Ziegfeld, Liv (2022) Designing a User Interface for Semi-Automatic Tumor Segmentation: Using Certainty Visualization to Promote Explainability. Master's Thesis / Essay, Computational Cognitive Science.
|
Text
mCCS_2022_ZiegfeldL.pdf Download (14MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
toestemming.pdf Restricted to Registered users only Download (125kB) |
Abstract
Automatic tumor segmentation using deep learning models is a promising avenue for decreasing the inter-observer variability and time needed for manual tumor segmentation. Since tumor segmentation is still carried out manually at the Universitair Medisch Centrum Groningen (UMCG), the first aim of this project was to design a user interface for the computer-aided segmentation of head and neck tumors. To promote appropriate trust and optimal usage of the tool, it was also investigated how to incorporate visualizations of the model’s confidence in its predictions. This should increase the explainability of the model’s output, which has been lacking in similar tools that give binary outputs. Lastly, the project focused on exploring whether a semi-automatic segmentation tool is desired and is clinically feasible at the UMCG
| Item Type: | Thesis (Master's Thesis / Essay) |
|---|---|
| Supervisor name: | Cnossen, F. |
| Degree programme: | Computational Cognitive Science |
| Thesis type: | Master's Thesis / Essay |
| Language: | English |
| Date Deposited: | 11 Oct 2022 14:26 |
| Last Modified: | 21 Oct 2022 12:32 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/28612 |
Actions (login required)
 |
View Item |