Viewpoint estimation in medical imaging

dc.contributor.advisorNicolls, Frederick
dc.contributor.advisorAmayo Paul
dc.contributor.authorHounkanrin, Mahouclo Anicet
dc.date.accessioned2024-07-04T13:53:30Z
dc.date.available2024-07-04T13:53:30Z
dc.date.issued2024
dc.date.updated2024-07-03T13:29:59Z
dc.description.abstractIn medical imaging, the appearance of a certain body part on a radiograph depends not only on the position but also on the orientation of the X-ray imaging system with respect to the patient. Given a 2D image of a 3D scene, the problem of viewpoint estimation aims to determine the position and the orientation of the imaging sensor that resulted in that view. We investigate methods to solve the viewpoint estimation problem for medical images, notably the determination of orientation parameters. Machine learning models, particularly convolutional neural networks (CNNs), are developed to predict a human subject's orientation in a radiograph. Since deep learning models require data for training, we first generate a dataset of digitally reconstructed radiographs (DRRs) from a set of computed tomography (CT) scans using Fourier volume rendering (FVR). The dataset of DRRs is then used to train CNN models for viewpoint regression and classification. A label-softening strategy is used to improve the performance of the classification models. Meanwhile, a geometric structure-aware cost function is used to account for the geometric continuity of the viewpoint space. Several 3D rotation methods such as Euler angle, axis-angle, and quaternions are investigated for viewpoint representation. The results demonstrate that viewpoint estimation in medical imaging can be effectively solved using CNN-based classification and regression models. The geometric structure-aware cost function proves to be essential to the success of classification models for viewpoint estimation. The regression-based models, on the order hand, appear to be sensitive to the type of parametrization used to represent the viewpoints. In particular, the unit quaternion representation of 3D rotations proves to be more effective than other representations for viewpoint regression with CNN models. Moreover, we extend the proposed method to perform viewpoint estimation for natural images. The performance on the PASCAL3D+ dataset indicates that the application of the methods presented is not restricted to medical imaging.
dc.identifier.apacitationHounkanrin, M. A. (2024). <i>Viewpoint estimation in medical imaging</i>. (). ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering. Retrieved from http://hdl.handle.net/11427/40304en_ZA
dc.identifier.chicagocitationHounkanrin, Mahouclo Anicet. <i>"Viewpoint estimation in medical imaging."</i> ., ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering, 2024. http://hdl.handle.net/11427/40304en_ZA
dc.identifier.citationHounkanrin, M.A. 2024. Viewpoint estimation in medical imaging. . ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering. http://hdl.handle.net/11427/40304en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Hounkanrin, Mahouclo Anicet AB - In medical imaging, the appearance of a certain body part on a radiograph depends not only on the position but also on the orientation of the X-ray imaging system with respect to the patient. Given a 2D image of a 3D scene, the problem of viewpoint estimation aims to determine the position and the orientation of the imaging sensor that resulted in that view. We investigate methods to solve the viewpoint estimation problem for medical images, notably the determination of orientation parameters. Machine learning models, particularly convolutional neural networks (CNNs), are developed to predict a human subject's orientation in a radiograph. Since deep learning models require data for training, we first generate a dataset of digitally reconstructed radiographs (DRRs) from a set of computed tomography (CT) scans using Fourier volume rendering (FVR). The dataset of DRRs is then used to train CNN models for viewpoint regression and classification. A label-softening strategy is used to improve the performance of the classification models. Meanwhile, a geometric structure-aware cost function is used to account for the geometric continuity of the viewpoint space. Several 3D rotation methods such as Euler angle, axis-angle, and quaternions are investigated for viewpoint representation. The results demonstrate that viewpoint estimation in medical imaging can be effectively solved using CNN-based classification and regression models. The geometric structure-aware cost function proves to be essential to the success of classification models for viewpoint estimation. The regression-based models, on the order hand, appear to be sensitive to the type of parametrization used to represent the viewpoints. In particular, the unit quaternion representation of 3D rotations proves to be more effective than other representations for viewpoint regression with CNN models. Moreover, we extend the proposed method to perform viewpoint estimation for natural images. The performance on the PASCAL3D+ dataset indicates that the application of the methods presented is not restricted to medical imaging. DA - 2024 DB - OpenUCT DP - University of Cape Town KW - Electrical Engineering LK - https://open.uct.ac.za PY - 2024 T1 - Viewpoint estimation in medical imaging TI - Viewpoint estimation in medical imaging UR - http://hdl.handle.net/11427/40304 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/40304
dc.identifier.vancouvercitationHounkanrin MA. Viewpoint estimation in medical imaging. []. ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering, 2024 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/40304en_ZA
dc.language.rfc3066Eng
dc.publisher.departmentDepartment of Electrical Engineering
dc.publisher.facultyFaculty of Engineering and the Built Environment
dc.subjectElectrical Engineering
dc.titleViewpoint estimation in medical imaging
dc.typeThesis / Dissertation
dc.type.qualificationlevelDoctoral
dc.type.qualificationlevelPhD
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
thesis_ebe_2024_hounkanrin mahouclo anicet.pdf
Size:
9.66 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.72 KB
Format:
Item-specific license agreed upon to submission
Description:
Collections