The feature selection problem in computer-assisted cytology

• Autorzy: Kowal M. , Skobel M. , Nowicki N.

Identyfikatory

DOI

10.2478/amcs-2018-0058

• Języki publikacji: EN

Abstrakty

EN

Modern cancer diagnostics is based heavily on cytological examinations. Unfortunately, visual inspection of cytological preparations under the microscope is a tedious and time-consuming process. Moreover, intra- and inter-observer variations in cytological diagnosis are substantial. Cytological diagnostics can be facilitated and objectified by using automatic image analysis and machine learning methods. Computerized systems usually preprocess cytological images, segment and detect nuclei, extract and select features, and finally classify the sample. In spite of the fact that a lot of different computerized methods and systems have already been proposed for cytology, they are still not routinely used because there is a need for improvement in their accuracy. This contribution focuses on computerized breast cancer classification. The task at hand is to classify cellular samples coming from fine-needle biopsy as either benign or malignant. For this purpose, we compare 5 methods of nuclei segmentation and detection, 4 methods of feature selection and 4 methods of classification. Nuclei detection and segmentation methods are compared with respect to recall and the F1 score based on the Jaccard index. Feature selection and classification methods are compared with respect to classification accuracy. Nevertheless, the main contribution of our study is to determine which features of nuclei indicate reliably the type of cancer. We also check whether the quality of nuclei segmentation/detection significantly affects the accuracy of cancer classification. It is verified using the test set that the average accuracy of cancer classification is around 76%. Spearman’s correlation and chi-square test allow us to determine significantly better features than the feature forward selection method.

Słowa kluczowe

EN

nuclei segmentation; feature selection; breast cancer; convolutional neural network

PL

segmentacja jądra; selekcja cech; rak piersi; sieć neuronowa konwolucyjna

• Wydawca: Oficyna Wydawnicza Uniwersytetu Zielonogórskiego
• Czasopismo: International Journal of Applied Mathematics and Computer Science
• Rocznik: 2018
• Tom: Vol. 28, no. 4
• Strony: 759--770
• Opis fizyczny: Bibliogr. 29 poz., rys., tab., wykr.

Twórcy

autor

Kowal M.

• Institute of Control and Computation Engineering, University of Zielona Góra, ul. Szafrana 2, 65-516 Zielona Góra, Poland

autor

Skobel M.

• Institute of Control and Computation Engineering, University of Zielona Góra, ul. Szafrana 2, 65-516 Zielona Góra, Poland

autor

Nowicki N.

• Department of Medical Physics, University Hospital in Zielona Góra, ul. Zyty 26, 65-046 Zielona Góra, Poland

Bibliografia

• [1] Araújo, T., Aresta, G., Castro, E., Rouco, J., Aguiar, P., Eloy, C., Polónia, A. and Campilho, A. (2017). Classification of breast cancer histology images using convolutional neural networks, PLOS ONE 12(6): 1–14.
• [2] Breiman, L., Friedman, J., Olshen, R. and Stone, C. (1984). Classification and Regression Trees, Wadsworth & Brooks/Cole Advanced Books & Software, Monterey, CA.
• [3] Cheng, J. and Rajapakse, J.C. (2009). Segmentation of clustered nuclei with shape markers and marking function, IEEE Transactions on Biomedical Engineering 56(3): 741–748.
• [4] Cortes, C. and Vapnik, V. (1995). Support-vector networks, Machine Learning 20(3): 273–297.
• [5] Cover, T. and Hart, P. (1967). Nearest neighbor pattern classification, IEEE Transactions on Information Theory 13(1): 21–27.
• [6] Filipczuk, P., Fevens, T., Krzyżak, A. and Monczak, R. (2013). Computer-aided breast cancer diagnosis based on the analysis of cytological images of fine needle biopsies, IEEE Transactions on Medical Imaging 32(12): 2169–2178.
• [7] Haralick, R., Shanmugam, K. and Dinstein, I. (1973). Textural features for image classification, IEEE Transactions on Systems, Man, and Cybernetics 3(6): 610–621.
• [8] ImageJ (2015). Nuclei watershed separation, https://imagej.net/Nuclei_Watershed_Separation.
• [9] Irshad, H., Veillard, A., Roux, L. and Racoceanu, D. (2014). Methods for nuclei detection, segmentation, and classification in digital histopathology: A review—current status and future potential, IEEE Reviews in Biomedical Engineering 7: 97–114.
• [10] Jeleń, L., Fevens, T. and Krzyżak, A. (2008). Classification of breast cancer malignancy using cytological images of fine needle aspiration biopsies, International Journal of Applied Mathematics and Computer Science 18(1): 75–83, DOI: 10.2478/v10006-008-0007-x.
• [11] Jung, C. and Kim, C. (2010). Segmenting clustered nuclei using H-minima transform-based marker extraction and contour parameterization, IEEE Transactions on Biomedical Engineering 57(10): 2600–2604.
• [12] Khoshdeli, M., Cong, R. and Parvin, B. (2017). Detection of nuclei in H&E stained sections using convolutional neural networks, 2017 IEEE EMBS International Conference on Biomedical Health Informatics, Orlando, FL, USA, pp. 105–108.
• [13] Kłeczek, P., Dyduch, G., Jaworek-Korjakowska, J. and Tadeusiewicz, R. (2017). Automated epidermis segmentation in histopathological images of human skin stained with hematoxylin and eosin, Proceedings of SPIE: Medical Imaging 10140: 10140–10140–19.
• [14] Kowal, M. and Filipczuk, P. (2014). Nuclei segmentation for computer-aided diagnosis of breast cancer, International Journal of Applied Mathematics and Computer Science 24(1): 19–31, DOI: 10.2478/amcs-2014-0002.
• [15] Koyuncu, C.F., Akhan, E., Ersahin, T., Cetin-Atalay, R. and Gunduz-Demir, C. (2016). Iterative h-minima-based marker-controlled watershed for cell nucleus segmentation, Cytometry A 89(4): 338–349.
• [16] Nurzynska, K. (2018). Optimal parameter search for colour normalization aiding cell nuclei segmentation, in S. Kozielski et al. (Eds.), Beyond Databases, Architectures and Structures. Facing the Challenges of Data Proliferation and Growing Variety, Springer International Publishing, Cham, pp. 349–360.
• [17] Otsu, N. (1979). A threshold selection method from gray-level histograms, IEEE Transactions on Systems, Man, and Cybernetics 9(1): 62–66.
• [18] Paramanandam, M., O’Byrne, M., Ghosh, B., Mammen, J.J., Manipadam, M.T., Thamburaj, R. and Pakrashi, V. (2016). Automated segmentation of nuclei in breast cancer histopathology images, PLOS ONE 11(9): 1–15.
• [19] Piórkowski, A. (2016). A statistical dominance algorithm for edge detection and segmentation of medical images, in E. Piętka et al. (Eds.), Information Technologies in Medicine, Advances in Intelligent Systems and Computing, Vol. 471, Springer, Cham, pp. 3–14.
• [20] Roffo, G. (2016). Feature selection library (Matlab toolbox), arXiv: 1607.01327.
• [21] Ronneberger, O., Fischer, P. and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation, CoRR: abs/1505.04597.
• [22] Ruifrok, A.C. and Johnston, D.A. (2001). Quantification of histochemical staining by color deconvolution, Analytical and Quantitative Cytology and Histology 23(4): 291–299.
• [23] Sadanandan, S.K., Ranefall, P., Guyader, S.L. and Wählby, C. (2017). Automated training of deep convolutional neural networks for cell segmentation, Scientific Report 7: 7860, DOI: 10.1038/s41598-017-07599-6.
• [24] Spearman, C. (1904). The proof and measurement of association between two things, The American Journal of Psychology 15(1): 72–101.
• [25] Szemenyei, M. and Vajda, F. (2017). Dimension reduction for objects composed of vector sets, International Journal of Applied Mathematics and Computer Science 27(1): 169–180, DOI: 10.1515/amcs-2017-0012.
• [26] Tang, X. (1998). Texture information in run-length matrices, IEEE Transactions on Image Processing 7(11): 1602–1609.
• [27] Vincent, L. (1993). Morphological grayscale reconstruction in image analysis: Applications and Efficient Algorithms, IEEE Transactions on Image Processing 2(2): 176–201.
• [28] Więcławek, W. and Piętka, E. (2015). Watershed based intelligent scissors, Computerized Medical Imaging and Graphics 43: 122–129.
• [29] Yang, X., Li, H. and Zhou, X. (2006). Nuclei segmentation using marker-controlled watershed, tracking using mean-shift, and Kalman filter in time-lapse microscopy, IEEE Transactions on Circuits and Systems I: Regular Papers 53(11): 2405–2414.

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2018).