Auto Segmentation of Lung in Non-small Cell Lung Cancer Using Deep Convolution Neural Network

Ravindra Patil; Leonard Wee; Andre Dekker

doi:10.1007/978-981-15-6634-9_31

Auto Segmentation of Lung in Non-small Cell Lung Cancer Using Deep Convolution Neural Network

Ravindra Patil^*, Leonard Wee, Andre Dekker

^*Corresponding author for this work

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

12 Downloads (Pure)

Abstract

Segmentation of Lung is the vital first step in radiologic diagnosis of lung cancer. In this work, we present a deep learning based automated technique that overcomes various shortcomings of traditional lung segmentation and explores the role of adding “explainability” to deep learning models so that the trust can be built on these models. Our approach shows better generalization across different scanner settings, vendors and the slice thickness. In addition, there is no initialization of the seed point making it complete automated without manual intervention. The dice score of 0.98 is achieved for lung segmentation on an independent data set of non-small cell lung cancer.

Original language	English
Title of host publication	Advances in Computing and Data Sciences - 4th International Conference, ICACDS 2020, Revised Selected Papers
Editors	Mayank Singh, Gupta, Vipin Tyagi, Jan Flusser, Tuncer Ören, Gianluca Valentino
Publisher	Springer
Pages	340-351
Number of pages	12
Volume	1244 CCIS
ISBN (Print)	9789811566332
DOIs	https://doi.org/10.1007/978-981-15-6634-9_31
Publication status	Published - 1 Jan 2020
Event	4th International Conference on Advances in Computing and Data Sciences - Msida, Malta Duration: 24 Apr 2020 → 25 Apr 2020 Conference number: 4

Publication series

Series	Communications in Computer and Information Science
Volume	1244 CCIS
ISSN	1865-0929

Conference

Conference	4th International Conference on Advances in Computing and Data Sciences
Abbreviated title	ICACDS 2020
Country/Territory	Malta
City	Msida
Period	24/04/20 → 25/04/20

Keywords

Deep learning
Lung segmentation
NSCLC

Access to Document

10.1007/978-981-15-6634-9_31

Full TextFinal published version, 2.47 MBLicence: Taverne

Cite this

Patil, R., Wee, L., & Dekker, A. (2020). Auto Segmentation of Lung in Non-small Cell Lung Cancer Using Deep Convolution Neural Network. In M. Singh, Gupta, V. Tyagi, J. Flusser, T. Ören, & G. Valentino (Eds.), Advances in Computing and Data Sciences - 4th International Conference, ICACDS 2020, Revised Selected Papers (Vol. 1244 CCIS, pp. 340-351). Springer. https://doi.org/10.1007/978-981-15-6634-9_31

Patil, Ravindra ; Wee, Leonard ; Dekker, Andre. / Auto Segmentation of Lung in Non-small Cell Lung Cancer Using Deep Convolution Neural Network. Advances in Computing and Data Sciences - 4th International Conference, ICACDS 2020, Revised Selected Papers. editor / Mayank Singh ; Gupta ; Vipin Tyagi ; Jan Flusser ; Tuncer Ören ; Gianluca Valentino. Vol. 1244 CCIS Springer, 2020. pp. 340-351 (Communications in Computer and Information Science, Vol. 1244 CCIS).

@inproceedings{620084dc50a641b6a27a88edd58a1d59,

title = "Auto Segmentation of Lung in Non-small Cell Lung Cancer Using Deep Convolution Neural Network",

abstract = "Segmentation of Lung is the vital first step in radiologic diagnosis of lung cancer. In this work, we present a deep learning based automated technique that overcomes various shortcomings of traditional lung segmentation and explores the role of adding “explainability” to deep learning models so that the trust can be built on these models. Our approach shows better generalization across different scanner settings, vendors and the slice thickness. In addition, there is no initialization of the seed point making it complete automated without manual intervention. The dice score of 0.98 is achieved for lung segmentation on an independent data set of non-small cell lung cancer.",

keywords = "Deep learning, Lung segmentation, NSCLC",

author = "Ravindra Patil and Leonard Wee and Andre Dekker",

note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Singapore Pte Ltd.; 4th International Conference on Advances in Computing and Data Sciences, ICACDS 2020 ; Conference date: 24-04-2020 Through 25-04-2020",

year = "2020",

month = jan,

day = "1",

doi = "10.1007/978-981-15-6634-9_31",

language = "English",

isbn = "9789811566332",

volume = "1244 CCIS",

series = "Communications in Computer and Information Science",

publisher = "Springer",

pages = "340--351",

editor = "Mayank Singh and Gupta and Vipin Tyagi and Jan Flusser and Tuncer {\"O}ren and Gianluca Valentino",

booktitle = "Advances in Computing and Data Sciences - 4th International Conference, ICACDS 2020, Revised Selected Papers",

address = "United States",

}

Patil, R , Wee, L & Dekker, A 2020, Auto Segmentation of Lung in Non-small Cell Lung Cancer Using Deep Convolution Neural Network. in M Singh, Gupta, V Tyagi, J Flusser, T Ören & G Valentino (eds), Advances in Computing and Data Sciences - 4th International Conference, ICACDS 2020, Revised Selected Papers. vol. 1244 CCIS, Springer, Communications in Computer and Information Science, vol. 1244 CCIS, pp. 340-351, 4th International Conference on Advances in Computing and Data Sciences, Msida, Malta, 24/04/20. https://doi.org/10.1007/978-981-15-6634-9_31

Auto Segmentation of Lung in Non-small Cell Lung Cancer Using Deep Convolution Neural Network. / Patil, Ravindra ; Wee, Leonard ; Dekker, Andre.
Advances in Computing and Data Sciences - 4th International Conference, ICACDS 2020, Revised Selected Papers. ed. / Mayank Singh; Gupta; Vipin Tyagi; Jan Flusser; Tuncer Ören; Gianluca Valentino. Vol. 1244 CCIS Springer, 2020. p. 340-351 (Communications in Computer and Information Science, Vol. 1244 CCIS).

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

TY - GEN

T1 - Auto Segmentation of Lung in Non-small Cell Lung Cancer Using Deep Convolution Neural Network

AU - Patil, Ravindra

AU - Wee, Leonard

AU - Dekker, Andre

N1 - Conference code: 4

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Segmentation of Lung is the vital first step in radiologic diagnosis of lung cancer. In this work, we present a deep learning based automated technique that overcomes various shortcomings of traditional lung segmentation and explores the role of adding “explainability” to deep learning models so that the trust can be built on these models. Our approach shows better generalization across different scanner settings, vendors and the slice thickness. In addition, there is no initialization of the seed point making it complete automated without manual intervention. The dice score of 0.98 is achieved for lung segmentation on an independent data set of non-small cell lung cancer.

AB - Segmentation of Lung is the vital first step in radiologic diagnosis of lung cancer. In this work, we present a deep learning based automated technique that overcomes various shortcomings of traditional lung segmentation and explores the role of adding “explainability” to deep learning models so that the trust can be built on these models. Our approach shows better generalization across different scanner settings, vendors and the slice thickness. In addition, there is no initialization of the seed point making it complete automated without manual intervention. The dice score of 0.98 is achieved for lung segmentation on an independent data set of non-small cell lung cancer.

KW - Deep learning

KW - Lung segmentation

KW - NSCLC

U2 - 10.1007/978-981-15-6634-9_31

DO - 10.1007/978-981-15-6634-9_31

M3 - Conference article in proceeding

SN - 9789811566332

VL - 1244 CCIS

T3 - Communications in Computer and Information Science

SP - 340

EP - 351

BT - Advances in Computing and Data Sciences - 4th International Conference, ICACDS 2020, Revised Selected Papers

A2 - Singh, Mayank

A2 - Gupta, null

A2 - Tyagi, Vipin

A2 - Flusser, Jan

A2 - Ören, Tuncer

A2 - Valentino, Gianluca

PB - Springer

T2 - 4th International Conference on Advances in Computing and Data Sciences

Y2 - 24 April 2020 through 25 April 2020

ER -

Patil R , Wee L , Dekker A. Auto Segmentation of Lung in Non-small Cell Lung Cancer Using Deep Convolution Neural Network. In Singh M, Gupta, Tyagi V, Flusser J, Ören T, Valentino G, editors, Advances in Computing and Data Sciences - 4th International Conference, ICACDS 2020, Revised Selected Papers. Vol. 1244 CCIS. Springer. 2020. p. 340-351. (Communications in Computer and Information Science, Vol. 1244 CCIS). doi: 10.1007/978-981-15-6634-9_31