Coarse-to-Fine Stacked Fully Convolutional Nets for lymph node segmentation in ultrasound images

Yizhe Zhang; Tin Cheung Ying; Lin Yang; Anil T. Ahuja; Danny Z. Chen

doi:10.1109/BIBM.2016.7822557

Coarse-to-Fine Stacked Fully Convolutional Nets for lymph node segmentation in ultrasound images

Yizhe Zhang, Tin Cheung Ying, Lin Yang, Anil T. Ahuja, Danny Z. Chen

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

57 Citations (Scopus)

Abstract

Ultrasound as a well-established imaging modality is widely used in imaging lymph nodes for clinical diagnosis and disease analysis. Quantitative analysis of lymph node features, morphology, and relations can provide valuable information for diagnosis and immune system studies. For such analysis, it is necessary to first accurately segment the lymph node areas in ultrasound images. In this paper, we develop a new deep learning method, called Coarse-to-Fine Stacked Fully Convolutional Nets (CFS-FCN), for automatically segmenting lymph nodes in ultrasound images. Our method consists of multiple stages of FCN modules. We train the CFS-FCN model to learn the segmentation knowledge from a coarse-to-fine, simple-to-complex manner. A data set of 80 ultrasound images containing both normal and diseased lymph nodes is used in our experiments, which show that our method considerably outperforms the state-of-the-art deep learning methods for lymph node segmentation.

Original language	English
Title of host publication	Proceedings - 2016 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2016
Publisher	IEEE
Pages	443-448
Number of pages	6
ISBN (Electronic)	9781509016105
DOIs	https://doi.org/10.1109/BIBM.2016.7822557
Publication status	Published - 17 Jan 2017
Event	2016 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2016 - Shenzhen, China Duration: 15 Dec 2016 → 18 Dec 2016

Conference

Conference	2016 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2016
Country/Territory	China
City	Shenzhen
Period	15/12/16 → 18/12/16

ASJC Scopus subject areas

Genetics
Medicine (miscellaneous)
Genetics(clinical)
Biochemistry, medical
Biochemistry
Molecular Medicine
Health Informatics

More information

10.1109/BIBM.2016.7822557

Cite this

@inproceedings{51f5afd56b3645bd913da8a8a48b5e09,

title = "Coarse-to-Fine Stacked Fully Convolutional Nets for lymph node segmentation in ultrasound images",

abstract = "Ultrasound as a well-established imaging modality is widely used in imaging lymph nodes for clinical diagnosis and disease analysis. Quantitative analysis of lymph node features, morphology, and relations can provide valuable information for diagnosis and immune system studies. For such analysis, it is necessary to first accurately segment the lymph node areas in ultrasound images. In this paper, we develop a new deep learning method, called Coarse-to-Fine Stacked Fully Convolutional Nets (CFS-FCN), for automatically segmenting lymph nodes in ultrasound images. Our method consists of multiple stages of FCN modules. We train the CFS-FCN model to learn the segmentation knowledge from a coarse-to-fine, simple-to-complex manner. A data set of 80 ultrasound images containing both normal and diseased lymph nodes is used in our experiments, which show that our method considerably outperforms the state-of-the-art deep learning methods for lymph node segmentation.",

author = "Yizhe Zhang and Ying, {Tin Cheung} and Lin Yang and Ahuja, {Anil T.} and Chen, {Danny Z.}",

year = "2017",

month = jan,

day = "17",

doi = "10.1109/BIBM.2016.7822557",

language = "English",

pages = "443--448",

booktitle = "Proceedings - 2016 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2016",

publisher = "IEEE",

address = "United States",

note = "2016 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2016 ; Conference date: 15-12-2016 Through 18-12-2016",

}

Zhang, Y, Ying, TC, Yang, L, Ahuja, AT & Chen, DZ 2017, Coarse-to-Fine Stacked Fully Convolutional Nets for lymph node segmentation in ultrasound images. in Proceedings - 2016 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2016., 7822557, IEEE, pp. 443-448, 2016 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2016, Shenzhen, China, 15/12/16. https://doi.org/10.1109/BIBM.2016.7822557

Coarse-to-Fine Stacked Fully Convolutional Nets for lymph node segmentation in ultrasound images. / Zhang, Yizhe; Ying, Tin Cheung; Yang, Lin et al.
Proceedings - 2016 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2016. IEEE, 2017. p. 443-448 7822557.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Coarse-to-Fine Stacked Fully Convolutional Nets for lymph node segmentation in ultrasound images

AU - Zhang, Yizhe

AU - Ying, Tin Cheung

AU - Yang, Lin

AU - Ahuja, Anil T.

AU - Chen, Danny Z.

PY - 2017/1/17

Y1 - 2017/1/17

N2 - Ultrasound as a well-established imaging modality is widely used in imaging lymph nodes for clinical diagnosis and disease analysis. Quantitative analysis of lymph node features, morphology, and relations can provide valuable information for diagnosis and immune system studies. For such analysis, it is necessary to first accurately segment the lymph node areas in ultrasound images. In this paper, we develop a new deep learning method, called Coarse-to-Fine Stacked Fully Convolutional Nets (CFS-FCN), for automatically segmenting lymph nodes in ultrasound images. Our method consists of multiple stages of FCN modules. We train the CFS-FCN model to learn the segmentation knowledge from a coarse-to-fine, simple-to-complex manner. A data set of 80 ultrasound images containing both normal and diseased lymph nodes is used in our experiments, which show that our method considerably outperforms the state-of-the-art deep learning methods for lymph node segmentation.

AB - Ultrasound as a well-established imaging modality is widely used in imaging lymph nodes for clinical diagnosis and disease analysis. Quantitative analysis of lymph node features, morphology, and relations can provide valuable information for diagnosis and immune system studies. For such analysis, it is necessary to first accurately segment the lymph node areas in ultrasound images. In this paper, we develop a new deep learning method, called Coarse-to-Fine Stacked Fully Convolutional Nets (CFS-FCN), for automatically segmenting lymph nodes in ultrasound images. Our method consists of multiple stages of FCN modules. We train the CFS-FCN model to learn the segmentation knowledge from a coarse-to-fine, simple-to-complex manner. A data set of 80 ultrasound images containing both normal and diseased lymph nodes is used in our experiments, which show that our method considerably outperforms the state-of-the-art deep learning methods for lymph node segmentation.

UR - http://www.scopus.com/inward/record.url?scp=85013270506&partnerID=8YFLogxK

U2 - 10.1109/BIBM.2016.7822557

DO - 10.1109/BIBM.2016.7822557

M3 - Conference article published in proceeding or book

SP - 443

EP - 448

BT - Proceedings - 2016 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2016

PB - IEEE

T2 - 2016 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2016

Y2 - 15 December 2016 through 18 December 2016

ER -

Coarse-to-Fine Stacked Fully Convolutional Nets for lymph node segmentation in ultrasound images

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this