Efficient Triple Output Network for Vertebral Segmentation and Identification
顯示簡易詮釋資料 統計資料| 欄位 | 內容 | 語言 |
|---|---|---|
dc.citation.epage |
117985 | en_US |
dc.citation.spage |
117978 | en_US |
dc.citation.volume |
7 | en_US |
dc.citation.woscount |
0 | en_US |
dc.contributor.author |
Chuang, Cheng-Hung | en_US |
dc.contributor.author |
Lin, Chih-Yang | en_US |
dc.contributor.author |
Tsai, Yuan-Yu | en_US |
dc.contributor.author |
Lian, Zhen-You | en_US |
dc.contributor.author |
Xie, Hong-Xia | en_US |
dc.contributor.author |
Hsu, Chih-Chao | en_US |
dc.contributor.author |
Huang, Chung-Lin | en_US |
dc.contributor.department |
電子工程學系及電子研究所 | zh_TW |
dc.contributor.department |
Department of Electronics Engineering and Institute of Electronics | en_US |
dc.date.accessioned |
2019-10-05T00:08:48Z | |
dc.date.available |
2019-10-05T00:08:48Z | |
dc.date.issued |
2019-01-01 | en_US |
dc.description.abstract |
Precise vertebral segmentation provides the basis for spinal image analyses and interventions, such as vertebral compression fracture detection and other abnormalities. Deep learning is a popular and useful paradigm for medical image process. In this paper, we proposed an iterative vertebrae instance segmentation model, which has good generalization ability for segmenting all types of vertebrae, including cervical, thoracic, and lumbar vertebrae. In experimental results, our model not only used 17% less memory but also achieves better performance on vertebrae segmentation compared to existing methods. The existing method provides only two output for segmentation and classification respectively. However, with more memory available, our model is capable of providing third output for accurate anatomical prediction under the same amount of memory. | en_US |
dc.identifier.doi |
10.1109/ACCESS.2019.2934325 | en_US |
dc.identifier.issn |
2169-3536 | en_US |
dc.identifier.journal |
IEEE ACCESS | en_US |
dc.identifier.uri |
http://dx.doi.org/10.1109/ACCESS.2019.2934325 | en_US |
dc.identifier.uri |
https://ir.lib.nycu.edu.tw/handle/11536/152874 | |
dc.identifier.wosnumber |
WOS:000484317000001 | en_US |
dc.language.iso |
en_US | en_US |
dc.subject |
Deep learning | en_US |
dc.subject |
vertebra segmentation | en_US |
dc.subject |
triple output | en_US |
dc.title |
Efficient Triple Output Network for Vertebral Segmentation and Identification | en_US |
dc.type |
Article | en_US |
檔案
本條目沒有附加檔案。
所屬典藏: 期刊論文
引用此條目
Chuang, C.-H., Lin, C.-Y., Tsai, Y.-Y., Lian, Z.-Y., Xie, H.-X., Hsu, C.-C., & Huang, C.-L. (2019). Efficient Triple Output Network for Vertebral Segmentation and Identification. IEEE ACCESS, 7, 117978–117985. https://doi.org/10.1109/ACCESS.2019.2934325
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/152874