Wirtz, Andreas ; Jung, Florian ; Noll, Matthias ; Wang, Anqi ; Wesarg, Stefan (2021)
Automatic model-based 3D reconstruction of the teeth from five photographs with predefined viewing directions.
SPIE Medical Imaging Conference 2021. virtual Conference (15.-19.02.2021)
doi: 10.1117/12.2582253
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Misalignment of teeth or jaws can impact the ability to chew or speak, increase the risk of gum disease or tooth decay, and potentially inuence a person's (psychological) well-being. Orthodontic treatments of misaligned teeth are complex procedures that employ dental braces to apply forces in order to move the teeth or jaws to their correct position. Photographs are typically used to document the treatment. An automatic analysis of those photographs could support the decision making and monitoring process. In this paper, we propose an automatic model-based end-to-end 3-D reconstruction approach of the teeth from _ve photographs with prede_ned viewing directions (i.e. the photographs used in orthodontic treatment documentation). It uses photo- or view-speci_c 2- D coupled shape models to extract the teeth contours from the images. The shape reconstruction is then carried out by a deformation-based reconstruction approach that utilizes 3-D coupled shape models and minimizes a silhouette-based loss. The optimal model parameters are determined by an optimization which maximizes the overlaps between the projected 2-D outlines of individual teeth of the 3-D model and the contours extracted from the corresponding photograph. After that the point displacements between the projected outline and segmented contour are used to iteratively deform the 3-D shape model of each tooth for all _ve views. Back-projection into shape space ensures that the 3-D coupled shape model consists of (statistically) valid teeth. Evaluation on 22 data sets shows promising results with an average symmetric surface distance of 0.848mm and an average DICE coe_cient of 0.659.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2021 |
| Autor(en): | Wirtz, Andreas ; Jung, Florian ; Noll, Matthias ; Wang, Anqi ; Wesarg, Stefan |
| Art des Eintrags: | Bibliographie |
| Titel: | Automatic model-based 3D reconstruction of the teeth from five photographs with predefined viewing directions |
| Sprache: | Englisch |
| Publikationsjahr: | 15 Februar 2021 |
| Verlag: | SPIE |
| Buchtitel: | Medical Imaging 2021: Image Processing |
| Reihe: | Proceedings of SPIE |
| Band einer Reihe: | 11596 |
| Veranstaltungstitel: | SPIE Medical Imaging Conference 2021 |
| Veranstaltungsort: | virtual Conference |
| Veranstaltungsdatum: | 15.-19.02.2021 |
| DOI: | 10.1117/12.2582253 |
| Kurzbeschreibung (Abstract): | Misalignment of teeth or jaws can impact the ability to chew or speak, increase the risk of gum disease or tooth decay, and potentially inuence a person's (psychological) well-being. Orthodontic treatments of misaligned teeth are complex procedures that employ dental braces to apply forces in order to move the teeth or jaws to their correct position. Photographs are typically used to document the treatment. An automatic analysis of those photographs could support the decision making and monitoring process. In this paper, we propose an automatic model-based end-to-end 3-D reconstruction approach of the teeth from _ve photographs with prede_ned viewing directions (i.e. the photographs used in orthodontic treatment documentation). It uses photo- or view-speci_c 2- D coupled shape models to extract the teeth contours from the images. The shape reconstruction is then carried out by a deformation-based reconstruction approach that utilizes 3-D coupled shape models and minimizes a silhouette-based loss. The optimal model parameters are determined by an optimization which maximizes the overlaps between the projected 2-D outlines of individual teeth of the 3-D model and the contours extracted from the corresponding photograph. After that the point displacements between the projected outline and segmented contour are used to iteratively deform the 3-D shape model of each tooth for all _ve views. Back-projection into shape space ensures that the 3-D coupled shape model consists of (statistically) valid teeth. Evaluation on 22 data sets shows promising results with an average symmetric surface distance of 0.848mm and an average DICE coe_cient of 0.659. |
| Freie Schlagworte: | Statistical shape models (SSM), Dental imaging, 3D Model reconstruction, Convolutional Neural Networks (CNN), Model based segmentations |
| Zusätzliche Informationen: | Art.No.: 11596-21 |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Graphisch-Interaktive Systeme |
| Hinterlegungsdatum: | 19 Apr 2021 07:34 |
| Letzte Änderung: | 19 Apr 2021 07:34 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum