Abstract
Quantitative analysis of histopathological sections can be used to support the diagnosis and evaluate the disease progression by pathologists. The use of computer-aided diagnosis in pathology can substantially enhance the efficiency and accuracy of pathologists decisions, and overall benefit the patient. The evaluation of the shape of specific types of cell nuclei plays an important role in histopathological examination in various types of cancer. In this study we try to verify how much the results of segmentation could be improved with applying boundary refinement algorithm to thresholded histopathological image. In this paper we studied 5 methods based on various approaches: active contour, k-means clustering, and region-growing. For evaluation purposes, ground truth templates were generated by manual annotation of images. The performance is evaluated using pixel-wise sensitivity and specificity metrics. It appears that satisfactory results were achieved only by two algorithms based on active contour. By applying methodology based on active contour algorithm we managed to achieve sensitivity of about 93% and specificity of over 99%. To sum up, thresholding algorithms produce results that almost never perfectly fit to real object’s boundary, but this initial detection of objects followed by boundary refinement results in more accurate segmentation.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Al-Kofahi, Y.: Improved automatic detection and segmentation of cell nuclei in histopathology images. IEEE Trans. Biomed. Eng. 57(4), 841–852 (2010)
Bezdek, J.C.: FCM: the fuzzy c-means clustering algorithm. Comput. Geosci. 10(2–3), 191–203 (1984)
Bradley, D., et al.: Adaptive thresholding using the integral image. J. Graph. Tools 12(2), 13–21 (2007). https://doi.org/10.1080/2151237X.2007.10129236
Brink, A., et al.: Minimum cross-entropy threshold selection. Pattern Recogn. 29(1), 179–188 (1996)
Bunyak, F., et al.: Histopathology tissue segmentation by combining fuzzy clustering with multiphase vector level sets. In: Advances in Experimental Medicine and Biology, pp. 413–424. Springer, New York (2011)
Daniel: Implementation of recursive region growing algorithm (...) (2011). https://www.mathworks.com/matlabcentral/fileexchange/32532. Accessed 18 June 2018
Fonseca, P.: Implementation of k-means image segmentation based on histogram (2011). https://www.mathworks.com/matlabcentral/fileexchange/30740. Accessed 18 June 2018
Irshad, H.: Methods for nuclei detection, segmentation, and classification in digital histopathology: a review–current status and future potential. IEEE Rev. Biomed. Eng. 7, 97–114 (2014)
Khurshid, K., et al.: Comparison of niblack inspired binarization methods for ancient documents. In: Document Recognition and Retrieval XVI (2009)
Korzynska et al., A.: The METINUS plus method for nuclei quantification in tissue microarrays of breast cancer and axillary node tissue section. Biomed. Signal Process. 32, 1–9 (2017)
Kroon, D.J.: Implementation of segmentation by growing a region from seed point using intensity mean measure (2008). https://www.mathworks.com/matlabcentral/fileexchange/19084. Accessed 18 June 2018
Markiewicz, T., et al.: MIAP – web-based platform for the computer analysis of microscopic images to support the pathological diagnosis. Biocybern Biomed. Eng. 36(4), 597–609 (2016)
Pang, J.: Implementation of the localized active contour method using level set method (2014). https://www.mathworks.com/matlabcentral/fileexchange/44906. Accessed 18 June 2018
Roszkowiak, L., et al.: Nuclei detection methods in immunohistochemically stained tissue sections of breast cancer. (Submitted to Computer Methods and Programs in Biomedicine on 19 June 2018)
Snoj, N., et al.: Molecular Biology of Breast Cancer, pp. 341–349. Academic Press (2010). https://www.scopus.com/inward/record.uri?eid=2-s2.0-84884578034&doi=10.1016%2fB978-0-12-374418-0.00026-8&partnerID=40&md5=75f68bd64c6de8f9dde1630b973b017d
Wu, Y.: Implementation of active contours without edges by Chan and Vese (2009). https://www.mathworks.com/matlabcentral/fileexchange/23445. Accessed 18 June 2018
Funding
We acknowledge the financial support of the Polish National Science Center grant, PRELUDIUM, 2013/11/N/ST7/02797.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Roszkowiak, Ł., Korzyńska, A., Siemion, K., Pijanowska, D. (2019). The Influence of Object Refining in Digital Pathology. In: Choraś, M., Choraś, R. (eds) Image Processing and Communications Challenges 10. IP&C 2018. Advances in Intelligent Systems and Computing, vol 892. Springer, Cham. https://doi.org/10.1007/978-3-030-03658-4_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-03658-4_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-03657-7
Online ISBN: 978-3-030-03658-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)