Extreme Learning Machine based Differentiation of Pulmonary Tuberculosis in Chest Radiographs using Integrated Local Feature Descriptors

•Automated differentiation of Tuberculosis in chest radiographs is carried out using two variants of extreme learning machine.•Lung fields in the images are segmented using Reaction Diffusion Level Set and integrated local feature descriptors•Both the variants of Extreme learning machine with Sigmoi...

Full description

Saved in:
Bibliographic Details
Published inComputer methods and programs in biomedicine Vol. 204; p. 106058
Main Authors Govindarajan, Satyavratan, Swaminathan, Ramakrishnan
Format Journal Article
LanguageEnglish
Published Ireland Elsevier B.V 01.06.2021
Subjects
Online AccessGet full text
ISSN0169-2607
1872-7565
1872-7565
DOI10.1016/j.cmpb.2021.106058

Cover

More Information
Summary:•Automated differentiation of Tuberculosis in chest radiographs is carried out using two variants of extreme learning machine.•Lung fields in the images are segmented using Reaction Diffusion Level Set and integrated local feature descriptors•Both the variants of Extreme learning machine with Sigmoid activation function yield maximum accuracy andsensitivity•Online Sequential Extreme learning machine is found better in detecting Tuberculosis with minimum features•This method seems suitable for the computerised diagnostics of Tuberculosis in chest radiographs with subtle and non-specific alterations Computer aided diagnostics of Pulmonary Tuberculosis in chest radiographs relies on the differentiation of subtle and non-specific alterations in the images. In this study, an attempt has been made to identify and classify Tuberculosis conditions from healthy subjects in chest radiographs using integrated local feature descriptors and variants of extreme learning machine. Lung fields in the chest images are segmented using Reaction Diffusion Level Set method. Local feature descriptors such as Median Robust Extended Local Binary Patterns and Gradient Local Ternary Patterns are extracted. Extreme Learning Machine (ELM) and Online Sequential ELM (OSELM) classifiers are employed to identify Tuberculosis conditions and, their performances are analysed using standard metrics. Results show that the adopted segmentation method is able to delineate lung fields in both healthy and Tuberculosis images. Extracted features are statistically significant even in images with inter and intra subject variability. Sigmoid activation function yields accuracy and sensitivity values greater than 98% for both the classifiers. Highest sensitivity is observed with OSELM for minimal significant features in detecting Tuberculosis images. As ELM based method is able to differentiate the subtle changes in inter and intra subject variations of chest X-ray images, the proposed methodology seems to be useful for computer-based detection of Pulmonary Tuberculosis.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0169-2607
1872-7565
1872-7565
DOI:10.1016/j.cmpb.2021.106058