Article: Computer aided diagnosis of drug sensitive pulmonary tuberculosis with cavities, consolidations and nodular manifestations on lung CT images Journal: International Journal of Bio-Inspired Computation (IJBIC) 2019 Vol.13 No.2 pp.71 - 85 Abstract: In this work, a computer aided diagnosis (CAD) system to improve the diagnostic accuracy and consistency in image interpretation of pulmonary tuberculosis is proposed. The lung fields are segmented using region growing and edge reconstruction algorithms. Texture features are extracted from the diseased regions manifested as consolidations, cavitations and nodular opacities. A wrapper approach that combines cuckoo search optimisation and one-against-all SVM classifier is used to select optimal feature subset. Cuckoo search algorithm is implemented first using entropy and second without using entropy measure. Training is done with the selected features using one-against-all (SVM) classifier. Among the 98 features extracted from the diseased regions, 47 features are selected with entropy measure giving 92.77% accuracy. When entropy measure is not used, 51 features are selected giving 91.89% accuracy. From the results, it is inferred that selecting appropriate features for training the classifier has an impact on the classifier performance. Inderscience Publishers - linking academia, business and industry through research

Title: Computer aided diagnosis of drug sensitive pulmonary tuberculosis with cavities, consolidations and nodular manifestations on lung CT images

Authors: J. Dhalia Sweetlin; H. Khanna Nehemiah; A. Kannan

Addresses: Ramanujan Computing Centre, Anna University, Chennai – 600025, India ' Ramanujan Computing Centre, Anna University, Chennai – 600025, India ' Department of Information Science and Technology, Anna University, Chennai – 600025, India

Abstract: In this work, a computer aided diagnosis (CAD) system to improve the diagnostic accuracy and consistency in image interpretation of pulmonary tuberculosis is proposed. The lung fields are segmented using region growing and edge reconstruction algorithms. Texture features are extracted from the diseased regions manifested as consolidations, cavitations and nodular opacities. A wrapper approach that combines cuckoo search optimisation and one-against-all SVM classifier is used to select optimal feature subset. Cuckoo search algorithm is implemented first using entropy and second without using entropy measure. Training is done with the selected features using one-against-all (SVM) classifier. Among the 98 features extracted from the diseased regions, 47 features are selected with entropy measure giving 92.77% accuracy. When entropy measure is not used, 51 features are selected giving 91.89% accuracy. From the results, it is inferred that selecting appropriate features for training the classifier has an impact on the classifier performance.

Keywords: computer aided diagnosis; CAD; pulmonary tuberculosis; tuberculosis manifestations; binary cuckoo search; BCS; one-against-all SVM classification; drug sensitive TB; miliary TB; cavitary TB; nodular TB; bio-inspired optimisation.

DOI: 10.1504/IJBIC.2019.098405

International Journal of Bio-Inspired Computation, 2019 Vol.13 No.2, pp.71 - 85

Received: 03 Jul 2016
Accepted: 16 Mar 2017
Published online: 19 Mar 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Computer aided diagnosis of drug sensitive pulmonary tuberculosis with cavities, consolidations and nodular manifestations on lung CT images

Keep up-to-date