3D Convolutional Neural Networks Fusion Model for Lung Nodule Detection onClinical CT Scans

Guitao Cao; Tiantian Huang; Kai Hou; Wenming Cao; Peng Liu; Jiawei Zhang

doi:10.1109/BIBM.2018.8621468

3D Convolutional Neural Networks Fusion Model for Lung Nodule Detection onClinical CT Scans

Guitao Cao^*
, Tiantian Huang
, Kai Hou
, Wenming Cao
, Peng Liu
, Jiawei Zhang

^*Corresponding author for this work

Software Engineering Institute

East China Normal University
Fudan University
Shenzhen University
Ltd

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

9 Scopus citations

Abstract

Automatically accurate pulmonary nodule detection plays an important role in lung cancer diagnosis and early treatment. We propose a three-dimensional (3D) Convolutional Neural Networks (ConvNets) fusion model for lung nodule detection on clinical CT scans. Two 3D ConvNets models are trained separately without any pre-training weights: One trained on the LUng Nodule Analysis 2016 dataset (LUNA) and additional augmented data to learn the nodules' representative features in volumetric space, which may cause overfitting problems meanwhile, so we train another network on original data and fuse the results of the two best-performing models to reduce this risk. Both use reshaped objective function to solve the class imbalance problem and differentiate hard samples from easy samples. More importantly, 335 patients' CT scans from the hospital are further used to evaluate and help optimize the performance of our approach in the real situation, and we develop a system based on this method. Experimental results show a sensitivity of 95.1% at 8 false positives per scan in Free Receiver Operating Characteristics (FROC) curve analysis, and our system has a pleasing generalization ability in clinical data.

Original language	English
Title of host publication	Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018
Editors	Harald Schmidt, David Griol, Haiying Wang, Jan Baumbach, Huiru Zheng, Zoraida Callejas, Xiaohua Hu, Julie Dickerson, Le Zhang
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	973-978
Number of pages	6
ISBN (Electronic)	9781538654880
DOIs	https://doi.org/10.1109/BIBM.2018.8621468
State	Published - 21 Jan 2019
Event	2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018 - Madrid, Spain Duration: 3 Dec 2018 → 6 Dec 2018

Publication series

Name	Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018

Conference

Conference	2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018
Country/Territory	Spain
City	Madrid
Period	3/12/18 → 6/12/18

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

3D Convolutional Neural Networks
clinical data
model fusion
nodule detection

Access to Document

10.1109/BIBM.2018.8621468

Cite this

Cao, G., Huang, T., Hou, K., Cao, W., Liu, P., & Zhang, J. (2019). 3D Convolutional Neural Networks Fusion Model for Lung Nodule Detection onClinical CT Scans. In H. Schmidt, D. Griol, H. Wang, J. Baumbach, H. Zheng, Z. Callejas, X. Hu, J. Dickerson, & L. Zhang (Eds.), Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018 (pp. 973-978). Article 8621468 (Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIBM.2018.8621468

Cao, Guitao ; Huang, Tiantian ; Hou, Kai et al. / 3D Convolutional Neural Networks Fusion Model for Lung Nodule Detection onClinical CT Scans. Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018. editor / Harald Schmidt ; David Griol ; Haiying Wang ; Jan Baumbach ; Huiru Zheng ; Zoraida Callejas ; Xiaohua Hu ; Julie Dickerson ; Le Zhang. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 973-978 (Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018).

@inproceedings{a500c6de8e494f5eb4a778237980d637,

title = "3D Convolutional Neural Networks Fusion Model for Lung Nodule Detection onClinical CT Scans",

abstract = "Automatically accurate pulmonary nodule detection plays an important role in lung cancer diagnosis and early treatment. We propose a three-dimensional (3D) Convolutional Neural Networks (ConvNets) fusion model for lung nodule detection on clinical CT scans. Two 3D ConvNets models are trained separately without any pre-training weights: One trained on the LUng Nodule Analysis 2016 dataset (LUNA) and additional augmented data to learn the nodules' representative features in volumetric space, which may cause overfitting problems meanwhile, so we train another network on original data and fuse the results of the two best-performing models to reduce this risk. Both use reshaped objective function to solve the class imbalance problem and differentiate hard samples from easy samples. More importantly, 335 patients' CT scans from the hospital are further used to evaluate and help optimize the performance of our approach in the real situation, and we develop a system based on this method. Experimental results show a sensitivity of 95.1\% at 8 false positives per scan in Free Receiver Operating Characteristics (FROC) curve analysis, and our system has a pleasing generalization ability in clinical data.",

keywords = "3D Convolutional Neural Networks, clinical data, model fusion, nodule detection",

author = "Guitao Cao and Tiantian Huang and Kai Hou and Wenming Cao and Peng Liu and Jiawei Zhang",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018 ; Conference date: 03-12-2018 Through 06-12-2018",

year = "2019",

month = jan,

day = "21",

doi = "10.1109/BIBM.2018.8621468",

language = "英语",

series = "Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018",

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

pages = "973--978",

editor = "Harald Schmidt and David Griol and Haiying Wang and Jan Baumbach and Huiru Zheng and Zoraida Callejas and Xiaohua Hu and Julie Dickerson and Le Zhang",

booktitle = "Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018",

address = "美国",

}

Cao, G, Huang, T, Hou, K, Cao, W, Liu, P & Zhang, J 2019, 3D Convolutional Neural Networks Fusion Model for Lung Nodule Detection onClinical CT Scans. in H Schmidt, D Griol, H Wang, J Baumbach, H Zheng, Z Callejas, X Hu, J Dickerson & L Zhang (eds), Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018., 8621468, Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018, Institute of Electrical and Electronics Engineers Inc., pp. 973-978, 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018, Madrid, Spain, 3/12/18. https://doi.org/10.1109/BIBM.2018.8621468

3D Convolutional Neural Networks Fusion Model for Lung Nodule Detection onClinical CT Scans. / Cao, Guitao; Huang, Tiantian; Hou, Kai et al.
Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018. ed. / Harald Schmidt; David Griol; Haiying Wang; Jan Baumbach; Huiru Zheng; Zoraida Callejas; Xiaohua Hu; Julie Dickerson; Le Zhang. Institute of Electrical and Electronics Engineers Inc., 2019. p. 973-978 8621468 (Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018).

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

TY - GEN

T1 - 3D Convolutional Neural Networks Fusion Model for Lung Nodule Detection onClinical CT Scans

AU - Cao, Guitao

AU - Huang, Tiantian

AU - Hou, Kai

AU - Cao, Wenming

AU - Liu, Peng

AU - Zhang, Jiawei

PY - 2019/1/21

Y1 - 2019/1/21

N2 - Automatically accurate pulmonary nodule detection plays an important role in lung cancer diagnosis and early treatment. We propose a three-dimensional (3D) Convolutional Neural Networks (ConvNets) fusion model for lung nodule detection on clinical CT scans. Two 3D ConvNets models are trained separately without any pre-training weights: One trained on the LUng Nodule Analysis 2016 dataset (LUNA) and additional augmented data to learn the nodules' representative features in volumetric space, which may cause overfitting problems meanwhile, so we train another network on original data and fuse the results of the two best-performing models to reduce this risk. Both use reshaped objective function to solve the class imbalance problem and differentiate hard samples from easy samples. More importantly, 335 patients' CT scans from the hospital are further used to evaluate and help optimize the performance of our approach in the real situation, and we develop a system based on this method. Experimental results show a sensitivity of 95.1% at 8 false positives per scan in Free Receiver Operating Characteristics (FROC) curve analysis, and our system has a pleasing generalization ability in clinical data.

AB - Automatically accurate pulmonary nodule detection plays an important role in lung cancer diagnosis and early treatment. We propose a three-dimensional (3D) Convolutional Neural Networks (ConvNets) fusion model for lung nodule detection on clinical CT scans. Two 3D ConvNets models are trained separately without any pre-training weights: One trained on the LUng Nodule Analysis 2016 dataset (LUNA) and additional augmented data to learn the nodules' representative features in volumetric space, which may cause overfitting problems meanwhile, so we train another network on original data and fuse the results of the two best-performing models to reduce this risk. Both use reshaped objective function to solve the class imbalance problem and differentiate hard samples from easy samples. More importantly, 335 patients' CT scans from the hospital are further used to evaluate and help optimize the performance of our approach in the real situation, and we develop a system based on this method. Experimental results show a sensitivity of 95.1% at 8 false positives per scan in Free Receiver Operating Characteristics (FROC) curve analysis, and our system has a pleasing generalization ability in clinical data.

KW - 3D Convolutional Neural Networks

KW - clinical data

KW - model fusion

KW - nodule detection

UR - https://www.scopus.com/pages/publications/85062541577

U2 - 10.1109/BIBM.2018.8621468

DO - 10.1109/BIBM.2018.8621468

M3 - 会议稿件

AN - SCOPUS:85062541577

T3 - Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018

SP - 973

EP - 978

BT - Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018

A2 - Schmidt, Harald

A2 - Griol, David

A2 - Wang, Haiying

A2 - Baumbach, Jan

A2 - Zheng, Huiru

A2 - Callejas, Zoraida

A2 - Hu, Xiaohua

A2 - Dickerson, Julie

A2 - Zhang, Le

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018

Y2 - 3 December 2018 through 6 December 2018

ER -

Cao G, Huang T, Hou K, Cao W, Liu P, Zhang J. 3D Convolutional Neural Networks Fusion Model for Lung Nodule Detection onClinical CT Scans. In Schmidt H, Griol D, Wang H, Baumbach J, Zheng H, Callejas Z, Hu X, Dickerson J, Zhang L, editors, Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 973-978. 8621468. (Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018). doi: 10.1109/BIBM.2018.8621468

3D Convolutional Neural Networks Fusion Model for Lung Nodule Detection onClinical CT Scans

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this