Digital chemical pathology

The field of pathology has relied on traditional morphological examination for decades, which can be time-consuming and costly for low-resource institutions. However, recent advancements in digital pathology and machine learning have shown promise in streamlining the process and improving healthcare outcomes for patients. In this thesis, we introduce a new technique called "Digital Chemical Pathology" (DCP), which integrates label-free imaging methods like chemical imaging with innovative machine learning techniques to measure and analyze both the morphology and chemistry of pathology samples. By being sensitive to chemical properties and considering morphology, DCP aims to provide a more comprehensive molecular analysis of tissue and aid in diagnosis and prognosis. As a result of DCP, we expect to alter the current workflow of pathology, making it faster, more accurate, and more accessible to a wider range of patients, ultimately enhancing healthcare for everyone.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Chemical Engineering

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2023

Author dc:creator

• Falahkheirkhah, Kianoush

Contributors dc:contributor

• Bhargava, Rohit
• Zhao, Huimin
• Rao, Christopher V
• Harley, Brendan A

• Chemical Imaging
• Digital Pathology
• Machine Learning
• Computer Vision

Statement dc:rights

• Copyright 2023 Kianoush Falahkheirkhah

Language dc:language

en, eng

Handle dc:identifier

https://hdl.handle.net/2142/120292

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F120292