GT-net: A deep learning network for gastric tumor diagnosis

Yuexiang Li; Xinpeng Xie; Shaoxiong Liu; Xuechen Li; Linlin Shen

doi:10.1109/ICTAI.2018.00014

GT-net: A deep learning network for gastric tumor diagnosis

Yuexiang Li
, Xinpeng Xie
, Shaoxiong Liu
, Xuechen Li
, Linlin Shen

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

18 Citations (Scopus)

Abstract

Gastric cancer is one of the most common cancers, which causes the second largest number of deaths in the world. Traditional diagnosis approach requires pathologists to manually annotate the gastric tumor in gastric slice for cancer identification, which is laborious and time-consuming. In this paper, we proposed a deep learning based framework, namely GT-Net, for automatic segmentation of gastric tumor. The proposed GT-Net adopts different architectures for shallow and deep layers for better feature extraction. We evaluate the proposed framework on publicly available BOT gastric slice dataset. The experimental results show that our GT-Net performs better than state-of-the-art networks like FCN-8s, U-net, and achieved a new state-of-the-art F1 score of 90.88% for gastric tumor segmentation.

Original language	English
Title of host publication	Proceedings - 2018 IEEE 30th International Conference on Tools with Artificial Intelligence, ICTAI 2018
Publisher	IEEE Computer Society
Pages	20-24
Number of pages	5
ISBN (Electronic)	9781538674499
DOIs	https://doi.org/10.1109/ICTAI.2018.00014
Publication status	Published - 13 Dec 2018
Externally published	Yes
Event	30th International Conference on Tools with Artificial Intelligence, ICTAI 2018 - Volos, Greece Duration: 5 Nov 2018 → 7 Nov 2018

Publication series

Name	Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI
Volume	2018-November
ISSN (Print)	1082-3409

Conference

Conference	30th International Conference on Tools with Artificial Intelligence, ICTAI 2018
Country/Territory	Greece
City	Volos
Period	5/11/18 → 7/11/18

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Free Keywords

Fully Convolutional Network
Gastric Tumor
Segmentation

ASJC Scopus subject areas

Software
Artificial Intelligence
Computer Science Applications

Access to Document

10.1109/ICTAI.2018.00014

Cite this

Li, Y., Xie, X., Liu, S., Li, X., & Shen, L. (2018). GT-net: A deep learning network for gastric tumor diagnosis. In Proceedings - 2018 IEEE 30th International Conference on Tools with Artificial Intelligence, ICTAI 2018 (pp. 20-24). Article 8576012 (Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI; Vol. 2018-November). IEEE Computer Society. https://doi.org/10.1109/ICTAI.2018.00014

@inproceedings{fc850d5e018b4d48804188b2eb866ce1,

title = "GT-net: A deep learning network for gastric tumor diagnosis",

abstract = "Gastric cancer is one of the most common cancers, which causes the second largest number of deaths in the world. Traditional diagnosis approach requires pathologists to manually annotate the gastric tumor in gastric slice for cancer identification, which is laborious and time-consuming. In this paper, we proposed a deep learning based framework, namely GT-Net, for automatic segmentation of gastric tumor. The proposed GT-Net adopts different architectures for shallow and deep layers for better feature extraction. We evaluate the proposed framework on publicly available BOT gastric slice dataset. The experimental results show that our GT-Net performs better than state-of-the-art networks like FCN-8s, U-net, and achieved a new state-of-the-art F1 score of 90.88\% for gastric tumor segmentation.",

keywords = "Fully Convolutional Network, Gastric Tumor, Segmentation",

author = "Yuexiang Li and Xinpeng Xie and Shaoxiong Liu and Xuechen Li and Linlin Shen",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 30th International Conference on Tools with Artificial Intelligence, ICTAI 2018 ; Conference date: 05-11-2018 Through 07-11-2018",

year = "2018",

month = dec,

day = "13",

doi = "10.1109/ICTAI.2018.00014",

language = "English",

series = "Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI",

publisher = "IEEE Computer Society",

pages = "20--24",

booktitle = "Proceedings - 2018 IEEE 30th International Conference on Tools with Artificial Intelligence, ICTAI 2018",

address = "United States",

}

Li, Y, Xie, X, Liu, S, Li, X & Shen, L 2018, GT-net: A deep learning network for gastric tumor diagnosis. in Proceedings - 2018 IEEE 30th International Conference on Tools with Artificial Intelligence, ICTAI 2018., 8576012, Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI, vol. 2018-November, IEEE Computer Society, pp. 20-24, 30th International Conference on Tools with Artificial Intelligence, ICTAI 2018, Volos, Greece, 5/11/18. https://doi.org/10.1109/ICTAI.2018.00014

GT-net: A deep learning network for gastric tumor diagnosis. / Li, Yuexiang; Xie, Xinpeng; Liu, Shaoxiong et al.
Proceedings - 2018 IEEE 30th International Conference on Tools with Artificial Intelligence, ICTAI 2018. IEEE Computer Society, 2018. p. 20-24 8576012 (Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI; Vol. 2018-November).

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - GT-net

T2 - 30th International Conference on Tools with Artificial Intelligence, ICTAI 2018

AU - Li, Yuexiang

AU - Xie, Xinpeng

AU - Liu, Shaoxiong

AU - Li, Xuechen

AU - Shen, Linlin

PY - 2018/12/13

Y1 - 2018/12/13

N2 - Gastric cancer is one of the most common cancers, which causes the second largest number of deaths in the world. Traditional diagnosis approach requires pathologists to manually annotate the gastric tumor in gastric slice for cancer identification, which is laborious and time-consuming. In this paper, we proposed a deep learning based framework, namely GT-Net, for automatic segmentation of gastric tumor. The proposed GT-Net adopts different architectures for shallow and deep layers for better feature extraction. We evaluate the proposed framework on publicly available BOT gastric slice dataset. The experimental results show that our GT-Net performs better than state-of-the-art networks like FCN-8s, U-net, and achieved a new state-of-the-art F1 score of 90.88% for gastric tumor segmentation.

AB - Gastric cancer is one of the most common cancers, which causes the second largest number of deaths in the world. Traditional diagnosis approach requires pathologists to manually annotate the gastric tumor in gastric slice for cancer identification, which is laborious and time-consuming. In this paper, we proposed a deep learning based framework, namely GT-Net, for automatic segmentation of gastric tumor. The proposed GT-Net adopts different architectures for shallow and deep layers for better feature extraction. We evaluate the proposed framework on publicly available BOT gastric slice dataset. The experimental results show that our GT-Net performs better than state-of-the-art networks like FCN-8s, U-net, and achieved a new state-of-the-art F1 score of 90.88% for gastric tumor segmentation.

KW - Fully Convolutional Network

KW - Gastric Tumor

KW - Segmentation

UR - https://www.scopus.com/pages/publications/85060802850

U2 - 10.1109/ICTAI.2018.00014

DO - 10.1109/ICTAI.2018.00014

M3 - Conference contribution

AN - SCOPUS:85060802850

T3 - Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI

SP - 20

EP - 24

BT - Proceedings - 2018 IEEE 30th International Conference on Tools with Artificial Intelligence, ICTAI 2018

PB - IEEE Computer Society

Y2 - 5 November 2018 through 7 November 2018

ER -

GT-net: A deep learning network for gastric tumor diagnosis

Abstract

Publication series

Conference

UN SDGs

Free Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this