Tuberculosis (TB) is a respiratory disease which affects millions of people each year, accounting for the tenth leading cause of death worldwide, and is especially prevalent in underdeveloped regions where access to adequate medical care may be limited. Analysis of digital chest radiographs (CXRs) is a common and inexpensive method for the diagnosis of TB; however, a trained radiologist is required to interpret the results, and is subject to human error. Computer-Aided Detection (CAD) systems are a promising machine-learning based solution to automate the diagnosis of TB from CXR images. As the dimensionality of a high-resolution CXR image is very large, image features are used to describe the CXR image in a lower dimension while preserving the elements in the CXR necessary for the detection of TB. In this thesis, I present a set of image features using Pyramid Histogram of Oriented Gradients, Local Binary Patterns, and Principal Component Analysis which provides high classifier performance on two publicly available CXR datasets, and compare my results to current state-of-the-art research.
","abstract_html":"<p>Tuberculosis (TB) is a respiratory disease which affects millions of people each year, accounting for the tenth leading cause of death worldwide, and is especially prevalent in underdeveloped regions where access to adequate medical care may be limited. Analysis of digital chest radiographs (CXRs) is a common and inexpensive method for the diagnosis of TB; however, a trained radiologist is required to interpret the results, and is subject to human error. Computer-Aided Detection (CAD) systems are a promising machine-learning based solution to automate the diagnosis of TB from CXR images. As the dimensionality of a high-resolution CXR image is very large, image features are used to describe the CXR image in a lower dimension while preserving the elements in the CXR necessary for the detection of TB. In this thesis, I present a set of image features using Pyramid Histogram of Oriented Gradients, Local Binary Patterns, and Principal Component Analysis which provides high classifier performance on two publicly available CXR datasets, and compare my results to current state-of-the-art research.</p>","abstract_has_math":false,"creators":["Hooper, Brian"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":null,"degree_discipline":"Computational Science","degree_department":null,"school":null,"contributors":["Szilard Vajda","Donald Davendra","Razvan Andonie"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-01-01T08:00:00Z","date_published":"2020-01-01T08:00:00Z","updated_at":"2026-07-24T01:37:48Z","subjects":["Automatic chest x-ray analysis","Feature selection","Neural networks","PHOG","Machine Learning","Automatic TB screening","Artificial Intelligence and Robotics","Data Science"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.cwu.edu/etd/1356","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Szilard Vajda","Donald Davendra","Razvan Andonie"]},{"key":"dc:creator","label":"Author","values":["Hooper, Brian"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2020-06-10T07:00:00Z"]},{"key":"dc:type","label":"Dc Type","values":["Text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computational Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Automatic chest x-ray analysis","Feature selection","Neural networks","PHOG","Machine Learning","Automatic TB screening","Artificial Intelligence and Robotics","Data Science"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.cwu.edu/etd/1356"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Tuberculosis (TB) is a respiratory disease which affects millions of people each year, accounting for the tenth leading cause of death worldwide, and is especially prevalent in underdeveloped regions where access to adequate medical care may be limited. Analysis of digital chest radiographs (CXRs) is a common and inexpensive method for the diagnosis of TB; however, a trained radiologist is required to interpret the results, and is subject to human error. Computer-Aided Detection (CAD) systems are a promising machine-learning based solution to automate the diagnosis of TB from CXR images. As the dimensionality of a high-resolution CXR image is very large, image features are used to describe the CXR image in a lower dimension while preserving the elements in the CXR necessary for the detection of TB. In this thesis, I present a set of image features using Pyramid Histogram of Oriented Gradients, Local Binary Patterns, and Principal Component Analysis which provides high classifier performance on two publicly available CXR datasets, and compare my results to current state-of-the-art research.
"]},{"key":"dc:title","label":"Title","values":["Image Features for Tuberculosis Classification in Digital Chest Radiographs"]}]}],"canonical_facts":{"dc:contributor":["Szilard Vajda","Donald Davendra","Razvan Andonie"],"dc:creator":["Hooper, Brian"],"dc:date.available":["2020-06-10T07:00:00Z"],"dc:description.abstract":["Tuberculosis (TB) is a respiratory disease which affects millions of people each year, accounting for the tenth leading cause of death worldwide, and is especially prevalent in underdeveloped regions where access to adequate medical care may be limited. Analysis of digital chest radiographs (CXRs) is a common and inexpensive method for the diagnosis of TB; however, a trained radiologist is required to interpret the results, and is subject to human error. Computer-Aided Detection (CAD) systems are a promising machine-learning based solution to automate the diagnosis of TB from CXR images. As the dimensionality of a high-resolution CXR image is very large, image features are used to describe the CXR image in a lower dimension while preserving the elements in the CXR necessary for the detection of TB. In this thesis, I present a set of image features using Pyramid Histogram of Oriented Gradients, Local Binary Patterns, and Principal Component Analysis which provides high classifier performance on two publicly available CXR datasets, and compare my results to current state-of-the-art research.
"],"dc:identifier":["https://digitalcommons.cwu.edu/etd/1356"],"dc:subject":["Automatic chest x-ray analysis","Feature selection","Neural networks","PHOG","Machine Learning","Automatic TB screening","Artificial Intelligence and Robotics","Data Science"],"dc:title":["Image Features for Tuberculosis Classification in Digital Chest Radiographs"],"dc:type":["Text"],"thesis:degree_discipline":["Computational Science"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-07-24T01:37:48Z"}