A Coarse Feature Reuse Deep Neural Network for CXR Lesion Detection

Xinquan Yang; Xuechen Li; Linlin Shen; Min Cao; Changen Zhou

doi:10.1109/ITME53901.2021.00070

A Coarse Feature Reuse Deep Neural Network for CXR Lesion Detection

Xinquan Yang
, Xuechen Li
, Linlin Shen
, Min Cao
, Changen Zhou

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

1 Citation (Scopus)

Abstract

Lung disease screening using Chest x-ray (CXR) radiographs can obviously decrease the incidence of lung cancer. Using computer-aided diagnosis system to assist doctors in lung disease screening can greatly improve the diagnosis efficiency. In this paper, a coarse feature reuse deep neural network for CXR lesion detection is proposed. Firstly, we design a coarse feature reuse (CFR) block that can reuse low-level semantic features and extract high-level semantic information, which is used to replace the max-pooling layer in the shallow part of the network to achieve better feature extraction. A novel backbone network - RRCNet, which combines RepVGG block and Resblock, is proposed. The RepVggblock is used for better feature extraction at shallow layers and the Resblock is used for better feature fusion at deep layers. Extensive experiments on VinDr-CXR dataset demonstrate that our RRCNet-based detection network outperformes other classic detectors on both mAP (17.67%) and inference speed (0.1426s).

Original language	English
Title of host publication	Proceedings - 11th International Conference on Information Technology in Medicine and Education, ITME 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	307-313
Number of pages	7
ISBN (Electronic)	9781665406796
DOIs	https://doi.org/10.1109/ITME53901.2021.00070
Publication status	Published - 2021
Externally published	Yes
Event	11th International Conference on Information Technology in Medicine and Education, ITME 2021 - Wuyishan, China Duration: 19 Nov 2021 → 21 Nov 2021

Publication series

Name	Proceedings - 11th International Conference on Information Technology in Medicine and Education, ITME 2021

Conference

Conference	11th International Conference on Information Technology in Medicine and Education, ITME 2021
Country/Territory	China
City	Wuyishan
Period	19/11/21 → 21/11/21

UN SDGs

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

SDG 3 Good Health and Well-being

Free Keywords

chest x-ray radiograph
computer-aided detection
medical image
neural network
pulmonary lesion detection

ASJC Scopus subject areas

Computer Science Applications
Information Systems
Information Systems and Management
Health Informatics
Education
Management Information Systems
Computer Networks and Communications

Access to Document

10.1109/ITME53901.2021.00070

Cite this

Yang, X., Li, X., Shen, L., Cao, M., & Zhou, C. (2021). A Coarse Feature Reuse Deep Neural Network for CXR Lesion Detection. In Proceedings - 11th International Conference on Information Technology in Medicine and Education, ITME 2021 (pp. 307-313). (Proceedings - 11th International Conference on Information Technology in Medicine and Education, ITME 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ITME53901.2021.00070

Yang, Xinquan ; Li, Xuechen ; Shen, Linlin et al. / A Coarse Feature Reuse Deep Neural Network for CXR Lesion Detection. Proceedings - 11th International Conference on Information Technology in Medicine and Education, ITME 2021. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 307-313 (Proceedings - 11th International Conference on Information Technology in Medicine and Education, ITME 2021).

@inproceedings{34d4c96a6009428d890ac51a566d9349,

title = "A Coarse Feature Reuse Deep Neural Network for CXR Lesion Detection",

abstract = "Lung disease screening using Chest x-ray (CXR) radiographs can obviously decrease the incidence of lung cancer. Using computer-aided diagnosis system to assist doctors in lung disease screening can greatly improve the diagnosis efficiency. In this paper, a coarse feature reuse deep neural network for CXR lesion detection is proposed. Firstly, we design a coarse feature reuse (CFR) block that can reuse low-level semantic features and extract high-level semantic information, which is used to replace the max-pooling layer in the shallow part of the network to achieve better feature extraction. A novel backbone network - RRCNet, which combines RepVGG block and Resblock, is proposed. The RepVggblock is used for better feature extraction at shallow layers and the Resblock is used for better feature fusion at deep layers. Extensive experiments on VinDr-CXR dataset demonstrate that our RRCNet-based detection network outperformes other classic detectors on both mAP (17.67\%) and inference speed (0.1426s).",

keywords = "chest x-ray radiograph, computer-aided detection, medical image, neural network, pulmonary lesion detection",

author = "Xinquan Yang and Xuechen Li and Linlin Shen and Min Cao and Changen Zhou",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 11th International Conference on Information Technology in Medicine and Education, ITME 2021 ; Conference date: 19-11-2021 Through 21-11-2021",

year = "2021",

doi = "10.1109/ITME53901.2021.00070",

language = "English",

series = "Proceedings - 11th International Conference on Information Technology in Medicine and Education, ITME 2021",

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

pages = "307--313",

booktitle = "Proceedings - 11th International Conference on Information Technology in Medicine and Education, ITME 2021",

address = "United States",

}

Yang, X, Li, X, Shen, L, Cao, M & Zhou, C 2021, A Coarse Feature Reuse Deep Neural Network for CXR Lesion Detection. in Proceedings - 11th International Conference on Information Technology in Medicine and Education, ITME 2021. Proceedings - 11th International Conference on Information Technology in Medicine and Education, ITME 2021, Institute of Electrical and Electronics Engineers Inc., pp. 307-313, 11th International Conference on Information Technology in Medicine and Education, ITME 2021, Wuyishan, China, 19/11/21. https://doi.org/10.1109/ITME53901.2021.00070

A Coarse Feature Reuse Deep Neural Network for CXR Lesion Detection. / Yang, Xinquan; Li, Xuechen; Shen, Linlin et al.
Proceedings - 11th International Conference on Information Technology in Medicine and Education, ITME 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 307-313 (Proceedings - 11th International Conference on Information Technology in Medicine and Education, ITME 2021).

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

TY - GEN

T1 - A Coarse Feature Reuse Deep Neural Network for CXR Lesion Detection

AU - Yang, Xinquan

AU - Li, Xuechen

AU - Shen, Linlin

AU - Cao, Min

AU - Zhou, Changen

PY - 2021

Y1 - 2021

N2 - Lung disease screening using Chest x-ray (CXR) radiographs can obviously decrease the incidence of lung cancer. Using computer-aided diagnosis system to assist doctors in lung disease screening can greatly improve the diagnosis efficiency. In this paper, a coarse feature reuse deep neural network for CXR lesion detection is proposed. Firstly, we design a coarse feature reuse (CFR) block that can reuse low-level semantic features and extract high-level semantic information, which is used to replace the max-pooling layer in the shallow part of the network to achieve better feature extraction. A novel backbone network - RRCNet, which combines RepVGG block and Resblock, is proposed. The RepVggblock is used for better feature extraction at shallow layers and the Resblock is used for better feature fusion at deep layers. Extensive experiments on VinDr-CXR dataset demonstrate that our RRCNet-based detection network outperformes other classic detectors on both mAP (17.67%) and inference speed (0.1426s).

AB - Lung disease screening using Chest x-ray (CXR) radiographs can obviously decrease the incidence of lung cancer. Using computer-aided diagnosis system to assist doctors in lung disease screening can greatly improve the diagnosis efficiency. In this paper, a coarse feature reuse deep neural network for CXR lesion detection is proposed. Firstly, we design a coarse feature reuse (CFR) block that can reuse low-level semantic features and extract high-level semantic information, which is used to replace the max-pooling layer in the shallow part of the network to achieve better feature extraction. A novel backbone network - RRCNet, which combines RepVGG block and Resblock, is proposed. The RepVggblock is used for better feature extraction at shallow layers and the Resblock is used for better feature fusion at deep layers. Extensive experiments on VinDr-CXR dataset demonstrate that our RRCNet-based detection network outperformes other classic detectors on both mAP (17.67%) and inference speed (0.1426s).

KW - chest x-ray radiograph

KW - computer-aided detection

KW - medical image

KW - neural network

KW - pulmonary lesion detection

UR - https://www.scopus.com/pages/publications/85128828152

U2 - 10.1109/ITME53901.2021.00070

DO - 10.1109/ITME53901.2021.00070

M3 - Conference contribution

AN - SCOPUS:85128828152

T3 - Proceedings - 11th International Conference on Information Technology in Medicine and Education, ITME 2021

SP - 307

EP - 313

BT - Proceedings - 11th International Conference on Information Technology in Medicine and Education, ITME 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 11th International Conference on Information Technology in Medicine and Education, ITME 2021

Y2 - 19 November 2021 through 21 November 2021

ER -

Yang X, Li X, Shen L, Cao M, Zhou C. A Coarse Feature Reuse Deep Neural Network for CXR Lesion Detection. In Proceedings - 11th International Conference on Information Technology in Medicine and Education, ITME 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 307-313. (Proceedings - 11th International Conference on Information Technology in Medicine and Education, ITME 2021). doi: 10.1109/ITME53901.2021.00070

A Coarse Feature Reuse Deep Neural Network for CXR Lesion Detection

Abstract

Publication series

Conference

UN SDGs

Free Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this