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

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....