Automated approach for indirect immunofluorescence images classification based on unsupervised clustering method

• Published in: IET computer vision Vol. 12; no. 7; pp. 989 - 995
• Main Authors: Vivona, Letizia, Cascio, Donato, Taormina, Vincenzo, Raso, Giuseppe
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 01.10.2018; Wiley
• Subjects: ANAs; antinuclear antibodies; autoimmune diseases; automated approach; automatic system; biomedical optical imaging; blood; cellular biophysics; centromere pattern; centromere pattern classification; classification phase; clustering K-means algorithm; complex disorders; diseases; environmental factors; feature extraction; fluorescence; fluorescence intensity; genetic factors; HEp-2 cells; IIF images; image classification; image segmentation; image texture; immune responses; indirect immunofluorescence images classification; medical disorders; medical image processing; MIVIA; prevalent diseases; public database; representative state-of-the-art works; self-antigens; Special Section: Selected Papers from the 19th International Conference on Image Analysis and Processing (ICIAP) 2017; staining patterns; standard screening methods; state-of-the-art techniques; unknown aetiology; unsupervised clustering method; cellular biophysics; unsupervised clustering method; image classification; complex disorders; antinuclear antibodies; self-antigens; centromere pattern; representative state-of-the-art works; MIVIA; automated approach; genetic factors; standard screening methods; immune responses; state-of-the-art techniques; feature extraction; fluorescence; image segmentation; IIF images; medical image processing; autoimmune diseases; ANAs; databases; indirect immunofluorescence images classification; environmental factors; classification phase; diseases; staining patterns; blood; image texture; fluorescence intensity; unknown aetiology; prevalent diseases; medical disorders; HEp-2 cells; public database; automatic system; centromere pattern classification; biomedical optical imaging; clustering K-means algorithm
• ISSN: 1751-9632; 1751-9640; 1751-9640
• DOI: 10.1049/iet-cvi.2018.5271

Autoimmune diseases (ADs) are a collection of many complex disorders of unknown aetiology resulting in immune responses to self-antigens and are thought to result from interactions between genetic and environmental factors. ADs collectively are amongst the most prevalent diseases in the U.S., affecting at least 7% of the population. The diagnosis of ADs is very complex, the standard screening methods provides seeking and recognizing of Antinuclear Antibodies (ANA) by Indirect ImmunoFluorescence (IIF) based on HEp-2 cells. In this paper an automatic system able to identify and classify the Centromere pattern is presented. The method is based on the grouping of centromeres present on the cells through a clustering K-means algorithm. The performances were obtained on two public database of IIF images (A.I.D.A. and MIVIA). Our results showed a sensitivity for image of (90 ± 5)% and a Accuracy equal to (98.0 ± 0.5)%. Results demonstrate that the system is able to identify and classify Centromere pattern with accuracy better or comparable with some representative state of the art works. Moreover, it should be noted that for the classification phase the works used for the comparison used an expert-manual segmentation while, in the present work, the segmentation was obtained automatically.