X-ray computed tomography using AI-based reconstruction methods
Martois, Mikael (2022)
2022
Bioteknologian ja biolääketieteen tekniikan kandidaattiohjelma - Bachelor's Programme in Biotechnology and Biomedical Engineering
Lääketieteen ja terveysteknologian tiedekunta - Faculty of Medicine and Health Technology
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Hyväksymispäivämäärä
2022-08-30
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:tuni-202208026171
https://urn.fi/URN:NBN:fi:tuni-202208026171
Tiivistelmä
Computed tomography (CT) is based on the transmission and attenuation of X-ray radiation through the imaged object. In CT imaging, an X-ray image is taken from the object from several different angles. These X-ray images project the inner structure of the object into two-dimensional (2D) images. The object and its inner structure can be mathematically reconstructed from these 2D projections to create a virtual three-dimensional (3D) model of the object. Several reconstruction methods and algorithms have been introduced to reconstruct the original object. To improve CT reconstruction even further, the newest innovation of the use of artificial intelligence (AI) in the CT reconstruction process has been introduced.
The purpose of this study is to perform a literature review on some of the most recent AI-based CT reconstruction methods. To gain the necessary background information on the topic, the basic theory behind CT and conventional CT reconstruction is discussed at the beginning of the study. Also, the most prominent shortcomings of the conventional CT reconstruction methods are discussed. The theory also includes a small introduction to AI and its use in CT imaging. Once the necessary theoretical background has been discussed, the AI-based reconstruction methods are introduced and their results are reviewed.
The results show that the application of AI in CT reconstruction has been successful so far. The AI-based reconstruction methods have been successfully used in numerous studies and applications, and the first AI-based reconstruction methods are already commercially available. The newest reconstruction and restoration methods successfully fix the shortcomings of conventional reconstruction methods by increasing image quality and lowering the required radiation dose. Also, the computational cost of high-quality CT image reconstruction has been significantly reduced, which may lead to even more innovations in the area. The research into AI-based CT reconstruction methods is ongoing, and more advances in the field should be expected in the future.
The purpose of this study is to perform a literature review on some of the most recent AI-based CT reconstruction methods. To gain the necessary background information on the topic, the basic theory behind CT and conventional CT reconstruction is discussed at the beginning of the study. Also, the most prominent shortcomings of the conventional CT reconstruction methods are discussed. The theory also includes a small introduction to AI and its use in CT imaging. Once the necessary theoretical background has been discussed, the AI-based reconstruction methods are introduced and their results are reviewed.
The results show that the application of AI in CT reconstruction has been successful so far. The AI-based reconstruction methods have been successfully used in numerous studies and applications, and the first AI-based reconstruction methods are already commercially available. The newest reconstruction and restoration methods successfully fix the shortcomings of conventional reconstruction methods by increasing image quality and lowering the required radiation dose. Also, the computational cost of high-quality CT image reconstruction has been significantly reduced, which may lead to even more innovations in the area. The research into AI-based CT reconstruction methods is ongoing, and more advances in the field should be expected in the future.
Kokoelmat
- Kandidaatintutkielmat [9039]