University of Twente Student Theses
Automatic segmentation of microscopic cell images
Munteanu, A.M. (2024) Automatic segmentation of microscopic cell images.
|
PDF
26MB |
| Abstract: | Protoplasts are plant cells without cell walls. They provide a unique single- cell system to underpin several aspects of modern biotechnology. They are important in researching fundamental aspects of cell physiology and cell surface interaction with toxins and pathogens. The segmentation of protoplast cell images proves to be a difficult task even for the current state- of-the-art machine learning models. Even though some of them show good results, most lack accuracy when it comes to automatically segmenting cells from an image. A prevalent challenge in cell imaging is the occurrence of out-of-focus blur, which arises because cells are positioned at different levels along the Z-axis on the chamber slide. This study seeks to enhance automatic segmentation accuracy by training a U-net model with microscopy image annotation masks generated using SAM’s segmentation tools. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Computer Science BSc (56964) |
| Link to this item: | https://purl.utwente.nl/essays/100844 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page