{"id":{"repo_id":"houston","oai_identifier":"oai:uh-ir.tdl.org:10657/19471"},"canonical_url":"https://search.dev.ndltd.org/etd/houston/oai:uh-ir.tdl.org:10657/19471","repository":{"repo_id":"houston","name":"University of Houston","base_url":"https://uh-ir.tdl.org/server/oai/request"},"display":{"title":"Anthropomorphic Model for Medical Image Quality Assessment","abstract":"This dissertation explores advancements in task-based image quality assessment through the development and evaluation of an anthropomorphic visual search model observer. The model incorporates a novel threshold mechanism inspired by human visual system principles, particularly emphasizing the selective processing of high-salience features. This mechanism aims to enhance discrimination performance by filtering out irrelevant variability and noise, effectively improving the efficiency and accuracy of image analysis. The proposed model builds upon foundational visual search frameworks and employs a two-stage approach: candidate selection and decision-making. Thresholding during the candidate selection stage dynamically refines regions of interest, while stage-specific feature usage in the decision-making stage optimizes diagnostic accuracy. These innovations allow the model to align more closely with human visual behaviors, offering robust predictions of observer performance and practical applicability to real-world diagnostic imaging. Extensive experiments were conducted to validate the model, including simulations with Gabor features, feature selection strategies, and thresholding studies across single and multi-feature scenarios. Results demonstrate that thresholding not only improves observer performance but also reduces training resource requirements, enabling effective model training with fewer images. Furthermore, comparisons with human observer performance highlight the model’s ability to replicate critical aspects of human decision-making in visual search tasks. The findings of this research contribute to the advancement of model observers for medical image quality assessment, providing an innovative framework for optimizing imaging systems and diagnostic tasks.","abstract_html":"This dissertation explores advancements in task-based image quality assessment through the development and evaluation of an anthropomorphic visual search model observer. The model incorporates a novel threshold mechanism inspired by human visual system principles, particularly emphasizing the selective processing of high-salience features. This mechanism aims to enhance discrimination performance by filtering out irrelevant variability and noise, effectively improving the efficiency and accuracy of image analysis. The proposed model builds upon foundational visual search frameworks and employs a two-stage approach: candidate selection and decision-making. Thresholding during the candidate selection stage dynamically refines regions of interest, while stage-specific feature usage in the decision-making stage optimizes diagnostic accuracy. These innovations allow the model to align more closely with human visual behaviors, offering robust predictions of observer performance and practical applicability to real-world diagnostic imaging. Extensive experiments were conducted to validate the model, including simulations with Gabor features, feature selection strategies, and thresholding studies across single and multi-feature scenarios. Results demonstrate that thresholding not only improves observer performance but also reduces training resource requirements, enabling effective model training with fewer images. Furthermore, comparisons with human observer performance highlight the model’s ability to replicate critical aspects of human decision-making in visual search tasks. The findings of this research contribute to the advancement of model observers for medical image quality assessment, providing an innovative framework for optimizing imaging systems and diagnostic tasks.","abstract_has_math":false,"creators":["Lin, Hongwei"],"institution":"University of Houston","degree_name":"Doctor of Philosophy","degree_level":null,"degree_discipline":"Biomedical Engineering","degree_department":null,"school":null,"contributors":[],"advisors":["Gifford, Howard"],"committee_chairs":[],"committee_members":["Wang, Lu","Zhang, Yingchun","Francis, Joseph T","Das, Mini"],"year":2025,"date_issued":"2025-05","date_published":"2025-05","updated_at":"2026-07-24T02:32:44Z","subjects":["Biomedical engineering"],"languages":["English"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10657/19471","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Gifford, Howard"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Wang, Lu","Zhang, Yingchun","Francis, Joseph T","Das, Mini"]},{"key":"dc:creator","label":"Author","values":["Lin, Hongwei"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-06-20T17:16:10Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-05"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Biomedical Engineering"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Houston"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Biomedical engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["English"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10657/19471"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This dissertation explores advancements in task-based image quality assessment through the development and evaluation of an anthropomorphic visual search model observer. The model incorporates a novel threshold mechanism inspired by human visual system principles, particularly emphasizing the selective processing of high-salience features. This mechanism aims to enhance discrimination performance by filtering out irrelevant variability and noise, effectively improving the efficiency and accuracy of image analysis. The proposed model builds upon foundational visual search frameworks and employs a two-stage approach: candidate selection and decision-making. Thresholding during the candidate selection stage dynamically refines regions of interest, while stage-specific feature usage in the decision-making stage optimizes diagnostic accuracy. These innovations allow the model to align more closely with human visual behaviors, offering robust predictions of observer performance and practical applicability to real-world diagnostic imaging. Extensive experiments were conducted to validate the model, including simulations with Gabor features, feature selection strategies, and thresholding studies across single and multi-feature scenarios. Results demonstrate that thresholding not only improves observer performance but also reduces training resource requirements, enabling effective model training with fewer images. Furthermore, comparisons with human observer performance highlight the model’s ability to replicate critical aspects of human decision-making in visual search tasks. The findings of this research contribute to the advancement of model observers for medical image quality assessment, providing an innovative framework for optimizing imaging systems and diagnostic tasks."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Anthropomorphic Model for Medical Image Quality Assessment"]}]}],"canonical_facts":{"dc:contributor.advisor":["Gifford, Howard"],"dc:contributor.committeemember":["Wang, Lu","Zhang, Yingchun","Francis, Joseph T","Das, Mini"],"dc:creator":["Lin, Hongwei"],"dc:date.accessioned":["2025-06-20T17:16:10Z"],"dc:date.issued":["2025-05"],"dc:description.abstract":["This dissertation explores advancements in task-based image quality assessment through the development and evaluation of an anthropomorphic visual search model observer. The model incorporates a novel threshold mechanism inspired by human visual system principles, particularly emphasizing the selective processing of high-salience features. This mechanism aims to enhance discrimination performance by filtering out irrelevant variability and noise, effectively improving the efficiency and accuracy of image analysis. The proposed model builds upon foundational visual search frameworks and employs a two-stage approach: candidate selection and decision-making. Thresholding during the candidate selection stage dynamically refines regions of interest, while stage-specific feature usage in the decision-making stage optimizes diagnostic accuracy. These innovations allow the model to align more closely with human visual behaviors, offering robust predictions of observer performance and practical applicability to real-world diagnostic imaging. Extensive experiments were conducted to validate the model, including simulations with Gabor features, feature selection strategies, and thresholding studies across single and multi-feature scenarios. Results demonstrate that thresholding not only improves observer performance but also reduces training resource requirements, enabling effective model training with fewer images. Furthermore, comparisons with human observer performance highlight the model’s ability to replicate critical aspects of human decision-making in visual search tasks. The findings of this research contribute to the advancement of model observers for medical image quality assessment, providing an innovative framework for optimizing imaging systems and diagnostic tasks."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/10657/19471"],"dc:language.iso":["English"],"dc:subject":["Biomedical engineering"],"dc:title":["Anthropomorphic Model for Medical Image Quality Assessment"],"dc:type":["Thesis"],"thesis:degree_discipline":["Biomedical Engineering"],"thesis:degree_name":["Doctor of Philosophy"],"thesis:institution_name":["University of Houston"]},"updated_at":"2026-07-24T02:32:44Z"}