Deeply Supervised Active Learning for Finger Bones Segmentation

Page view(s)
12
Checked on Nov 23, 2023
Deeply Supervised Active Learning for Finger Bones Segmentation
Title:
Deeply Supervised Active Learning for Finger Bones Segmentation
Journal Title:
2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
Publication Date:
27 August 2020
Citation:
Z. Zhao, X. Yang, B. Veeravalli and Z. Zeng, "Deeply Supervised Active Learning for Finger Bones Segmentation," 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2020, pp. 1620-1623, doi: 10.1109/EMBC44109.2020.9176662.
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.Clinical relevance— The proposed method only needs a few annotated samples on the finger bones task to achieve comparable results in comparison with full annotation, which can be used to segment finger bones for medical practices, and generalized into other clinical applications.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Singapore-China - NRF-NSFC Grant
Grant Reference no. : Grant No. NRF2016NRF-NSFC001-111
Description:
© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
1558-4615
ISBN:
978-1-7281-1990-8
Files uploaded: