SIA OpenIR  > 光电信息技术研究室
LumNet: A Deep Neural Network for Lumbar Paraspinal Muscles Segmentation
Zhang YD(张英迪)1,2,3,4,5; Shi ZL(史泽林)1,4,5; Wang H(王欢)6; Yan CN(阎崇楠)6; Wang LB(王蓝博)6; Mu YM(穆月明)6; Liu YP(刘云鹏)1,4,5; Wu SH(邬抒航)1,4,5; Liu TC(刘天赐1,4,5
Department光电信息技术研究室
Conference Name32nd Australasian Joint Conference on Artificial Intelligence, AI 2019
Conference DateDecember 2-5, 2019
Conference PlaceAdelaide, SA, Australia
Source PublicationAI 2019: Advances in Artificial Intelligence - 32nd Australasian Joint Conference, 2019, Proceedings
PublisherSpringer
Publication PlaceBerlin
2019
Pages574-585
Indexed ByEI
EI Accession number20195107876112
Contribution Rank1
ISSN0302-9743
ISBN978-3-030-35287-5
KeywordConvolutional neural networks attention mechanism lumber paraspinal muscles segmentation attention mechanism
AbstractLumber paraspinal muscles (LPM) segmentation is of essential importance in predicting response to treatment of low back pain. To date, all LPM segmentation methods are manually based instead of automatic. Manual segmentation of LPM requires vast radiological knowledge and experience. Moreover, the manual segmentation usually induces subjective variance. Therefore, an automatic segmentation is desireable. It is challenging to achieve automatic segmentation mainly because the ambiguous boundary of the LPM can be very difficult to locate. In this paper, we present a novel encoder-decoder and attention based deep convolutional neural network (CNN) to address this problem. With the help of skip connections, the encoder-decoder structure can capture both shadow and deep features which represent local and global information. Pre-trained VGG11 in ImageNet performed as encoder. In the decoder part, an attention block is applied to recalibrate the input feature. With the help of attention block, meaningful features are highlighted while irrelevant features are suppressed. To fully evaluate the performance of our proposed network, we construct the first large-scale LPM segmentation dataset with 1080 images and its segmentation masks. Experimental results show that our proposed network can not only achieve a good LPM segmentation result with a high dice score of 0.94 but also outperforms other state-of-the-art segmentation methods.
Language英语
Document Type会议论文
Identifierhttp://ir.sia.cn/handle/173321/26061
Collection光电信息技术研究室
Corresponding AuthorZhang YD(张英迪)
Affiliation1.Shenyang Institute of Automation, Chinese Academy of Sciences, Beijing, China; Institute for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Beijing, China; Key Lab of Opto-Electronic Information Process, Shenyang, China;
2.The Key Lab of Image Understanding and Computer Vision, Shenyang, China;
3.Spine Surgery Department, Shengjing Hospital, Shenyang, China
4.Key Lab of Opto-Electronic Information Process, Shenyang, China
5.The Key Lab of Image Understanding and Computer Vision, Shenyang, China
6.Spine Surgery Department, Shengjing Hospital, Shenyang, China
Recommended Citation
GB/T 7714
Zhang YD,Shi ZL,Wang H,et al. LumNet: A Deep Neural Network for Lumbar Paraspinal Muscles Segmentation[C]. Berlin:Springer,2019:574-585.
Files in This Item:
File Name/Size DocType Version Access License
LumNet_ A Deep Neura(6801KB)会议论文 开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang YD(张英迪)]'s Articles
[Shi ZL(史泽林)]'s Articles
[Wang H(王欢)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang YD(张英迪)]'s Articles
[Shi ZL(史泽林)]'s Articles
[Wang H(王欢)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang YD(张英迪)]'s Articles
[Shi ZL(史泽林)]'s Articles
[Wang H(王欢)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: LumNet_ A Deep Neural Network for Lumbar Paraspinal Muscles Segmentation.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.