Classification of liver tumors with CEUS based on 3D-CNN

Fengxin Pan; Qinghua Huang; Xuelong Li

doi:10.1109/ICARM.2019.8834190

Classification of liver tumors with CEUS based on 3D-CNN

Fengxin Pan
, Qinghua Huang
, Xuelong Li

School of Artificial Intelligence, OPtics and Electronics

South China University of Technology
Northwestern Polytechnical University Xian

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

44 Scopus citations

Abstract

Liver cancer has the third highest mortality rate in the world. Effective treatment depends on the accurate identification of benign and malignant tumors. This paper proposed a computer-aided system for distinguishing liver lesions based on CEUS, a widely accepted inspection technique. Video sequences are handled by the 3D convolutional neural network (3D-CNN) to extract spatial and temporal features. Meanwhile, the framework is trained by a specific dataset to yield a classification network. According to the results, our system obtained higher performance than the previous system. The average accuracy rate reached 93.1% with ten-fold cross-validation. It is noteworthy that the system is potential and easy to expand to other applications.

Original language	English
Title of host publication	2019 4th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	845-849
Number of pages	5
ISBN (Electronic)	9781728100647
DOIs	https://doi.org/10.1109/ICARM.2019.8834190
State	Published - Jul 2019
Event	4th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2019 - Osaka, Japan Duration: 3 Jul 2019 → 5 Jul 2019

Publication series

Name	2019 4th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2019

Conference

Conference	4th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2019
Country/Territory	Japan
City	Osaka
Period	3/07/19 → 5/07/19

UN SDGs

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

SDG 3 Good Health and Well-being

Access to Document

10.1109/ICARM.2019.8834190

Cite this

Pan, F., Huang, Q., & Li, X. (2019). Classification of liver tumors with CEUS based on 3D-CNN. In 2019 4th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2019 (pp. 845-849). Article 8834190 (2019 4th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICARM.2019.8834190

@inproceedings{d6d12d37fd1341fca0b9c8846426fdb5,

title = "Classification of liver tumors with CEUS based on 3D-CNN",

abstract = "Liver cancer has the third highest mortality rate in the world. Effective treatment depends on the accurate identification of benign and malignant tumors. This paper proposed a computer-aided system for distinguishing liver lesions based on CEUS, a widely accepted inspection technique. Video sequences are handled by the 3D convolutional neural network (3D-CNN) to extract spatial and temporal features. Meanwhile, the framework is trained by a specific dataset to yield a classification network. According to the results, our system obtained higher performance than the previous system. The average accuracy rate reached 93.1\% with ten-fold cross-validation. It is noteworthy that the system is potential and easy to expand to other applications.",

author = "Fengxin Pan and Qinghua Huang and Xuelong Li",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 4th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2019 ; Conference date: 03-07-2019 Through 05-07-2019",

year = "2019",

month = jul,

doi = "10.1109/ICARM.2019.8834190",

language = "英语",

series = "2019 4th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "845--849",

booktitle = "2019 4th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2019",

}

Pan, F, Huang, Q & Li, X 2019, Classification of liver tumors with CEUS based on 3D-CNN. in 2019 4th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2019., 8834190, 2019 4th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2019, Institute of Electrical and Electronics Engineers Inc., pp. 845-849, 4th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2019, Osaka, Japan, 3/07/19. https://doi.org/10.1109/ICARM.2019.8834190

Classification of liver tumors with CEUS based on 3D-CNN. / Pan, Fengxin; Huang, Qinghua; Li, Xuelong.
2019 4th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 845-849 8834190 (2019 4th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2019).

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

TY - GEN

T1 - Classification of liver tumors with CEUS based on 3D-CNN

AU - Pan, Fengxin

AU - Huang, Qinghua

AU - Li, Xuelong

PY - 2019/7

Y1 - 2019/7

N2 - Liver cancer has the third highest mortality rate in the world. Effective treatment depends on the accurate identification of benign and malignant tumors. This paper proposed a computer-aided system for distinguishing liver lesions based on CEUS, a widely accepted inspection technique. Video sequences are handled by the 3D convolutional neural network (3D-CNN) to extract spatial and temporal features. Meanwhile, the framework is trained by a specific dataset to yield a classification network. According to the results, our system obtained higher performance than the previous system. The average accuracy rate reached 93.1% with ten-fold cross-validation. It is noteworthy that the system is potential and easy to expand to other applications.

AB - Liver cancer has the third highest mortality rate in the world. Effective treatment depends on the accurate identification of benign and malignant tumors. This paper proposed a computer-aided system for distinguishing liver lesions based on CEUS, a widely accepted inspection technique. Video sequences are handled by the 3D convolutional neural network (3D-CNN) to extract spatial and temporal features. Meanwhile, the framework is trained by a specific dataset to yield a classification network. According to the results, our system obtained higher performance than the previous system. The average accuracy rate reached 93.1% with ten-fold cross-validation. It is noteworthy that the system is potential and easy to expand to other applications.

UR - https://www.scopus.com/pages/publications/85073240903

U2 - 10.1109/ICARM.2019.8834190

DO - 10.1109/ICARM.2019.8834190

M3 - 会议稿件

AN - SCOPUS:85073240903

T3 - 2019 4th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2019

SP - 845

EP - 849

BT - 2019 4th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 4th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2019

Y2 - 3 July 2019 through 5 July 2019

ER -

Pan F, Huang Q, Li X. Classification of liver tumors with CEUS based on 3D-CNN. In 2019 4th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 845-849. 8834190. (2019 4th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2019). doi: 10.1109/ICARM.2019.8834190

Classification of liver tumors with CEUS based on 3D-CNN

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this