Gallagher, Kiana2026-04-272026-04-272026https://hdl.handle.net/1828/23730Photon-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.encomputed tomographymachine learningmedical physicslow-dose CTphoton-counting CTJamie Cassels Undergraduate Research Awards (JCURA)PosterDepartment of Physics and Astronomy