Date of Award

12-31-2021

Document Type

Campus Access Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Daniel Haehn

Second Advisor

Dan Simovici

Third Advisor

Funda Durupinar Babur

Abstract

To investigate if adding biological features can improve the existing registration process in state-of-art and deep learning networks, mitochondria masks or lung masks data were used to guide the alignment procedures in real-time. The input datasets consist of unaligned 2D electron microscopy (EM) images that are computationally expensive to map and create 3D volumetric datasets. Feature matching methods and a deep learning framework, MONAI, were implemented to align 2D EM images and 3D lung CT scans, respectively. This approach will guide the registration methods to run faster and with better accuracy for biomedical image analysis.

Comments

Free and open access to this Campus Access Thesis is made available to the UMass Boston community by ScholarWorks at UMass Boston. Those not on campus and those without a UMass Boston campus username and password may gain access to this thesis through resources like Proquest Dissertations & Theses Global or through Interlibrary Loan. If you have a UMass Boston campus username and password and would like to download this work from off-campus, click on the "Off-Campus UMass Boston Users" link above.

Share

COinS