Science and Technology Production
Proceedings of the 2024 IEEE International Symposium on Biomedical Imaging (ISBI), 1-4 - Fitting Skeletal Models via Graph-Based Learning
Congress
Date:
2024Publishing House and Editing Place:
IEEESummary *
Skeletonization is a popular shape analysis technique that models an object’s interior as opposed to just its boundary. Fitting template-based skeletal models is a time-consuming process requiring much manual parameter tuning. Recently, machine learning-based methods have shown promise for generating s-reps from object boundaries. In this work, we propose a new skeletonization method which leverages graph convolutional networks to produce skeletal representations (s-reps) from dense segmentation masks. The method is evaluated on both synthetic data and real hippocampus segmentations, achieving promising results and fast inference. Information provided by the agent in SIGEVAKey Words
machine learningcomputer graphicsmedical image segmentationgraphs