Date of Award

5-2023

Document Type

Open Access Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Daniel Haehn

Second Advisor

Dan Simovici

Third Advisor

Jens Rister

Abstract

The Drosophila fruit fly is a well-established model organism for studying vision and neural perception. In this research, we focused on segmenting and analyzing photoreceptor cells in the Drosophila retina, specifically rhabdomeres. To facilitate our study, we acquired a comprehensive 3D dataset of Drosophila retina EM images and developed an automated segmentation pipeline using computer vision techniques. We evaluated the performance of our pipeline using automated metrics on Wild Type CS 1 and Nina D1 Mutant Drosophila datasets and prototyped a 3D model of segmented cells. The generated segmentation masks and 3D models of photoreceptor cells contribute to a better understanding of Drosophila vision and neural perception, and may have implications for further studies in developmental biology, and neurobiology.

Share

COinS