2026-09-27T06:40:52Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/108636 2023-07-11 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

Embargo set by: Seth Robbins for item 116263 Lift date: 2022-10-07T22:44:53Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system Koyejo, Oluwasanmi Cole, Patrick Alexander 2020-10-07T22:44:43Z 2020-10-07T22:44:43Z 2022-10-07T22:44:53Z 2020-07-22 2020-08 Radiology exams require exposing a patient to a variable dosage of radiation. The amount of radiation used during the exam directly corresponds to the level of noise in the resulting image. While large amounts of radiation can be dangerous for certain patients, radiologists need an uncorrupted image to make a diagnosis. In our work, we detail methods for simulating low-dose noise for two popular radiology exams: x-ray radiograph and computed tomography. We propose a methodology to recover the uncorrupted exam results given a noisy, or low-dose, sample. Using a two-part criterion that consists of a pixel-wise loss and an adversarial loss, we are able to recover the structure and fine detail of the normal-dose sample. Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2022-08-01 The student, Patrick Cole, accepted the attached license on 2020-07-21 at 15:48. The student, Patrick Cole, submitted this Thesis for approval on 2020-07-21 at 16:16. This Thesis was approved for publication on 2020-07-22 at 11:47. DSpace SAF Submission Ingestion Package generated from Vireo submission #15715 on 2020-10-02 at 15:34:01 Made available in DSpace on 2020-10-07T22:44:43Z (GMT). No. of bitstreams: 3 COLE-THESIS-2020.pdf: 3546309 bytes, checksum: c26b52104a9cc979b9c01adebce11aab (MD5) latex-source.zip: 9205461 bytes, checksum: 54328882559ec27cbcf7cc47d97eba4d (MD5) LICENSE.txt: 4209 bytes, checksum: f56e4ffa562e6f3f4b70104e923a81e7 (MD5) Previous issue date: 2020-07-22 U of I Only application/pdf http://hdl.handle.net/2142/108636 en Copyright 2020 Patrick Cole Machine Learning Artificial Intelligence Computer Vision Radiology X-ray Radiograph Computed Tomography Super Resolution Denoise Image Processing Joint super resolution and denoising: learning to recover sharp features in radiology images text Thesis Computer Science Computer Science University of Illinois at Urbana-Champaign Thesis M.S.