eprintid: 1572777 rev_number: 37 eprint_status: archive userid: 608 dir: disk0/01/57/27/77 datestamp: 2017-09-10 03:46:55 lastmod: 2021-11-23 00:54:54 status_changed: 2018-03-13 11:54:16 type: proceedings_section metadata_visibility: show creators_name: Pichat, J creators_name: Iglesias, JE creators_name: Nousias, S creators_name: Yousry, T creators_name: Ourselin, S creators_name: Modat, M title: Part-to-Whole Registration of Histology and MRI Using Shape Elements ispublished: pub divisions: UCL divisions: B02 divisions: C07 divisions: D07 divisions: F82 divisions: B04 divisions: C05 divisions: F42 keywords: IMAGE REGISTRATION, FRECHET DISTANCE, SECTIONS, CURVES, BRAIN, Shape, Conferences, Reliability note: © 2017 IEEE. This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: Image registration between histology and magnetic resonance imaging (MRI) is a challenging task due to differences in structural content and contrast. Too thick and wide specimens cannot be processed all at once and must be cut into smaller pieces. This dramatically increases the complexity of the problem, since each piece should be individually and manually pre-aligned. To the best of our knowledge, no automatic method can reliably locate such piece of tissue within its respective whole in the MRI slice, and align it without any prior information. We propose here a novel automatic approach to the joint problem of multi-modal registration between histology and MRI, when only a fraction of tissue is available from histology. The approach relies on the representation of images using their level lines so as to reach contrast invariance. Shape elements obtained via the extraction of bitangents are encoded in a projective-invariant manner, which permits the identification of common pieces of curves between two images. We evaluated the approach on human brain histology and compared resulting alignments against manually annotated ground truths. Considering the complexity of the brain folding patterns, preliminary results are promising and suggest the use of characteristic and meaningful shape elements for improved robustness and efficiency. date: 2017-01-23 date_type: published publisher: IEEE official_url: http://doi.org/10.1109/ICCVW.2017.21 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1416290 doi: 10.1109/ICCVW.2017.21 isbn_13: 9781538610350 language_elements: English lyricists_name: Iglesias Gonzalez, Juan lyricists_name: Modat, Marc lyricists_name: Ourselin, Sebastien lyricists_name: Pichat, Jonas lyricists_name: Yousry, Tarek lyricists_id: JEIGL66 lyricists_id: MMODA28 lyricists_id: SOURS59 lyricists_id: JPICH60 lyricists_id: TAYOU67 actors_name: Ourselin, Sebastien actors_name: Laslett, David actors_id: SOURS59 actors_id: DLASL34 actors_role: owner actors_role: impersonator full_text_status: public series: IEEE International Conference on Computer Vision Workshops publication: 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2017) pagerange: 107-115 pages: 9 event_title: 2017 IEEE International Conference on Computer Vision Workshop (ICCVW) event_location: Venice, Italy event_dates: 22 October 2017 - 29 October 2017 institution: 16th IEEE International Conference on Computer Vision (ICCV) isbn: 9781538610343 issn: 2473-9936 book_title: 2017 IEEE International Conference on Computer Vision Workshops (ICCVW) citation: Pichat, J; Iglesias, JE; Nousias, S; Yousry, T; Ourselin, S; Modat, M; (2017) Part-to-Whole Registration of Histology and MRI Using Shape Elements. In: 2017 IEEE International Conference on Computer Vision Workshops (ICCVW). (pp. pp. 107-115). IEEE Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/1572777/1/Ourselin_1708.08117.pdf