University of Twente Student Theses

Login

Tracking and segmentation, a tool for assessment of human engineered heart tissue

Keekstra, D.L. (2021) Tracking and segmentation, a tool for assessment of human engineered heart tissue.

Full text not available from this repository.

Full Text Status:Access to this publication is restricted
Embargo date:6 May 2022
Abstract:Engineered heart tissues (EHT) are a promising in vitro 3D model for studying heart disease and drug discovery. This study presents a method to analyze microscopic videos of the EHTs automatically. The analysis consists of tracking the movement of the EHT, which is relatively small and therefore challenging, and segmentation of the different parts of the EHT where the difficulty is in the different illuminations and noise. This study proposes template matching with the extension of a novel method that delivers smooth sub-pixel precision trajectories for tracking. For segmentation, deep learning models are used to segment the EHTs. This study presents a framework to evaluate the quality of the tracking and segmentation to assess the outcome of the proposed methods.
Item Type:Essay (Master)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:42 biology, 54 computer science
Programme:Embedded Systems MSc (60331)
Link to this item:http://purl.utwente.nl/essays/88594
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page