Spatially-constrained Keypoint Matching for Efficient Statistical Shape Modelling
Statistical shape models (SSMs) allow the compact description of the variability of object shapes within a given sample set. They are commonly used in medical imaging to model and analyse the shape of anatomical structures such as organs. The generation of a SSM mainly consists of the calculation of...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2024-09-01
|
| Series: | Current Directions in Biomedical Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/cdbme-2024-1051 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832570484015759360 |
|---|---|
| author | Harkämper Lena Großbröhmer Christoph Himstedt Marian |
| author_facet | Harkämper Lena Großbröhmer Christoph Himstedt Marian |
| author_sort | Harkämper Lena |
| collection | DOAJ |
| description | Statistical shape models (SSMs) allow the compact description of the variability of object shapes within a given sample set. They are commonly used in medical imaging to model and analyse the shape of anatomical structures such as organs. The generation of a SSM mainly consists of the calculation of the average shape and the main directions of variation of the data set. Usually, structured point clouds are used as shape representations. A crucial step in the calculation of the average shape of the data set represents the transformation of the objects into a common reference space in order to average coordinates of corresponding points. When using unstructured point clouds without explicitly defined landmarks, the matching of correspondences remains a challenge. We propose a novel solution for a spatially-constrained keypoint matching (FPFH++). It is based on a first attempt of a feature-based registration using Fast Point Feature Histograms (FPFH) compared to a baseline approach utilizing Coherent Point Drift (CPD). |
| format | Article |
| id | doaj-art-2beac7f76afd4101a53994a0c4caf5af |
| institution | Kabale University |
| issn | 2364-5504 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Current Directions in Biomedical Engineering |
| spelling | doaj-art-2beac7f76afd4101a53994a0c4caf5af2025-02-02T15:45:00ZengDe GruyterCurrent Directions in Biomedical Engineering2364-55042024-09-011021410.1515/cdbme-2024-1051Spatially-constrained Keypoint Matching for Efficient Statistical Shape ModellingHarkämper Lena0Großbröhmer Christoph1Himstedt Marian2Institute of Medical Informatics, University of Lubeck, Lubeck, GermanyInstitute of Medical Informatics, University of Lubeck, Lubeck, GermanyInstitute of Medical Informatics, University of Lubeck, Lubeck, GermanyStatistical shape models (SSMs) allow the compact description of the variability of object shapes within a given sample set. They are commonly used in medical imaging to model and analyse the shape of anatomical structures such as organs. The generation of a SSM mainly consists of the calculation of the average shape and the main directions of variation of the data set. Usually, structured point clouds are used as shape representations. A crucial step in the calculation of the average shape of the data set represents the transformation of the objects into a common reference space in order to average coordinates of corresponding points. When using unstructured point clouds without explicitly defined landmarks, the matching of correspondences remains a challenge. We propose a novel solution for a spatially-constrained keypoint matching (FPFH++). It is based on a first attempt of a feature-based registration using Fast Point Feature Histograms (FPFH) compared to a baseline approach utilizing Coherent Point Drift (CPD).https://doi.org/10.1515/cdbme-2024-1051statistical shape modelsregistrationfeature extraction |
| spellingShingle | Harkämper Lena Großbröhmer Christoph Himstedt Marian Spatially-constrained Keypoint Matching for Efficient Statistical Shape Modelling Current Directions in Biomedical Engineering statistical shape models registration feature extraction |
| title | Spatially-constrained Keypoint Matching for Efficient Statistical Shape Modelling |
| title_full | Spatially-constrained Keypoint Matching for Efficient Statistical Shape Modelling |
| title_fullStr | Spatially-constrained Keypoint Matching for Efficient Statistical Shape Modelling |
| title_full_unstemmed | Spatially-constrained Keypoint Matching for Efficient Statistical Shape Modelling |
| title_short | Spatially-constrained Keypoint Matching for Efficient Statistical Shape Modelling |
| title_sort | spatially constrained keypoint matching for efficient statistical shape modelling |
| topic | statistical shape models registration feature extraction |
| url | https://doi.org/10.1515/cdbme-2024-1051 |
| work_keys_str_mv | AT harkamperlena spatiallyconstrainedkeypointmatchingforefficientstatisticalshapemodelling AT großbrohmerchristoph spatiallyconstrainedkeypointmatchingforefficientstatisticalshapemodelling AT himstedtmarian spatiallyconstrainedkeypointmatchingforefficientstatisticalshapemodelling |