Back to Search
Start Over
Deeply Supervised Active Learning for Finger Bones Segmentation
- Source :
- 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
- Publication Year :
- 2020
-
Abstract
- Segmentation is a prerequisite yet challenging task for medical image analysis. In this paper, we introduce a novel deeply supervised active learning approach for finger bones segmentation. The proposed architecture is fine-tuned in an iterative and incremental learning manner. In each step, the deep supervision mechanism guides the learning process of hidden layers and selects samples to be labeled. Extensive experiments demonstrated that our method achieves competitive segmentation results using less labeled samples as compared with full annotation.<br />Comment: Accepted version to be published in the 42nd IEEE Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2020, Montreal, Canada
Details
- Database :
- arXiv
- Journal :
- 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
- Publication Type :
- Report
- Accession number :
- edsarx.2005.03225
- Document Type :
- Working Paper
- Full Text :
- https://doi.org/10.1109/EMBC44109.2020.9176662