{"id":{"repo_id":"houston","oai_identifier":"oai:uh-ir.tdl.org:10657/17649"},"canonical_url":"https://search.dev.ndltd.org/etd/houston/oai:uh-ir.tdl.org:10657/17649","repository":{"repo_id":"houston","name":"University of Houston","base_url":"https://uh-ir.tdl.org/server/oai/request"},"display":{"title":"3D Torso Image Retrieval of Prior Patients Cases for Enhancing Consultation about Breast Reconstruction Surgery","abstract":"The ability to utilize 3D imaging technology to retrieve and compare cases of previous patients can improve the clarity and precision of the consultations. This dissertation introduces a novel system of 3D torso image retrieval, aimed at enhancing consultation process for breast reconstruction surgeries. The developed method integrates suggestive contours, the structure tensor, and mesh simplification using MeshCNN for 3D model retrieval. By coupling suggestive contours with the structure tensor, crucial features are effectively communicated, capturing prominent edges and features within 3D objects, and providing a concise representation of their geometry. The use of suggestive contours from multiple viewpoints, combined with the structure tensor analysis and the proposed feature descriptor, provided a comprehensive and informative representation of the 3D model's geometry. This approach captured the distinctive silhouette and contour shape characteristics of objects, leading to efficient retrieval of images of the female torso, for applications in breast reconstruction surgery. Extensive experiments involving both proprietary and public datasets were conducted to validate the effectiveness of the proposed method, via an evaluation framework of qualitative and quantitative metrics. The results highlight improved performance of the proposed approach in comparison to existing techniques for retrieval of images of the female torso, demonstrating its potential for applications related to breast reconstruction surgery.","abstract_html":"The ability to utilize 3D imaging technology to retrieve and compare cases of previous patients can improve the clarity and precision of the consultations. This dissertation introduces a novel system of 3D torso image retrieval, aimed at enhancing consultation process for breast reconstruction surgeries. The developed method integrates suggestive contours, the structure tensor, and mesh simplification using MeshCNN for 3D model retrieval. By coupling suggestive contours with the structure tensor, crucial features are effectively communicated, capturing prominent edges and features within 3D objects, and providing a concise representation of their geometry. The use of suggestive contours from multiple viewpoints, combined with the structure tensor analysis and the proposed feature descriptor, provided a comprehensive and informative representation of the 3D model's geometry. This approach captured the distinctive silhouette and contour shape characteristics of objects, leading to efficient retrieval of images of the female torso, for applications in breast reconstruction surgery. Extensive experiments involving both proprietary and public datasets were conducted to validate the effectiveness of the proposed method, via an evaluation framework of qualitative and quantitative metrics. The results highlight improved performance of the proposed approach in comparison to existing techniques for retrieval of images of the female torso, demonstrating its potential for applications related to breast reconstruction surgery.","abstract_has_math":false,"creators":["Noufail, Nassima"],"institution":"University of Houston","degree_name":"Doctor of Philosophy","degree_level":"Doctoral","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Merchant, Fatima"],"committee_chairs":[],"committee_members":["Shah, Shishir","Gregory, Reece","Guoning, Chen"],"year":2024,"date_issued":"2024-04-30","date_published":"2024-04-30","updated_at":"2026-07-24T02:32:24Z","subjects":["image retrieval, suggestive contours, 3D torso images."],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10657/17649","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Merchant, Fatima"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Shah, Shishir","Gregory, Reece","Guoning, Chen"]},{"key":"dc:creator","label":"Author","values":["Noufail, Nassima"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-07-26T03:43:27Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-04-30"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Doctoral"]},{"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":["image retrieval, suggestive contours, 3D torso images."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10657/17649"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The ability to utilize 3D imaging technology to retrieve and compare cases of previous patients can improve the clarity and precision of the consultations. This dissertation introduces a novel system of 3D torso image retrieval, aimed at enhancing consultation process for breast reconstruction surgeries. The developed method integrates suggestive contours, the structure tensor, and mesh simplification using MeshCNN for 3D model retrieval. By coupling suggestive contours with the structure tensor, crucial features are effectively communicated, capturing prominent edges and features within 3D objects, and providing a concise representation of their geometry. The use of suggestive contours from multiple viewpoints, combined with the structure tensor analysis and the proposed feature descriptor, provided a comprehensive and informative representation of the 3D model's geometry. This approach captured the distinctive silhouette and contour shape characteristics of objects, leading to efficient retrieval of images of the female torso, for applications in breast reconstruction surgery. Extensive experiments involving both proprietary and public datasets were conducted to validate the effectiveness of the proposed method, via an evaluation framework of qualitative and quantitative metrics. The results highlight improved performance of the proposed approach in comparison to existing techniques for retrieval of images of the female torso, demonstrating its potential for applications related to breast reconstruction surgery."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["3D Torso Image Retrieval of Prior Patients Cases for Enhancing Consultation about Breast Reconstruction Surgery"]}]}],"canonical_facts":{"dc:contributor.advisor":["Merchant, Fatima"],"dc:contributor.committeemember":["Shah, Shishir","Gregory, Reece","Guoning, Chen"],"dc:creator":["Noufail, Nassima"],"dc:date.accessioned":["2024-07-26T03:43:27Z"],"dc:date.issued":["2024-04-30"],"dc:description.abstract":["The ability to utilize 3D imaging technology to retrieve and compare cases of previous patients can improve the clarity and precision of the consultations. This dissertation introduces a novel system of 3D torso image retrieval, aimed at enhancing consultation process for breast reconstruction surgeries. The developed method integrates suggestive contours, the structure tensor, and mesh simplification using MeshCNN for 3D model retrieval. By coupling suggestive contours with the structure tensor, crucial features are effectively communicated, capturing prominent edges and features within 3D objects, and providing a concise representation of their geometry. The use of suggestive contours from multiple viewpoints, combined with the structure tensor analysis and the proposed feature descriptor, provided a comprehensive and informative representation of the 3D model's geometry. This approach captured the distinctive silhouette and contour shape characteristics of objects, leading to efficient retrieval of images of the female torso, for applications in breast reconstruction surgery. Extensive experiments involving both proprietary and public datasets were conducted to validate the effectiveness of the proposed method, via an evaluation framework of qualitative and quantitative metrics. The results highlight improved performance of the proposed approach in comparison to existing techniques for retrieval of images of the female torso, demonstrating its potential for applications related to breast reconstruction surgery."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/10657/17649"],"dc:language.iso":["en"],"dc:subject":["image retrieval, suggestive contours, 3D torso images."],"dc:title":["3D Torso Image Retrieval of Prior Patients Cases for Enhancing Consultation about Breast Reconstruction Surgery"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Doctoral"],"thesis:degree_name":["Doctor of Philosophy"],"thesis:institution_name":["University of Houston"]},"updated_at":"2026-07-24T02:32:24Z"}