Method of segmentation of overlapping blood cells on microscopic medical images
DOI:
https://doi.org/10.18413/2687-0932-2020-47-4-803-815Keywords:
erythrocytometry, computer vision, blood microscopic image, overlapping objects, concave points, curvature analysis, elliptical objectAbstract
The article discusses the solution to the problem of erythrocytometry using computer vision methods. To carry out erythrocytometry, it is necessary to isolate erythrocytes on a microscopic image of blood and then calculate their parameters such as diameter, volume and thickness. The main problem when calculating the areas of red blood cells is that they can overlap each other, and also change their shape in a certain range. At the first stage, the proposed approach provides for the preprocessing of microscopic images of blood cells. Then, the outline of a group of overlapping objects is divided into many segments, separated by special points, the so-called concave points. A combined approach is proposed for extracting contour evidence, which is based on the detection of concave points using curvature analysis, the use of concavity testing and an efficient search procedure. It is then suggested to use the segment grouping method to find a group of path segments that together form an elliptical object. Segment grouping means iterating over preselected contour segments in order to be able to combine them into a single closed object. The testing of the segmentation algorithm for overlapping erythrocytes in microscopic images on 24 real microscopic medical images of blood showed the effectiveness of the developed method.
Downloads
References
Батищев Д.С., Сойникова Е.С., Михелев В.М., Синюк В.Г. 2018. Использование алгоритмов компьютерного зрения для выполнения гематологического анализа на основе кривой Прайс-Джонса. Научные ведомости белгородского государственного университета. Серия: экономика. Информатика. 45 (3): 537–546.
Гонсалес Р., Вудс Р. 2005. Цифровая обработка изображений. М.: Техносфера, 1072 с.
Камышников В. 2015. Методы клинических лабораторных исследований (6-е издание). ISBN: 978-5-00030-273-6. 8-е изд. перераб., 736 с.
Кудрявцев Л.Д. 1981. Гл. 1. Дифференциальное исчисление функций одного переменного. Математический анализ. Москва: «Высшая школа». Т. 1. С. 190–195.
Липунова Е.А., Скоркина М.Ю. 2004. Система красной крови: сравнительная физиология. БелГУ. Белгород: БелГУ, 215 с.: ил., табл.
Сойникова Е.С., Рябых М.С., Батищев Д.С., Синюк В.Г., Михелев В.М. 2016. Высокопроизводительный метод обнаружения границ на медицинских изображениях. Научный результат. Информационные технологии, 1 (3): 4–9.
Сойникова Е.С., Батищев Д.С., Михелев В.М. 2018. О распознавании форменных объектов крови на основе медицинских изображений. Научный результат. Информационные технологии. 3 (3): 54–65.
Bai, X., Sun, C., Zhou, F. 2009. Splitting touching cells based on concave points and ellipse fitting. Pattern Recognition 42: 2434–2446.
Canny, J. 1986.A computational approach to edge detection, IEEE Transactions on pattern analysis and Machine Intelligence, 8 (6): 679–698.
David Douglas, Thomas Peucker. 1973. Algorithms for the reduction of the number of points required to represent a digitized line or its caricature», The Canadian Cartographer 10(2), 112–122.
Fitzgibbon, A., Pilu, M., Fisher, R.B. 1999. Direct least square fitting of ellipses. IEEE Transactions on Pattern Analysis and Machine Intelligence 21: 476–480.
He, X., Yung, N.: Curvature scale space corner detector with adaptive threshold and dynamic region of support. In: Proceedings of the 17th International Conference on Pattern Recognition. ICPR 2004. (Volume 2.) 791–794.
Otsu N. A threshold selection method from gray-level histograms. IEEE Trans. Sys., Man., Cyber.: journal. – 1979. – Vol. 9. – P. 62–66.
Park, C., Huang, J.Z., Ji, J.X., Ding, Y.: Segmentation, inference and classification of partially overlapping nanoparticles. IEEE Transactions on Pattern Analysis and Machine Intelligence 35 (2013) 669–681.
Pizer Stephen M.et al. Adaptive histogram equalization and its variations. Computer vision, graphics, and image processing. 1987. V.39. No 3. P. 355–368.
Satoshi Suzuki, Keiichi Abe. New fusion operations for digitized binary images and their applications. IEEE Transactions on Pattern Analysis and Machine Intelligence. Volume: PAMI-7, Issue: 6, Nov. (1985) 638–651.
Urs Ramer. An iterative procedure for the polygonal approximation of plane curves. Computer Graphics and Image Processing, 1(3), 1912, 244–256.
Z Zafari S., Eerola T., Sampo J., Kalviainen H., Haario H. Segmentation of partially overlapping nanoparticles using concave points. In: Advances in Visual Computing, Springer, 2015, 187–197.
Zafari S., Eerola T., Sampo J., Kalviainen H., Haario H. H. Segmentation of overlapping elliptical objects in silhouette images. IEEE Transactions on Image Processing24(12), 2015, 5942–5952.
Zafari S., Eerola T., Sampo J., Kalviainen H., Haario H. Comparison of concave point detection methods for overlapping convex objects segmentation. In: 20th Scandinavian Conference on Image Analysis. SCIA 2017, June12–14, 2017, 245–256.
Zhang, W.H., Jiang, X., Liu, Y.M.: A method for recognizing overlapping elliptical bubbles in bubble image. Pattern Recognition Letters (2012) 33(12), 1543–1548.
Abstract views: 335
Share
Published
How to Cite
Issue
Section
Copyright (c) 2020 ECONOMICS. INFORMATION TECHNOLOGIES
This work is licensed under a Creative Commons Attribution 4.0 International License.
