Options
Learning CT Segmentation from Label Masks Only
Citation Link: https://doi.org/10.15480/882.15180
Publikationstyp
Conference Paper
Date Issued
2024-04-27
Sprache
English
TORE-DOI
Citation
7th International Conference on Medical Imaging with Deep Learning, MIDL 2024
Contribution to Conference
Publisher Link
Training segmentation models for CT scans in the absence of input data is a challenging problem. Methods based on generative adversarial networks translate images from other modalities but still require additional data and training. Synthesizing images directly from segmentation masks using heuristics can overcome this limitation. However, capabilities for model generalization remain underexplored for these methods. In this study, we generate synthetic data for liver segmentation using organ labels and prior CT knowledge. Ground truth labels serve as a source of information about global structures and are filled with artificial textures in various settings. Segmentation models trained on synthetic data demonstrate sufficient generalization to real CT data, highlighting a perspective of a simple yet powerful approach to data bootstrapping.
Subjects
Semantic Segmentation | CT | Synthetic Data Generation
DDC Class
610: Medicine, Health
006: Special computer methods
616: Deseases
Publication version
publishedVersion
Loading...
Name
85_Learning_CT_Segmentation_fr.pdf
Size
1.54 MB
Format
Adobe PDF