605.
• [39] Yang J, Jiang YG, Hauptmann AG, Ngo CW. Evaluating bag-of-visual-words representations in scene classification. Proc. of the International Workshop on Multimedia Information Retrieval. 2007. pp. 197–206.
• [40] Ensafi S, Lu S, Kassim AA, Tan CL. A bag of words based approach for classification of HEp-2 cell images. Proc of the Workshop on Pattern Recognition Techniques for Indirect Immunofluorescence Images. 2014. pp. 29–32.
• [41] Wiliem A, Hobson P, Minchin RF, Lovell BC. A bag of cells approach for antinuclear antibodies HEp-2 image classification. Cytom Part A 2015;87(6):549–57.
• [42] Razavian AS, Azizpour H, Sullivan J, Carlsson S. CNN features off-the-shelf: an astounding baseline for recognition. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2014. pp. 512–9.
• [43] 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.
• [44] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition; 2014, CoRR. 2014;abs/1409.1556.
• [45] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition; 2015, CoRR. 2015;abs/1512.03385.
• [46] García V, Mollineda RA, Sánchez JS. Index of balanced accuracy: a performance measure for skewed class distributions. Proc of Pattern Recognition and Image Analysis. 2009. pp. 441–8.
• [47] Boughorbel S, Jarray F, El-Anbari M. Optimal classifier for imbalanced data using Matthews correlation coefficient metric. PLOS ONE 2017;12(6):1–17. 06.
• [48] Ensafi S, Lu S, Kassim AA, Tan CL. Accurate HEp-2 cell classification based on sparse coding of superpixels. Pattern Recognit Lett 2016;82(Part 1):64–71.
• [49] Gragnaniello D, Sansone C, Verdoliva L. Cell image classification by a scale and rotation invariant dense local descriptor. Pattern Recognit Lett 2016;82(Part 1):72–8.
• [50] Li Y, Shen L, Zhou X, Yu S. HEp-2 specimen classification with fully convolutional network. Proc. of International Conference on Pattern Recognition. 2016. pp. 96–100.

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).