Seminars

View all Seminars  |  Download ICal for this event

Fully automated workflow for processing multi-channel Drosophila Melanogaster optic lobe microscopy images.

Series: Department Seminar

Speaker: Blaz Brence, Zuse Institute Berlin

Date/Time: Jul 01 11:00:00

Location: CSA Auditorium, (Room No. 104, Ground Floor)

Abstract:
Workload presented by image analysis remains a major bottleneck to advances across the life sciences, especially when working with high-dimensional imaging data. To overcome this challenge, we developed a fully automated workflow for processing complex 3D multi-channel microscopy images. Specifically, our workflow is specialized for analysis of confocal images of the Drosophila Melanogaster optic lobe. The workflow consists of multiple stages, combining both traditional and machine learning-based approaches for image analysis and scientific computing. It performs segmentation of brain regions, photoreceptor instance identification and precise localization of synaptic sites. The key novelty of the workflow lies in the automatic alignment of synapses into the reference cylindrical coordinate system, allowing for comparative synaptic analysis across photoreceptors. To demonstrate the workflows applicability, a test analysis with 50 randomly selected images is performed. 

Speaker Bio:
Blaz Brence is a Ph.D. candidate and research assistant at the Zuse Institute Berlin (ZIB), working in Department of Visual and Data-Centric Computing (VDCC). His work focuses on visual data analysis, predominantly biomedical image processing and feature extraction. Prior to his employment at ZIB he worked at German Federal Institute for Material Research and Testing (BAM), specializing in damage detection and visualization in metal and composite objects. He holds a Masters degree in Electronic Engineering.

Microsoft teams link: https://tinyurl.com/4hcuay2e

Host Faculty: Prof. Vijay Natarajan