Towards automatic pulmonary nodule management in lung cancer screening with deep learning

Francesco Ciompi, Kaman Chung, Sarah J. Van Riel, Arnaud Arindra Adiyoso Setio, Paul K. Gerke, Colin Jacobs, Ernst Th Scholten, Cornelia Schaefer-Prokop, Mathilde M.W. Wille, Alfonso Marchianò, Ugo Pastorino, Mathias Prokop, Bram Van Ginneken

Research output: Contribution to journalArticle

71 Citations (Scopus)

Abstract

The introduction of lung cancer screening programs will produce an unprecedented amount of chest CT scans in the near future, which radiologists will have to read in order to decide on a patient follow-up strategy. According to the current guidelines, the workup of screen-detected nodules strongly relies on nodule size and nodule type. In this paper, we present a deep learning system based on multi-stream multi-scale convolutional networks, which automatically classifies all nodule types relevant for nodule workup. The system processes raw CT data containing a nodule without the need for any additional information such as nodule segmentation or nodule size and learns a representation of 3D data by analyzing an arbitrary number of 2D views of a given nodule. The deep learning system was trained with data from the Italian MILD screening trial and validated on an independent set of data from the Danish DLCST screening trial. We analyze the advantage of processing nodules at multiple scales with a multi-stream convolutional network architecture, and we show that the proposed deep learning system achieves performance at classifying nodule type that surpasses the one of classical machine learning approaches and is within the inter-observer variability among four experienced human observers.

Original languageEnglish
Article number46479
JournalScientific Reports
Volume7
DOIs
Publication statusPublished - Apr 19 2017

Fingerprint

Learning systems
Screening
Computerized tomography
Network architecture
Deep learning
Processing

ASJC Scopus subject areas

  • General

Cite this

Ciompi, F., Chung, K., Van Riel, S. J., Setio, A. A. A., Gerke, P. K., Jacobs, C., ... Van Ginneken, B. (2017). Towards automatic pulmonary nodule management in lung cancer screening with deep learning. Scientific Reports, 7, [46479]. https://doi.org/10.1038/srep46479

Towards automatic pulmonary nodule management in lung cancer screening with deep learning. / Ciompi, Francesco; Chung, Kaman; Van Riel, Sarah J.; Setio, Arnaud Arindra Adiyoso; Gerke, Paul K.; Jacobs, Colin; Th Scholten, Ernst; Schaefer-Prokop, Cornelia; Wille, Mathilde M.W.; Marchianò, Alfonso; Pastorino, Ugo; Prokop, Mathias; Van Ginneken, Bram.

In: Scientific Reports, Vol. 7, 46479, 19.04.2017.

Research output: Contribution to journalArticle

Ciompi, F, Chung, K, Van Riel, SJ, Setio, AAA, Gerke, PK, Jacobs, C, Th Scholten, E, Schaefer-Prokop, C, Wille, MMW, Marchianò, A, Pastorino, U, Prokop, M & Van Ginneken, B 2017, 'Towards automatic pulmonary nodule management in lung cancer screening with deep learning', Scientific Reports, vol. 7, 46479. https://doi.org/10.1038/srep46479
Ciompi F, Chung K, Van Riel SJ, Setio AAA, Gerke PK, Jacobs C et al. Towards automatic pulmonary nodule management in lung cancer screening with deep learning. Scientific Reports. 2017 Apr 19;7. 46479. https://doi.org/10.1038/srep46479
Ciompi, Francesco ; Chung, Kaman ; Van Riel, Sarah J. ; Setio, Arnaud Arindra Adiyoso ; Gerke, Paul K. ; Jacobs, Colin ; Th Scholten, Ernst ; Schaefer-Prokop, Cornelia ; Wille, Mathilde M.W. ; Marchianò, Alfonso ; Pastorino, Ugo ; Prokop, Mathias ; Van Ginneken, Bram. / Towards automatic pulmonary nodule management in lung cancer screening with deep learning. In: Scientific Reports. 2017 ; Vol. 7.
@article{84965f1c8b734a6a983b526c30b3a080,
title = "Towards automatic pulmonary nodule management in lung cancer screening with deep learning",
abstract = "The introduction of lung cancer screening programs will produce an unprecedented amount of chest CT scans in the near future, which radiologists will have to read in order to decide on a patient follow-up strategy. According to the current guidelines, the workup of screen-detected nodules strongly relies on nodule size and nodule type. In this paper, we present a deep learning system based on multi-stream multi-scale convolutional networks, which automatically classifies all nodule types relevant for nodule workup. The system processes raw CT data containing a nodule without the need for any additional information such as nodule segmentation or nodule size and learns a representation of 3D data by analyzing an arbitrary number of 2D views of a given nodule. The deep learning system was trained with data from the Italian MILD screening trial and validated on an independent set of data from the Danish DLCST screening trial. We analyze the advantage of processing nodules at multiple scales with a multi-stream convolutional network architecture, and we show that the proposed deep learning system achieves performance at classifying nodule type that surpasses the one of classical machine learning approaches and is within the inter-observer variability among four experienced human observers.",
author = "Francesco Ciompi and Kaman Chung and {Van Riel}, {Sarah J.} and Setio, {Arnaud Arindra Adiyoso} and Gerke, {Paul K.} and Colin Jacobs and {Th Scholten}, Ernst and Cornelia Schaefer-Prokop and Wille, {Mathilde M.W.} and Alfonso Marchian{\`o} and Ugo Pastorino and Mathias Prokop and {Van Ginneken}, Bram",
year = "2017",
month = "4",
day = "19",
doi = "10.1038/srep46479",
language = "English",
volume = "7",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",

}

TY - JOUR

T1 - Towards automatic pulmonary nodule management in lung cancer screening with deep learning

AU - Ciompi, Francesco

AU - Chung, Kaman

AU - Van Riel, Sarah J.

AU - Setio, Arnaud Arindra Adiyoso

AU - Gerke, Paul K.

AU - Jacobs, Colin

AU - Th Scholten, Ernst

AU - Schaefer-Prokop, Cornelia

AU - Wille, Mathilde M.W.

AU - Marchianò, Alfonso

AU - Pastorino, Ugo

AU - Prokop, Mathias

AU - Van Ginneken, Bram

PY - 2017/4/19

Y1 - 2017/4/19

N2 - The introduction of lung cancer screening programs will produce an unprecedented amount of chest CT scans in the near future, which radiologists will have to read in order to decide on a patient follow-up strategy. According to the current guidelines, the workup of screen-detected nodules strongly relies on nodule size and nodule type. In this paper, we present a deep learning system based on multi-stream multi-scale convolutional networks, which automatically classifies all nodule types relevant for nodule workup. The system processes raw CT data containing a nodule without the need for any additional information such as nodule segmentation or nodule size and learns a representation of 3D data by analyzing an arbitrary number of 2D views of a given nodule. The deep learning system was trained with data from the Italian MILD screening trial and validated on an independent set of data from the Danish DLCST screening trial. We analyze the advantage of processing nodules at multiple scales with a multi-stream convolutional network architecture, and we show that the proposed deep learning system achieves performance at classifying nodule type that surpasses the one of classical machine learning approaches and is within the inter-observer variability among four experienced human observers.

AB - The introduction of lung cancer screening programs will produce an unprecedented amount of chest CT scans in the near future, which radiologists will have to read in order to decide on a patient follow-up strategy. According to the current guidelines, the workup of screen-detected nodules strongly relies on nodule size and nodule type. In this paper, we present a deep learning system based on multi-stream multi-scale convolutional networks, which automatically classifies all nodule types relevant for nodule workup. The system processes raw CT data containing a nodule without the need for any additional information such as nodule segmentation or nodule size and learns a representation of 3D data by analyzing an arbitrary number of 2D views of a given nodule. The deep learning system was trained with data from the Italian MILD screening trial and validated on an independent set of data from the Danish DLCST screening trial. We analyze the advantage of processing nodules at multiple scales with a multi-stream convolutional network architecture, and we show that the proposed deep learning system achieves performance at classifying nodule type that surpasses the one of classical machine learning approaches and is within the inter-observer variability among four experienced human observers.

UR - http://www.scopus.com/inward/record.url?scp=85017644487&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017644487&partnerID=8YFLogxK

U2 - 10.1038/srep46479

DO - 10.1038/srep46479

M3 - Article

AN - SCOPUS:85017644487

VL - 7

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

M1 - 46479

ER -