Diagnostics of Multi Drug Resistant Tuberculosis in Chest Radiographs using Local Textures & Extreme Gradient Boosting
This study attempts to detect and differentiate Multi Drug Resistant (MDR) - Tuberculosis (TB) and Drug Sensitive (DS)-TB Chest Radiographs (CXR) using local texture descriptors and Ensemble Learning method. Studies report that CXR images contain likelihood information of the drug resistance which c...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
De Gruyter
2023-09-01
|
Series: | Current Directions in Biomedical Engineering |
Subjects: | |
Online Access: | https://doi.org/10.1515/cdbme-2023-1181 |
_version_ | 1797646323293356032 |
---|---|
author | Govindarajan Satyavratan Manuskandan S. R. Swaminathan Ramakrishnan |
author_facet | Govindarajan Satyavratan Manuskandan S. R. Swaminathan Ramakrishnan |
author_sort | Govindarajan Satyavratan |
collection | DOAJ |
description | This study attempts to detect and differentiate Multi Drug Resistant (MDR) - Tuberculosis (TB) and Drug Sensitive (DS)-TB Chest Radiographs (CXR) using local texture descriptors and Ensemble Learning method. Studies report that CXR images contain likelihood information of the drug resistance which can be utilized computationally. Initially, CXR images are subjected to lung fields segmentation using Reaction Diffusion Level Set method. Further, Local Directional Texture Pattern (LDTP) features are extracted from the segmented lungs to characterize the localized textural variations. Extreme Gradient Boosting (XGBoost) classifier is employed to differentiate DS-TB and MDR-TB images. The obtained results demonstrate the ability of extracted LDTP features to characterize nonspecific textural inhomogeneities in images by operating on its principal directions. XGBoost algorithm provides maximum accuracy of 93% and true positive rate of 94.6% in detecting MDR-TB. As the proposed study differentiates the MDR-TB condition using CXR images, its computerized diagnostics could be used in the early screening and followup of TB ridden patients for public health infection control in any setting. |
first_indexed | 2024-03-11T15:01:01Z |
format | Article |
id | doaj.art-a221a28f36a24d60ac06d5f017e2c9e1 |
institution | Directory Open Access Journal |
issn | 2364-5504 |
language | English |
last_indexed | 2024-03-11T15:01:01Z |
publishDate | 2023-09-01 |
publisher | De Gruyter |
record_format | Article |
series | Current Directions in Biomedical Engineering |
spelling | doaj.art-a221a28f36a24d60ac06d5f017e2c9e12023-10-30T07:58:13ZengDe GruyterCurrent Directions in Biomedical Engineering2364-55042023-09-019172172410.1515/cdbme-2023-1181Diagnostics of Multi Drug Resistant Tuberculosis in Chest Radiographs using Local Textures & Extreme Gradient BoostingGovindarajan Satyavratan0Manuskandan S. R.1Swaminathan Ramakrishnan2Indian Institute of Technology Madras, Chennai, IndiaKaruvee Innovations Pvt. Ltd., Chennai, IndiaIndian Institute of Technology Madras, Chennai, IndiaThis study attempts to detect and differentiate Multi Drug Resistant (MDR) - Tuberculosis (TB) and Drug Sensitive (DS)-TB Chest Radiographs (CXR) using local texture descriptors and Ensemble Learning method. Studies report that CXR images contain likelihood information of the drug resistance which can be utilized computationally. Initially, CXR images are subjected to lung fields segmentation using Reaction Diffusion Level Set method. Further, Local Directional Texture Pattern (LDTP) features are extracted from the segmented lungs to characterize the localized textural variations. Extreme Gradient Boosting (XGBoost) classifier is employed to differentiate DS-TB and MDR-TB images. The obtained results demonstrate the ability of extracted LDTP features to characterize nonspecific textural inhomogeneities in images by operating on its principal directions. XGBoost algorithm provides maximum accuracy of 93% and true positive rate of 94.6% in detecting MDR-TB. As the proposed study differentiates the MDR-TB condition using CXR images, its computerized diagnostics could be used in the early screening and followup of TB ridden patients for public health infection control in any setting.https://doi.org/10.1515/cdbme-2023-1181tuberculosischest radiographxgboostdrug sensitivedrug resistive |
spellingShingle | Govindarajan Satyavratan Manuskandan S. R. Swaminathan Ramakrishnan Diagnostics of Multi Drug Resistant Tuberculosis in Chest Radiographs using Local Textures & Extreme Gradient Boosting Current Directions in Biomedical Engineering tuberculosis chest radiograph xgboost drug sensitive drug resistive |
title | Diagnostics of Multi Drug Resistant Tuberculosis in Chest Radiographs using Local Textures & Extreme Gradient Boosting |
title_full | Diagnostics of Multi Drug Resistant Tuberculosis in Chest Radiographs using Local Textures & Extreme Gradient Boosting |
title_fullStr | Diagnostics of Multi Drug Resistant Tuberculosis in Chest Radiographs using Local Textures & Extreme Gradient Boosting |
title_full_unstemmed | Diagnostics of Multi Drug Resistant Tuberculosis in Chest Radiographs using Local Textures & Extreme Gradient Boosting |
title_short | Diagnostics of Multi Drug Resistant Tuberculosis in Chest Radiographs using Local Textures & Extreme Gradient Boosting |
title_sort | diagnostics of multi drug resistant tuberculosis in chest radiographs using local textures extreme gradient boosting |
topic | tuberculosis chest radiograph xgboost drug sensitive drug resistive |
url | https://doi.org/10.1515/cdbme-2023-1181 |
work_keys_str_mv | AT govindarajansatyavratan diagnosticsofmultidrugresistanttuberculosisinchestradiographsusinglocaltexturesextremegradientboosting AT manuskandansr diagnosticsofmultidrugresistanttuberculosisinchestradiographsusinglocaltexturesextremegradientboosting AT swaminathanramakrishnan diagnosticsofmultidrugresistanttuberculosisinchestradiographsusinglocaltexturesextremegradientboosting |