Georgia Institute of Technology
Advanced Techniques in UV Microscopy: Integrating Deep Learning for Autofocusing, Whole Slide Imaging Optimization, and Spicule Detection in Bone Marrow Aspirations
Abstract
dc:description.abstractDeep-ultraviolet (UV) microscopy enables label-free, high-resolution, quantitative molecular imaging and enables unique applications in biomedicine. This is achieved by leveraging the unique absorption of different biomolecules in the deep UV spectrum (200~400nm). While UV microscopy has historically been limited by phototoxicity concerns, recent advances in UV imaging hardware have allowed for live cell imaging for more than six hours with no observable photodamage. This proposal aims to expand the capabilities of UV microscopy for biomedical applications using CNN based architectures. Initially, we will employ a custom benchtop multispectral microscope for single-shot autofocusing. Subsequently, we will utilize a lowcost compact UV microscope for automated whole-slide imaging, incorporating singleshot autofocusing as well. Additionally, the compact UV microscope will be employed for automated spicule detection in bone marrow aspirations to enable an untrained clinician to use the device.
Degree
thesis:*- Level thesis:degree_level
- Masters
- Department dc:contributor.department
- Biomedical Engineering (Joint GT/Emory Department)
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Subramanian, Ajay Rajaraman
- Advisor dc:contributor.advisor
-
- Robles, Francisco E.
Subjects
dc:subject × 3Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1853/77740