Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Assessing the accuracy of a deep learning method to risk stratify indeterminate pulmonary nodules

Massion, Pierre P. ; Antic, Sanja ; Ather, Sarim ; Arteta, Carlos ; Brabec, Jan LU ; Chen, Heidi ; Declerck, Jerome ; Dufek, David ; Hickes, William and Kadir, Timor , et al. (2020) In American Journal of Respiratory and Critical Care Medicine 202(2). p.241-249
Abstract

Rationale: The management of indeterminate pulmonary nodules (IPNs) remains challenging, resulting in invasive procedures and delays in diagnosis and treatment. Strategies to decrease the rate of unnecessary invasive procedures and optimize surveillance regimens are needed. Objectives: To develop and validate a deep learning method to improve the management of IPNs. Methods:ALung Cancer Prediction Convolutional Neural Network model was trained using computed tomography images of IPNs from the National Lung Screening Trial, internally validated, and externally tested on cohorts from two academic institutions. Measurements and Main Results: The areas under the receiver operating characteristic curve in the external validation cohorts were... (More)

Rationale: The management of indeterminate pulmonary nodules (IPNs) remains challenging, resulting in invasive procedures and delays in diagnosis and treatment. Strategies to decrease the rate of unnecessary invasive procedures and optimize surveillance regimens are needed. Objectives: To develop and validate a deep learning method to improve the management of IPNs. Methods:ALung Cancer Prediction Convolutional Neural Network model was trained using computed tomography images of IPNs from the National Lung Screening Trial, internally validated, and externally tested on cohorts from two academic institutions. Measurements and Main Results: The areas under the receiver operating characteristic curve in the external validation cohorts were 83.5% (95% confidence interval [CI], 75.4 90.7%) and 91.9% (95% CI, 88.7 94.7%), compared with 78.1% (95% CI, 68.7 86.4%) and 81.9 (95% CI, 76.1 87.1%), respectively, for a commonly used clinical risk model for incidental nodules. Using 5% and 65% malignancy thresholds defining low- and high-risk categories, the overall net reclassifications in the validation cohorts for cancers and benign nodules compared with the Mayo model were 0.34 (Vanderbilt) and 0.30 (Oxford) as a rule-in test, and 0.33 (Vanderbilt) and 0.58 (Oxford) as a rule-out test. Compared with traditional risk prediction models, the Lung Cancer Prediction Convolutional Neural Network was associated with improved accuracy in predicting the likelihood of disease at each threshold of management and in our external validation cohorts. Conclusions: This study demonstrates that this deep learning algorithm can correctly reclassify IPNs into low- or high-risk categories in more than a third of cancers and benign nodules when compared with conventional risk models, potentially reducing the number of unnecessary invasive procedures and delays in diagnosis.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; and (Less)
publishing date
type
Contribution to journal
publication status
published
keywords
Computer-aided image analysis, Early detection, Lung cancer, Neural networks, Risk stratification
in
American Journal of Respiratory and Critical Care Medicine
volume
202
issue
2
pages
241 - 249
publisher
American Thoracic Society
external identifiers
  • scopus:85088177199
  • pmid:32326730
ISSN
1073-449X
DOI
10.1164/rccm.201903-0505OC
language
English
LU publication?
no
additional info
Publisher Copyright: ©2020 by the American Thoracic Society.
id
c320bbeb-9066-4f99-a7f0-48bb7542a039
date added to LUP
2022-06-02 18:22:42
date last changed
2024-04-18 12:18:17
@article{c320bbeb-9066-4f99-a7f0-48bb7542a039,
  abstract     = {{<p>Rationale: The management of indeterminate pulmonary nodules (IPNs) remains challenging, resulting in invasive procedures and delays in diagnosis and treatment. Strategies to decrease the rate of unnecessary invasive procedures and optimize surveillance regimens are needed. Objectives: To develop and validate a deep learning method to improve the management of IPNs. Methods:ALung Cancer Prediction Convolutional Neural Network model was trained using computed tomography images of IPNs from the National Lung Screening Trial, internally validated, and externally tested on cohorts from two academic institutions. Measurements and Main Results: The areas under the receiver operating characteristic curve in the external validation cohorts were 83.5% (95% confidence interval [CI], 75.4 90.7%) and 91.9% (95% CI, 88.7 94.7%), compared with 78.1% (95% CI, 68.7 86.4%) and 81.9 (95% CI, 76.1 87.1%), respectively, for a commonly used clinical risk model for incidental nodules. Using 5% and 65% malignancy thresholds defining low- and high-risk categories, the overall net reclassifications in the validation cohorts for cancers and benign nodules compared with the Mayo model were 0.34 (Vanderbilt) and 0.30 (Oxford) as a rule-in test, and 0.33 (Vanderbilt) and 0.58 (Oxford) as a rule-out test. Compared with traditional risk prediction models, the Lung Cancer Prediction Convolutional Neural Network was associated with improved accuracy in predicting the likelihood of disease at each threshold of management and in our external validation cohorts. Conclusions: This study demonstrates that this deep learning algorithm can correctly reclassify IPNs into low- or high-risk categories in more than a third of cancers and benign nodules when compared with conventional risk models, potentially reducing the number of unnecessary invasive procedures and delays in diagnosis.</p>}},
  author       = {{Massion, Pierre P. and Antic, Sanja and Ather, Sarim and Arteta, Carlos and Brabec, Jan and Chen, Heidi and Declerck, Jerome and Dufek, David and Hickes, William and Kadir, Timor and Kunst, Jonas and Landman, Bennett A. and Munden, Reginald F. and Novotny, Petr and Peschl, Heiko and Pickup, Lyndsey C. and Santos, Catarina and Smith, Gary T. and Talwar, Ambika and Gleeson, Fergus}},
  issn         = {{1073-449X}},
  keywords     = {{Computer-aided image analysis; Early detection; Lung cancer; Neural networks; Risk stratification}},
  language     = {{eng}},
  number       = {{2}},
  pages        = {{241--249}},
  publisher    = {{American Thoracic Society}},
  series       = {{American Journal of Respiratory and Critical Care Medicine}},
  title        = {{Assessing the accuracy of a deep learning method to risk stratify indeterminate pulmonary nodules}},
  url          = {{http://dx.doi.org/10.1164/rccm.201903-0505OC}},
  doi          = {{10.1164/rccm.201903-0505OC}},
  volume       = {{202}},
  year         = {{2020}},
}