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 proceedingConference contributionpeer-review

9 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 languageEnglish
Title of host publicationProceedings - 2018 IEEE 30th International Conference on Tools with Artificial Intelligence, ICTAI 2018
PublisherIEEE Computer Society
Pages20-24
Number of pages5
ISBN (Electronic)9781538674499
DOIs
Publication statusPublished - 13 Dec 2018
Externally publishedYes
Event30th International Conference on Tools with Artificial Intelligence, ICTAI 2018 - Volos, Greece
Duration: 5 Nov 20187 Nov 2018

Publication series

NameProceedings - International Conference on Tools with Artificial Intelligence, ICTAI
Volume2018-November
ISSN (Print)1082-3409

Conference

Conference30th International Conference on Tools with Artificial Intelligence, ICTAI 2018
Country/TerritoryGreece
CityVolos
Period5/11/187/11/18

Keywords

  • Fully Convolutional Network
  • Gastric Tumor
  • Segmentation

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'GT-net: A deep learning network for gastric tumor diagnosis'. Together they form a unique fingerprint.

Cite this