A Lung-Parenchyma-Contrast Hybrid Network For EGFR Gene Mutation Prediction In Lung Cancer

Meili Liu; Shuo Wang; He Yu; Yongbei Zhu; Liusu Wang; Mingyu Zhang; Zhangjie Wu; Xiaohu Li; Weimin Li; Jie Tian

doi:10.1109/ISBI52829.2022.9761614

A Lung-Parenchyma-Contrast Hybrid Network For EGFR Gene Mutation Prediction In Lung Cancer

Meili Liu
, Shuo Wang
, He Yu
, Yongbei Zhu
, Liusu Wang
, Mingyu Zhang
, Zhangjie Wu
, Xiaohu Li
, Weimin Li
, Jie Tian^*

^*Corresponding author for this work

Sichuan University
Beihang University
Anhui Medical University

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

5 Scopus citations

Abstract

Epidermal growth factor receptor (EGFR) mutation status is critical for lung cancer treatment planning. Current identification relies on invasive biopsy and expensive gene sequencing. Recent studies revealed that CT images combined with deep learning can be used to non-invasively predict EGFR mutation status. However, how to enable the network to focus on the lung parenchyma area and extract discriminative features needs further exploration. In this study, we proposed a lung-parenchyma-contrast (LPC) hybrid network that: 1) uses a fully automatic whole-lung analysis method and enables the model to focus on the lung parenchyma area; 2) extracts local and global lung parenchyma features by a contrastive learning strategy; and 3) jointly performs feature learning and classifier learning to improve predictive performance. We evaluated our network on a large multi-center dataset (2316 patients), which outperforms (AUC=0.827) the previous state-of-the-art methods. Extensive experiments also demonstrated the effectiveness of the contrastive learning modules.†

Original language	English
Title of host publication	IEEE ISBI 2022 Proceedings - 2022 IEEE International Symposium on Biomedical Imaging
Publisher	IEEE Computer Society
ISBN (Electronic)	9781665429238
DOIs	https://doi.org/10.1109/ISBI52829.2022.9761614
State	Published - 2022
Event	19th IEEE International Symposium on Biomedical Imaging, ISBI 2022 - Hybrid, Kolkata, India Duration: 28 Mar 2022 → 31 Mar 2022

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2022-March
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	19th IEEE International Symposium on Biomedical Imaging, ISBI 2022
Country/Territory	India
City	Hybrid, Kolkata
Period	28/03/22 → 31/03/22

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

EGFR gene mutation
computed tomography
contrastive learning
lung cancer
targeted therapy

Access to Document

10.1109/ISBI52829.2022.9761614

Cite this

Liu, M., Wang, S., Yu, H., Zhu, Y., Wang, L., Zhang, M., Wu, Z., Li, X., Li, W., & Tian, J. (2022). A Lung-Parenchyma-Contrast Hybrid Network For EGFR Gene Mutation Prediction In Lung Cancer. In IEEE ISBI 2022 Proceedings - 2022 IEEE International Symposium on Biomedical Imaging (Proceedings - International Symposium on Biomedical Imaging; Vol. 2022-March). IEEE Computer Society. https://doi.org/10.1109/ISBI52829.2022.9761614

@inproceedings{a576fd6be61b4c8d8da4e5f598680a36,

title = "A Lung-Parenchyma-Contrast Hybrid Network For EGFR Gene Mutation Prediction In Lung Cancer",

abstract = "Epidermal growth factor receptor (EGFR) mutation status is critical for lung cancer treatment planning. Current identification relies on invasive biopsy and expensive gene sequencing. Recent studies revealed that CT images combined with deep learning can be used to non-invasively predict EGFR mutation status. However, how to enable the network to focus on the lung parenchyma area and extract discriminative features needs further exploration. In this study, we proposed a lung-parenchyma-contrast (LPC) hybrid network that: 1) uses a fully automatic whole-lung analysis method and enables the model to focus on the lung parenchyma area; 2) extracts local and global lung parenchyma features by a contrastive learning strategy; and 3) jointly performs feature learning and classifier learning to improve predictive performance. We evaluated our network on a large multi-center dataset (2316 patients), which outperforms (AUC=0.827) the previous state-of-the-art methods. Extensive experiments also demonstrated the effectiveness of the contrastive learning modules.†",

keywords = "EGFR gene mutation, computed tomography, contrastive learning, lung cancer, targeted therapy",

author = "Meili Liu and Shuo Wang and He Yu and Yongbei Zhu and Liusu Wang and Mingyu Zhang and Zhangjie Wu and Xiaohu Li and Weimin Li and Jie Tian",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 19th IEEE International Symposium on Biomedical Imaging, ISBI 2022 ; Conference date: 28-03-2022 Through 31-03-2022",

year = "2022",

doi = "10.1109/ISBI52829.2022.9761614",

language = "英语",

series = "Proceedings - International Symposium on Biomedical Imaging",

publisher = "IEEE Computer Society",

booktitle = "IEEE ISBI 2022 Proceedings - 2022 IEEE International Symposium on Biomedical Imaging",

address = "美国",

}

Liu, M , Wang, S, Yu, H, Zhu, Y, Wang, L, Zhang, M, Wu, Z, Li, X, Li, W & Tian, J 2022, A Lung-Parenchyma-Contrast Hybrid Network For EGFR Gene Mutation Prediction In Lung Cancer. in IEEE ISBI 2022 Proceedings - 2022 IEEE International Symposium on Biomedical Imaging. Proceedings - International Symposium on Biomedical Imaging, vol. 2022-March, IEEE Computer Society, 19th IEEE International Symposium on Biomedical Imaging, ISBI 2022, Hybrid, Kolkata, India, 28/03/22. https://doi.org/10.1109/ISBI52829.2022.9761614

A Lung-Parenchyma-Contrast Hybrid Network For EGFR Gene Mutation Prediction In Lung Cancer. / Liu, Meili ; Wang, Shuo; Yu, He et al.
IEEE ISBI 2022 Proceedings - 2022 IEEE International Symposium on Biomedical Imaging. IEEE Computer Society, 2022. (Proceedings - International Symposium on Biomedical Imaging; Vol. 2022-March).

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

TY - GEN

T1 - A Lung-Parenchyma-Contrast Hybrid Network For EGFR Gene Mutation Prediction In Lung Cancer

AU - Liu, Meili

AU - Wang, Shuo

AU - Yu, He

AU - Zhu, Yongbei

AU - Wang, Liusu

AU - Zhang, Mingyu

AU - Wu, Zhangjie

AU - Li, Xiaohu

AU - Li, Weimin

AU - Tian, Jie

PY - 2022

Y1 - 2022

N2 - Epidermal growth factor receptor (EGFR) mutation status is critical for lung cancer treatment planning. Current identification relies on invasive biopsy and expensive gene sequencing. Recent studies revealed that CT images combined with deep learning can be used to non-invasively predict EGFR mutation status. However, how to enable the network to focus on the lung parenchyma area and extract discriminative features needs further exploration. In this study, we proposed a lung-parenchyma-contrast (LPC) hybrid network that: 1) uses a fully automatic whole-lung analysis method and enables the model to focus on the lung parenchyma area; 2) extracts local and global lung parenchyma features by a contrastive learning strategy; and 3) jointly performs feature learning and classifier learning to improve predictive performance. We evaluated our network on a large multi-center dataset (2316 patients), which outperforms (AUC=0.827) the previous state-of-the-art methods. Extensive experiments also demonstrated the effectiveness of the contrastive learning modules.†

AB - Epidermal growth factor receptor (EGFR) mutation status is critical for lung cancer treatment planning. Current identification relies on invasive biopsy and expensive gene sequencing. Recent studies revealed that CT images combined with deep learning can be used to non-invasively predict EGFR mutation status. However, how to enable the network to focus on the lung parenchyma area and extract discriminative features needs further exploration. In this study, we proposed a lung-parenchyma-contrast (LPC) hybrid network that: 1) uses a fully automatic whole-lung analysis method and enables the model to focus on the lung parenchyma area; 2) extracts local and global lung parenchyma features by a contrastive learning strategy; and 3) jointly performs feature learning and classifier learning to improve predictive performance. We evaluated our network on a large multi-center dataset (2316 patients), which outperforms (AUC=0.827) the previous state-of-the-art methods. Extensive experiments also demonstrated the effectiveness of the contrastive learning modules.†

KW - EGFR gene mutation

KW - computed tomography

KW - contrastive learning

KW - lung cancer

KW - targeted therapy

UR - https://www.scopus.com/pages/publications/85129596732

U2 - 10.1109/ISBI52829.2022.9761614

DO - 10.1109/ISBI52829.2022.9761614

M3 - 会议稿件

AN - SCOPUS:85129596732

T3 - Proceedings - International Symposium on Biomedical Imaging

BT - IEEE ISBI 2022 Proceedings - 2022 IEEE International Symposium on Biomedical Imaging

PB - IEEE Computer Society

T2 - 19th IEEE International Symposium on Biomedical Imaging, ISBI 2022

Y2 - 28 March 2022 through 31 March 2022

ER -

A Lung-Parenchyma-Contrast Hybrid Network For EGFR Gene Mutation Prediction In Lung Cancer

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this