Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
3D reconstruction from bi-planar radiographs
Development of a pipeline for learning-based 3D reconstruction from bi-planar radiographs using anatomical mesh templates.
Keywords: 3D reconstruction, deep learning, mesh, medical imaging, X-ray, digitally
reconstructed radiograph (DRR), style transfer, computed tomography (CT)
Reconstruction of 3D surfaces from sparse 2D data is a challenging problem that attracted increasing attention also in the medical field where image acquisition is expensive and the patients often bear high radiation doses (CT, fluoroscopy). Further, advances in computer-guided surgical assistant systems and preoperative planning necessitate fast 3D reconstruction from scarce image data. Recent learning-based approaches showed notable success in reconstructing primitive objects leveraging abundant artificial data sets. However, quality 3D data in the clinical context is often scarce. This motivates the exploitation of domain knowledge in form of anatomical shape priors to simplify the reconstruction problem. Further, mesh-sensitive applications (e.g., finite element analysis of implant design) greatly benefit from pre-defined mesh topologies. Thus, we want to implement and train a learning-based patient-specific 3D reconstruction from bi-planar radiographs based on altering anatomical template meshes. The end-to-end mesh prediction facilitates patient-specific musculoskeletal modeling, finite element analysis, or preoperative planning.
Reconstruction of 3D surfaces from sparse 2D data is a challenging problem that attracted increasing attention also in the medical field where image acquisition is expensive and the patients often bear high radiation doses (CT, fluoroscopy). Further, advances in computer-guided surgical assistant systems and preoperative planning necessitate fast 3D reconstruction from scarce image data. Recent learning-based approaches showed notable success in reconstructing primitive objects leveraging abundant artificial data sets. However, quality 3D data in the clinical context is often scarce. This motivates the exploitation of domain knowledge in form of anatomical shape priors to simplify the reconstruction problem. Further, mesh-sensitive applications (e.g., finite element analysis of implant design) greatly benefit from pre-defined mesh topologies. Thus, we want to implement and train a learning-based patient-specific 3D reconstruction from bi-planar radiographs based on altering anatomical template meshes. The end-to-end mesh prediction facilitates patient-specific musculoskeletal modeling, finite element analysis, or preoperative planning.
The goal of this project is to develop a pipeline that reconstructs patient-specific geometries given only biplanar radiographs and a template mesh of the desired anatomical structure as inputs.
The goal of this project is to develop a pipeline that reconstructs patient-specific geometries given only biplanar radiographs and a template mesh of the desired anatomical structure as inputs.
moritz.jokeit@hest.ethz.ch (if you are applying for an internship, please note that we cannot provide a salary since we are a university department)
moritz.jokeit@hest.ethz.ch (if you are applying for an internship, please note that we cannot provide a salary since we are a university department)