Feature Description using Autoencoders for Fast 3D Ultrasound Tracking
3D ultrasound imaging is a promising modality for therapy guidance, e.g. in radiation therapy. It is able to provide volumetric soft tissue images in real-time. However, due to low image quality, high noise ratio and high data dimensionality, real-time capable US image processing methods like target...
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-2024-1057 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832570475513905152 |
|---|---|
| author | Wulff Daniel Ernst Floris |
| author_facet | Wulff Daniel Ernst Floris |
| author_sort | Wulff Daniel |
| collection | DOAJ |
| description | 3D ultrasound imaging is a promising modality for therapy guidance, e.g. in radiation therapy. It is able to provide volumetric soft tissue images in real-time. However, due to low image quality, high noise ratio and high data dimensionality, real-time capable US image processing methods like target tracking are challenging. In this study, a feature-based tracking approach is investigated. The FAST feature detector is used to detect local image features in 3D ultrasound images. Two different feature descriptors are tested and evaluated in terms of target tracking: The BRIEF descriptor as well as a slicedwasserstein autoencoder. On the basis of a feature matching algorithm, tracking experiments are executed and evaluated using eight labeled 3D US sequences. The mean tracking error measured is 2.08±1.50mm and 2.29±1.59mm using the autoencoder and the BRIEF descriptor, respectively. The results indicate that using an autoencoder for feature description improves the tracking performance compared to a binary descriptor. The proposed tracking method could be executed in fast runtimes of 137 ms and 256 ms per image on average making it real-time capable. |
| format | Article |
| id | doaj-art-11ebf86caffb475eb5a8fdf840b78e76 |
| 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-11ebf86caffb475eb5a8fdf840b78e762025-02-02T15:45:00ZengDe GruyterCurrent Directions in Biomedical Engineering2364-55042024-09-01102212410.1515/cdbme-2024-1057Feature Description using Autoencoders for Fast 3D Ultrasound TrackingWulff Daniel0Ernst Floris1Institute for Robotics and Cognitive Systems, Ratzeburger Allee 160, Lubeck, GermanyInstitute for Robotics and Cognitive Systems, Ratzeburger Allee 160, Lubeck, Germany3D ultrasound imaging is a promising modality for therapy guidance, e.g. in radiation therapy. It is able to provide volumetric soft tissue images in real-time. However, due to low image quality, high noise ratio and high data dimensionality, real-time capable US image processing methods like target tracking are challenging. In this study, a feature-based tracking approach is investigated. The FAST feature detector is used to detect local image features in 3D ultrasound images. Two different feature descriptors are tested and evaluated in terms of target tracking: The BRIEF descriptor as well as a slicedwasserstein autoencoder. On the basis of a feature matching algorithm, tracking experiments are executed and evaluated using eight labeled 3D US sequences. The mean tracking error measured is 2.08±1.50mm and 2.29±1.59mm using the autoencoder and the BRIEF descriptor, respectively. The results indicate that using an autoencoder for feature description improves the tracking performance compared to a binary descriptor. The proposed tracking method could be executed in fast runtimes of 137 ms and 256 ms per image on average making it real-time capable.https://doi.org/10.1515/cdbme-2024-1057fast detectorbrief descriptorfeature matching |
| spellingShingle | Wulff Daniel Ernst Floris Feature Description using Autoencoders for Fast 3D Ultrasound Tracking Current Directions in Biomedical Engineering fast detector brief descriptor feature matching |
| title | Feature Description using Autoencoders for Fast 3D Ultrasound Tracking |
| title_full | Feature Description using Autoencoders for Fast 3D Ultrasound Tracking |
| title_fullStr | Feature Description using Autoencoders for Fast 3D Ultrasound Tracking |
| title_full_unstemmed | Feature Description using Autoencoders for Fast 3D Ultrasound Tracking |
| title_short | Feature Description using Autoencoders for Fast 3D Ultrasound Tracking |
| title_sort | feature description using autoencoders for fast 3d ultrasound tracking |
| topic | fast detector brief descriptor feature matching |
| url | https://doi.org/10.1515/cdbme-2024-1057 |
| work_keys_str_mv | AT wulffdaniel featuredescriptionusingautoencodersforfast3dultrasoundtracking AT ernstfloris featuredescriptionusingautoencodersforfast3dultrasoundtracking |