Image processing for AFB segmentation in bacilloscopies of pulmonary tuberculosis diagnosis

• Published in: PloS one Vol. 14; no. 7; p. e0218861
• Main Authors: Díaz-Huerta, Jorge Luis, Téllez-Anguiano, Adriana del Carmen, Fraga-Aguilar, Miguelangel, Gutiérrez-Gnecchi, José Antonio, Arellano-Calderón, Sergio
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 15.07.2019; Public Library of Science (PLoS)
• Subjects: Air bases; Algorithms; Bacilli; Bayes Theorem; Bayesian analysis; Biology and Life Sciences; Cell Phone; Classifiers; Computer applications; Cost analysis; Diagnosis; Diagnostic Tests, Routine; Digital imaging; Disease; Engineering and Technology; HIV; Human immunodeficiency virus; Humans; Image analysis; Image databases; Image processing; Image Processing, Computer-Assisted; Image segmentation; International conferences; Internet; Medical diagnosis; Medical imaging; Medical imaging equipment; Medicine and Health Sciences; Methods; Microscopy; Microscopy - methods; Mycobacterium tuberculosis - isolation & purification; Mycobacterium tuberculosis - pathogenicity; Optical microscopes; Physical Sciences; Probabilistic models; Public health; Pulmonary tuberculosis; Research and Analysis Methods; Segmentation; Smear; Specimen Handling; Sputum - diagnostic imaging; Sputum - microbiology; Tuberculosis; Tuberculosis, Pulmonary - diagnosis; Tuberculosis, Pulmonary - diagnostic imaging; Tuberculosis, Pulmonary - microbiology; Zinc
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0218861

Image segmentation applied to medical image analysis is still a critical and important task. Although there exist several segmentation algorithms that have been widely studied in literature, these are subject to segmentation problems such as over- and under-segmentation as well as non-closed edges. In this paper, a simple method that combines well-known segmentation algorithms is presented. This method is applied to detect acid-fast bacilli (AFB) in bacilloscopies used to diagnose pulmonary tuberculosis (TB). This diagnosis can be performed through different tests, and the most used worldwide is smear microscopy because of its low cost and effectiveness. This diagnosis technique is based on the analysis and counting of the bacilli in the bacilloscopy observed under an optical microscope. The proposed method is used to segment the bacilli in digital images from bacilloscopies processed using Ziehl-Neelsen (ZN) staining. The proposed method is fast, has a low computational cost and good efficiency compared to other methods. The bacilli image segmentation is performed by image processing and analysis techniques, probability concepts and classifiers. In this work, a Bayesian classifier based on a Gaussian mixture model (GMM) is used. The segmentations' results are validated by using the Jaccard index, which indicates the efficiency of the classifier.