Automatic counting of trypanosomatid amastigotes in infected human cells. (1st October 2017)

• Record Type: Journal Article
• Authors: de Souza Relli, Cleber; Facon, Jacques; Ayala, Horacio Legal; De Souza Britto, Alceu
• Is Part Of: Computers in biology and medicine. Volume 89(2017)
• Page Start: 222
• Page End: 235
• Publication Date: 2017-10-01
• Subjects: Chagas disease -- Trypanosoma cruzi -- Segmentation -- Mathematical morphology -- Counting; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2017.08.010
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: This article presents an automatic approach to counting amastigotes in human cells infected with Chagas. The approach is divided into four steps: first, morphological pretreatment removes the complex image background; sets are then segmented by unsupervised classification; the infected cells are then preserved using a thresholding process; and, finally, they undergo morphological granulometric processing and are filtered by the average. An experimental protocol was employed to compare the amastigotes nuclei labeled by a professional biochemist with the results obtained by the proposed approach. We observed that using the granulometric sieving conducted with square SE plus average size filtering is the best option to obtain the minor error and the best precision and using the granulometric sieving conducted with rhombus SE without average size filtering represents the best combination for obtaining the best F-measure and recall rates. Highlights: The first contribution of this proposed approach is the use of TSL color space in the Fuzzy C-means clustering process. The second contribution is the use of HSL color space in the mathematical color morphology with lexicographical ordering. The third contribution of this proposed approach is the use of the color top-hat morphological process by reconstruction. The fourth contribution was to highlight some interesting based- metric combinations. The fifth contribution is planning to provide a public available software that will be used by other researchers.