All microscope imaging is largely affected by inherent resolution limitations because of out-of-focus light and diffraction effects. The traditional approach to restoring the image resolution is to use a deconvolution algorithm to “invert” the effect of convolving the volume with the point spread function. However, these algorithms fall short in several areas such as noise amplification and stopping criterion. In this paper, we try to reconstruct an explicit volumetric representation of the fluorescence density in the sample and fit a neural network to the target z-stack to properly minimize a reconstruction cost function for an optimal result. Additionally, we do a weighted sampling of the point spread function to avoid unnecessary computations and prioritize non-zero signals. In a baseline comparison against the Richardson-Lucy method, our algorithm outperforms RL for images affected with high levels of noise.
","abstract_html":"<p>All microscope imaging is largely affected by inherent resolution limitations because of out-of-focus light and diffraction effects. The traditional approach to restoring the image resolution is to use a deconvolution algorithm to “invert” the effect of convolving the volume with the point spread function. However, these algorithms fall short in several areas such as noise amplification and stopping criterion. In this paper, we try to reconstruct an explicit volumetric representation of the fluorescence density in the sample and fit a neural network to the target z-stack to properly minimize a reconstruction cost function for an optimal result. Additionally, we do a weighted sampling of the point spread function to avoid unnecessary computations and prioritize non-zero signals. In a baseline comparison against the Richardson-Lucy method, our algorithm outperforms RL for images affected with high levels of noise.</p>","abstract_has_math":false,"creators":["Inman, Eric A"],"institution":null,"degree_name":"MS in Computer Science","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Jonathan Ventura","Computer Science","College of Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-03-01T08:00:00Z","date_published":"2023-03-01T08:00:00Z","updated_at":"2026-07-24T01:32:29Z","subjects":["Deconvolution","SIM","Fluorescence","Microscopy","Deep-Learning","Biology","Computer Sciences","Microbiology"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["10.15368/theses.2023.5"],"render_values":[{"text":"10.15368/theses.2023.5","href":"https://doi.org/10.15368/theses.2023.5","code":true}]}]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/2644","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Jonathan Ventura","Computer Science","College of Engineering"]},{"key":"dc:creator","label":"Author","values":["Inman, Eric A"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2023-03-24T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Deconvolution","SIM","Fluorescence","Microscopy","Deep-Learning","Biology","Computer Sciences","Microbiology"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/2644","10.15368/theses.2023.5"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["All microscope imaging is largely affected by inherent resolution limitations because of out-of-focus light and diffraction effects. The traditional approach to restoring the image resolution is to use a deconvolution algorithm to “invert” the effect of convolving the volume with the point spread function. However, these algorithms fall short in several areas such as noise amplification and stopping criterion. In this paper, we try to reconstruct an explicit volumetric representation of the fluorescence density in the sample and fit a neural network to the target z-stack to properly minimize a reconstruction cost function for an optimal result. Additionally, we do a weighted sampling of the point spread function to avoid unnecessary computations and prioritize non-zero signals. In a baseline comparison against the Richardson-Lucy method, our algorithm outperforms RL for images affected with high levels of noise.
"]},{"key":"dc:title","label":"Title","values":["PSF Sampling in Fluorescence Image Deconvolution"]}]}],"canonical_facts":{"dc:contributor":["Jonathan Ventura","Computer Science","College of Engineering"],"dc:creator":["Inman, Eric A"],"dc:date.available":["2023-03-24T07:00:00Z"],"dc:description.abstract":["All microscope imaging is largely affected by inherent resolution limitations because of out-of-focus light and diffraction effects. The traditional approach to restoring the image resolution is to use a deconvolution algorithm to “invert” the effect of convolving the volume with the point spread function. However, these algorithms fall short in several areas such as noise amplification and stopping criterion. In this paper, we try to reconstruct an explicit volumetric representation of the fluorescence density in the sample and fit a neural network to the target z-stack to properly minimize a reconstruction cost function for an optimal result. Additionally, we do a weighted sampling of the point spread function to avoid unnecessary computations and prioritize non-zero signals. In a baseline comparison against the Richardson-Lucy method, our algorithm outperforms RL for images affected with high levels of noise.
"],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/2644","10.15368/theses.2023.5"],"dc:subject":["Deconvolution","SIM","Fluorescence","Microscopy","Deep-Learning","Biology","Computer Sciences","Microbiology"],"dc:title":["PSF Sampling in Fluorescence Image Deconvolution"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["MS in Computer Science"]},"updated_at":"2026-07-24T01:32:29Z"}