دورية أكاديمية
Shape-constrained Gaussian process regression for surface reconstruction and multimodal, non-rigid image registration.
| العنوان: | Shape-constrained Gaussian process regression for surface reconstruction and multimodal, non-rigid image registration. |
|---|---|
| المؤلفون: | Deregnaucourt T; LIMOS, CNRS UMR 6158, University of Clermont Auvergne, Aubiere, France., Samir C; LIMOS, CNRS UMR 6158, University of Clermont Auvergne, Aubiere, France., Kurtek S; Department of Statistics, Ohio State University, Columbus, OH, USA., Yao AF; LMBP, CNRS UMR 6620 University of Clermont Auvergne, Aubiere, France. |
| المصدر: | Journal of applied statistics [J Appl Stat] 2021 Mar 10; Vol. 49 (7), pp. 1865-1889. Date of Electronic Publication: 2021 Mar 10 (Print Publication: 2022). |
| نوع المنشور: | Journal Article |
| اللغة: | English |
| بيانات الدورية: | Publisher: Routledge, Taylor & Francis Country of Publication: England NLM ID: 9883455 Publication Model: eCollection Cited Medium: Print ISSN: 0266-4763 (Print) Linking ISSN: 02664763 NLM ISO Abbreviation: J Appl Stat Subsets: PubMed not MEDLINE |
| أسماء مطبوعة: | Original Publication: [London] : Routledge, Taylor & Francis, [1974]- |
| مستخلص: | We present a new statistical framework for landmark ?>curve-based image registration and surface reconstruction. The proposed method first elastically aligns geometric features (continuous, parameterized curves) to compute local deformations, and then uses a Gaussian random field model to estimate the full deformation vector field as a spatial stochastic process on the entire surface or image domain. The statistical estimation is performed using two different methods: maximum likelihood and Bayesian inference via Markov Chain Monte Carlo sampling. The resulting deformations accurately match corresponding curve regions while also being sufficiently smooth over the entire domain. We present several qualitative and quantitative evaluations of the proposed method on both synthetic and real data. We apply our approach to two different tasks on real data: (1) multimodal medical image registration, and (2) anatomical and pottery surface reconstruction. Competing Interests: No potential conflict of interest was reported by the author(s). (© 2021 Informa UK Limited, trading as Taylor & Francis Group.) |
| References: | Med Image Anal. 2017 Dec;42:241-256. (PMID: 28881251) IEEE Trans Image Process. 2011 May;20(5):1300-12. (PMID: 21095870) IEEE Trans Pattern Anal Mach Intell. 2011 Jul;33(7):1415-28. (PMID: 20921581) IEEE Trans Image Process. 2013 Jan;22(1):258-71. (PMID: 22910114) IEEE Trans Med Imaging. 2013 Jul;32(7):1153-90. (PMID: 23739795) J Comput Sci Technol. 2008 Nov 1;23(6):1026-1036. (PMID: 20495682) Inf Process Med Imaging. 2013;23:37-48. (PMID: 24683956) |
| فهرسة مساهمة: | Keywords: Bayesian inference; Elastic curve registration; Gaussian random fields; multimodal image registration; smooth deformation vector fields; surface reconstruction |
| تواريخ الأحداث: | Date Created: 20220616 Latest Revision: 20220716 |
| رمز التحديث: | 20240628 |
| مُعرف محوري في PubMed: | PMC9097978 |
| DOI: | 10.1080/02664763.2021.1897970 |
| PMID: | 35707551 |
| قاعدة البيانات: | MEDLINE |
PDF full text from Publisher 
Full Text Finder | تدمد: | 0266-4763 |
|---|---|
| DOI: | 10.1080/02664763.2021.1897970 |