Exploring the Value of Weakly-Supervised Deep Learning Approaches for Artefact Segmentation in Brightfield Microscopy Images
| dc.contributor.advisor | Ali, Mohammed, juhendaja | |
| dc.contributor.advisor | Fishman, Dmytro, juhendaja | |
| dc.contributor.author | Hollo, Kaspar | |
| dc.contributor.other | Tartu Ülikool. Loodus- ja täppisteaduste valdkond | et |
| dc.contributor.other | Tartu Ülikool. Arvutiteaduse instituut | et |
| dc.date.accessioned | 2023-09-21T08:05:58Z | |
| dc.date.available | 2023-09-21T08:05:58Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract | Brightfield microscopy is of great importance as it offers researchers a relatively simple way to quantify cellular experiments. However, brightfield images often contain a variety of artefacts that should be segmented and thereafter neutralized so that they would not affect the quantitative measurements of cellular experiments. While fully-supervised deep learning models offer state-of-the-art performance in most segmentation tasks in computer vision, it is laborious to acquire the pixel-level labels needed to train these models. Alternatively, segmentation tasks can also be solved using more time- and cost-effective weakly-supervised deep learning models that use image-level labels for training. In this thesis, we compare the performances of fully- (e.g., U-Net) and weakly-supervised approaches (e.g., Score-CAM) to determine whether weakly-supervised approaches could be used as a cheaper but still well-performing solution for segmenting artefacts in brightfield images. Six separate experiments with various fully- and weakly-supervised approaches, image datasets and method ensembles are carried out. The results of the experiments showed that with the number of images and labels currently available, none of the weakly-supervised approaches were able to replicate the performance of the baseline fully-supervised approach. However, some of the weakly supervised approaches, like the combined Score-CAM and U-Net approach, showed promising segmentation results. Moreover, the same approach also showed better generalizability on an unseen dataset than the baseline fully-supervised approach. Future work is required to find the amount of weak supervision signal needed to match the performance of the fully-supervised approaches. | et |
| dc.identifier.uri | https://hdl.handle.net/10062/92311 | |
| dc.language.iso | eng | et |
| dc.publisher | Tartu Ülikool | et |
| dc.rights | openAccess | et |
| dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 International | * |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
| dc.subject | deep learning | et |
| dc.subject | neural networks | et |
| dc.subject | weakly-supervised learning | et |
| dc.subject | brightfield microscopy | et |
| dc.subject | artefacts | et |
| dc.subject.other | magistritööd | et |
| dc.subject.other | informaatika | et |
| dc.subject.other | infotehnoloogia | et |
| dc.subject.other | informatics | et |
| dc.subject.other | infotechnology | et |
| dc.title | Exploring the Value of Weakly-Supervised Deep Learning Approaches for Artefact Segmentation in Brightfield Microscopy Images | et |
| dc.type | Thesis | et |