Using machine learning to improve the image quality of low-dose photon-counting computed tomography

Simple item page
dc.contributor.authorGallagher, Kiana
dc.date.accessioned2026-04-27T15:05:17Z
dc.date.available2026-04-27T15:05:17Z
dc.date.issued2026
dc.description.abstractPhoton-counting computed tomography (PCCT) systems use detectors that count individual X-ray photons. This makes it possible for PCCT to produce a spectrum of images based on photon energies. PCCT results in clearer images with finer anatomical detail, improved contrast between tissues, and better identification of materials. CT scans require a large number of X-ray views, collectively delivering a substantial ionizing radiation dose to patients. However, lowering the number of views decreases spatial resolution and increases image noise, making fine details harder to distinguish. This project aims to improve the image quality of low-dose PCCT scans by using a machine learning model trained on PCCT images. A U-Net was trained using ground-truth images reconstructed from 360 projections and corresponding low-dose images reconstructed from 90 projections across all energy bins. This work shows that machine learning can be used to improve the image quality of low-dose PCCT. Future work will focus on training the model on new datasets and exploring other models.
dc.description.reviewstatusReviewed
dc.description.scholarlevelUndergraduate
dc.description.sponsorshipJamie Cassels Undergraduate Research Awards (JCURA)
dc.identifier.urihttps://hdl.handle.net/1828/23730
dc.language.isoen
dc.publisherUniversity of Victoria
dc.subjectcomputed tomography
dc.subjectmachine learning
dc.subjectmedical physics
dc.subjectlow-dose CT
dc.subjectphoton-counting CT
dc.subjectJamie Cassels Undergraduate Research Awards (JCURA)
dc.subject.departmentDepartment of Physics and Astronomy
dc.titleUsing machine learning to improve the image quality of low-dose photon-counting computed tomography
dc.typePoster

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
gallagher_kiana_jcura_poster_2026.pdf
Size:
1.48 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.62 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Jamie Cassels Undergraduate Research Awards (JCURA)
 
University of Victoria Libraries

We acknowledge and respect the Lək̓ʷəŋən (Songhees and Esquimalt) Peoples on whose territory the university stands, and the Lək̓ʷəŋən and W̱SÁNEĆ Peoples whose historical relationships with the land continue to this day.