Optimizing Segmentation of Neonatal Brain MRI with Partially Annotated Multi-Label Data
| dc.contributor.advisor | Hlybovets, Andriy | |
| dc.contributor.advisor | Brudno, Michael | |
| dc.contributor.author | Kucheruk, Dariia | |
| dc.date.accessioned | 2024-04-04T11:10:44Z | |
| dc.date.available | 2024-04-04T11:10:44Z | |
| dc.date.issued | 2023 | |
| dc.description.abstract | This thesis proposes a multi-label segmentation model for optimizing the segmentation of neonatal brain MRI with partially annotated data. A multi-label segmentation model that addresses the challenges of limited annotated data by modifying the preprocessing, loss function, and postprocessing of the original multi-class label segmentation was developed. The proposed approach aims to improve the accuracy and efficiency of neonatal brain MRI segmentation by leveraging partially annotated data. We evaluate our method on a unique dataset of neonatal brain MRI and demonstrate its effectiveness compared to the models trained on fully annotated data. | en_US |
| dc.identifier.uri | https://ekmair.ukma.edu.ua/handle/123456789/28652 | |
| dc.language.iso | en | en_US |
| dc.status | first published | en_US |
| dc.subject | automatic Segmentation in the Field of Healthcare | en_US |
| dc.subject | evaluation Metrics | en_US |
| dc.subject | place for improvement | en_US |
| dc.subject | the Nature of the Dataset | en_US |
| dc.subject | bachelor's thesis | en_US |
| dc.title | Optimizing Segmentation of Neonatal Brain MRI with Partially Annotated Multi-Label Data | en_US |
| dc.type | Other | en_US |
Files
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: