Detection-based 3D-2D vertebra matching

3D-2D medical image matching is a crucial task in image-guided surgery, image-guided radiation therapy and minimally invasive surgery. The task relies on identifying the correspondence between a 2D reference image and the 2D projection of the 3D target image. In this thesis, we propose a novel image matching framework between 3D CT projection and 2D X-ray image, tailored for vertebra images. The main idea is to train a vertebra detector by means of the deep neural network. The detected vertebra is represented by a bounding box in the 3D CT projection. Next, the bounding box annotated by the doctor on the X-ray image is matched to the corresponding box in the 3D projection. We evaluate our proposed method on our own 3D-2D registration dataset. The experimental results show that our framework outperforms the state-of-the-art neural-network-based keypoint matching methods.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2020

Author dc:creator

• Yu, Hanchao

Contributors dc:contributor

• Huang, Thomas

• deep neural network
• 3D-2D registration
• object detection

Statement dc:rights

• Copyright 2019 Hanchao Yu

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/106170

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F106170