{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/106170"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/106170","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Detection-based 3D-2D vertebra matching","abstract":"The student, Hanchao Yu, submitted this Thesis for approval on 2019-10-09 at 15:07.","abstract_html":"The student, Hanchao Yu, submitted this Thesis for approval on 2019-10-09 at 15:07.","abstract_has_math":false,"creators":["Yu, Hanchao"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Huang, Thomas"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-03-02T21:58:03Z","date_published":"2020-03-02T21:58:03Z","updated_at":"2026-07-22T22:24:45Z","subjects":["deep neural network","3D-2D registration","object detection"],"languages":["en"],"rights":["Copyright 2019 Hanchao Yu"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/106170","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Huang, Thomas"]},{"key":"dc:creator","label":"Author","values":["Yu, Hanchao"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-03-02T21:58:03Z","2019-10-09","2019-12"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["deep neural network","3D-2D registration","object detection"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2019 Hanchao Yu"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/106170"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The student, Hanchao Yu, submitted this Thesis for approval on 2019-10-09 at 15:07.","This Thesis was approved for publication on 2019-10-09 at 15:56.","3D-2D medical image matching is a crucial task in image-guided surgery, image-guided radiation therapy and minimally invasive surgery. The task relies on identifying the correspondence between a 2D reference image and the 2D projection of the 3D target image. In this thesis, we propose a novel image matching framework between 3D CT projection and 2D X-ray image, tailored for vertebra images. The main idea is to train a vertebra detector by means of the deep neural network. The detected vertebra is represented by a bounding box in the 3D CT projection. Next, the bounding box annotated by the doctor on the X-ray image is matched to the corresponding box in the 3D projection. We evaluate our proposed method on our own 3D-2D registration dataset. The experimental results show that our framework outperforms the state-of-the-art neural-network-based keypoint matching methods.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-02-28 without embargo terms","The student, Hanchao Yu, accepted the attached license on 2019-10-09 at 14:48.","DSpace SAF Submission Ingestion Package generated from Vireo submission #14489 on 2020-02-28 at 17:12:47","Made available in DSpace on 2020-03-02T21:58:03Z (GMT). No. of bitstreams: 2 YU-THESIS-2019.pdf: 3293985 bytes, checksum: f291e6db6b8b3a671fd7621184cc4171 (MD5) LICENSE.txt: 4207 bytes, checksum: f28cc938a049dfb1ae8c05abcacec502 (MD5) Previous issue date: 2019-10-09"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Detection-based 3D-2D vertebra matching"]}]}],"canonical_facts":{"dc:contributor":["Huang, Thomas"],"dc:creator":["Yu, Hanchao"],"dc:date":["2020-03-02T21:58:03Z","2019-10-09","2019-12"],"dc:description":["The student, Hanchao Yu, submitted this Thesis for approval on 2019-10-09 at 15:07.","This Thesis was approved for publication on 2019-10-09 at 15:56.","3D-2D medical image matching is a crucial task in image-guided surgery, image-guided radiation therapy and minimally invasive surgery. The task relies on identifying the correspondence between a 2D reference image and the 2D projection of the 3D target image. In this thesis, we propose a novel image matching framework between 3D CT projection and 2D X-ray image, tailored for vertebra images. The main idea is to train a vertebra detector by means of the deep neural network. The detected vertebra is represented by a bounding box in the 3D CT projection. Next, the bounding box annotated by the doctor on the X-ray image is matched to the corresponding box in the 3D projection. We evaluate our proposed method on our own 3D-2D registration dataset. The experimental results show that our framework outperforms the state-of-the-art neural-network-based keypoint matching methods.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-02-28 without embargo terms","The student, Hanchao Yu, accepted the attached license on 2019-10-09 at 14:48.","DSpace SAF Submission Ingestion Package generated from Vireo submission #14489 on 2020-02-28 at 17:12:47","Made available in DSpace on 2020-03-02T21:58:03Z (GMT). No. of bitstreams: 2 YU-THESIS-2019.pdf: 3293985 bytes, checksum: f291e6db6b8b3a671fd7621184cc4171 (MD5) LICENSE.txt: 4207 bytes, checksum: f28cc938a049dfb1ae8c05abcacec502 (MD5) Previous issue date: 2019-10-09"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/106170"],"dc:language":["en"],"dc:rights":["Copyright 2019 Hanchao Yu"],"dc:subject":["deep neural network","3D-2D registration","object detection"],"dc:title":["Detection-based 3D-2D vertebra matching"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:45Z"}