Automatic emphysema detection using weakly labeled HRCT lung images

Isabel Pino Pena, Veronika Cheplygina, Sofia Paschaloudi, Morten Vuust, Jesper Carl, Ulla Moller Weinreich, Lasse Riis Ostergaard, Marleen de Bruijne

Research output: Contribution to journalArticleAcademicpeer-review

23 Downloads (Pure)

Abstract

Purpose A method for automatically quantifying emphysema regions using High-Resolution Computed Tomography (HRCT) scans of patients with chronic obstructive pulmonary disease (COPD) that does not require manually annotated scans for training is presented. Methods HRCT scans of controls and of COPD patients with diverse disease severity are acquired at two different centers. Textural features from co-occurrence matrices and Gaussian filter banks are used to characterize the lung parenchyma in the scans. Two robust versions of multiple instance learning (MIL) classifiers that can handle weakly labeled data, miSVM and MILES, are investigated. Weak labels give information relative to the emphysema without indicating the location of the lesions. The classifiers are trained with the weak labels extracted from the forced expiratory volume in one minute (FEV1) and diffusing capacity of the lungs for carbon monoxide (DLCO). At test time, the classifiers output a patient label indicating overall COPD diagnosis and local labels indicating the presence of emphysema. The classifier performance is compared with manual annotations made by two radiologists, a classical density based method, and pulmonary function tests (PFTs). Results The miSVM classifier performed better than MILES on both patient and emphysema classification. The classifier has a stronger correlation with PFT than the density based method, the percentage of emphysema in the intersection of annotations from both radiologists, and the percentage of emphysema annotated by one of the radiologists. The correlation between the classifier and the PFT is only outperformed by the second radiologist. Conclusions The presented method uses MIL classifiers to automatically identify emphysema regions in HRCT scans. Furthermore, this approach has been demonstrated to correlate better with DLCO than a classical density based method or a radiologist, which is known to be affected in emphysema. Therefore, it is relevant to facilitate assessment of emphysema and to reduce inter-observer variability.

Original languageEnglish
Article numbere0205397
Number of pages17
JournalPLoS ONE
Volume13
Issue number10
DOIs
Publication statusPublished - 15 Oct 2018

Cite this

Pena, I. P., Cheplygina, V., Paschaloudi, S., Vuust, M., Carl, J., Weinreich, U. M., ... de Bruijne, M. (2018). Automatic emphysema detection using weakly labeled HRCT lung images. PLoS ONE, 13(10), [e0205397]. https://doi.org/10.1371/journal.pone.0205397
Pena, Isabel Pino ; Cheplygina, Veronika ; Paschaloudi, Sofia ; Vuust, Morten ; Carl, Jesper ; Weinreich, Ulla Moller ; Ostergaard, Lasse Riis ; de Bruijne, Marleen. / Automatic emphysema detection using weakly labeled HRCT lung images. In: PLoS ONE. 2018 ; Vol. 13, No. 10.
@article{2937c7b464534bf4bc7c96905f90d468,
title = "Automatic emphysema detection using weakly labeled HRCT lung images",
abstract = "Purpose A method for automatically quantifying emphysema regions using High-Resolution Computed Tomography (HRCT) scans of patients with chronic obstructive pulmonary disease (COPD) that does not require manually annotated scans for training is presented. Methods HRCT scans of controls and of COPD patients with diverse disease severity are acquired at two different centers. Textural features from co-occurrence matrices and Gaussian filter banks are used to characterize the lung parenchyma in the scans. Two robust versions of multiple instance learning (MIL) classifiers that can handle weakly labeled data, miSVM and MILES, are investigated. Weak labels give information relative to the emphysema without indicating the location of the lesions. The classifiers are trained with the weak labels extracted from the forced expiratory volume in one minute (FEV1) and diffusing capacity of the lungs for carbon monoxide (DLCO). At test time, the classifiers output a patient label indicating overall COPD diagnosis and local labels indicating the presence of emphysema. The classifier performance is compared with manual annotations made by two radiologists, a classical density based method, and pulmonary function tests (PFTs). Results The miSVM classifier performed better than MILES on both patient and emphysema classification. The classifier has a stronger correlation with PFT than the density based method, the percentage of emphysema in the intersection of annotations from both radiologists, and the percentage of emphysema annotated by one of the radiologists. The correlation between the classifier and the PFT is only outperformed by the second radiologist. Conclusions The presented method uses MIL classifiers to automatically identify emphysema regions in HRCT scans. Furthermore, this approach has been demonstrated to correlate better with DLCO than a classical density based method or a radiologist, which is known to be affected in emphysema. Therefore, it is relevant to facilitate assessment of emphysema and to reduce inter-observer variability.",
author = "Pena, {Isabel Pino} and Veronika Cheplygina and Sofia Paschaloudi and Morten Vuust and Jesper Carl and Weinreich, {Ulla Moller} and Ostergaard, {Lasse Riis} and {de Bruijne}, Marleen",
year = "2018",
month = "10",
day = "15",
doi = "10.1371/journal.pone.0205397",
language = "English",
volume = "13",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "10",

}

Pena, IP, Cheplygina, V, Paschaloudi, S, Vuust, M, Carl, J, Weinreich, UM, Ostergaard, LR & de Bruijne, M 2018, 'Automatic emphysema detection using weakly labeled HRCT lung images', PLoS ONE, vol. 13, no. 10, e0205397. https://doi.org/10.1371/journal.pone.0205397

Automatic emphysema detection using weakly labeled HRCT lung images. / Pena, Isabel Pino; Cheplygina, Veronika; Paschaloudi, Sofia; Vuust, Morten; Carl, Jesper; Weinreich, Ulla Moller; Ostergaard, Lasse Riis; de Bruijne, Marleen.

In: PLoS ONE, Vol. 13, No. 10, e0205397, 15.10.2018.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Automatic emphysema detection using weakly labeled HRCT lung images

AU - Pena, Isabel Pino

AU - Cheplygina, Veronika

AU - Paschaloudi, Sofia

AU - Vuust, Morten

AU - Carl, Jesper

AU - Weinreich, Ulla Moller

AU - Ostergaard, Lasse Riis

AU - de Bruijne, Marleen

PY - 2018/10/15

Y1 - 2018/10/15

N2 - Purpose A method for automatically quantifying emphysema regions using High-Resolution Computed Tomography (HRCT) scans of patients with chronic obstructive pulmonary disease (COPD) that does not require manually annotated scans for training is presented. Methods HRCT scans of controls and of COPD patients with diverse disease severity are acquired at two different centers. Textural features from co-occurrence matrices and Gaussian filter banks are used to characterize the lung parenchyma in the scans. Two robust versions of multiple instance learning (MIL) classifiers that can handle weakly labeled data, miSVM and MILES, are investigated. Weak labels give information relative to the emphysema without indicating the location of the lesions. The classifiers are trained with the weak labels extracted from the forced expiratory volume in one minute (FEV1) and diffusing capacity of the lungs for carbon monoxide (DLCO). At test time, the classifiers output a patient label indicating overall COPD diagnosis and local labels indicating the presence of emphysema. The classifier performance is compared with manual annotations made by two radiologists, a classical density based method, and pulmonary function tests (PFTs). Results The miSVM classifier performed better than MILES on both patient and emphysema classification. The classifier has a stronger correlation with PFT than the density based method, the percentage of emphysema in the intersection of annotations from both radiologists, and the percentage of emphysema annotated by one of the radiologists. The correlation between the classifier and the PFT is only outperformed by the second radiologist. Conclusions The presented method uses MIL classifiers to automatically identify emphysema regions in HRCT scans. Furthermore, this approach has been demonstrated to correlate better with DLCO than a classical density based method or a radiologist, which is known to be affected in emphysema. Therefore, it is relevant to facilitate assessment of emphysema and to reduce inter-observer variability.

AB - Purpose A method for automatically quantifying emphysema regions using High-Resolution Computed Tomography (HRCT) scans of patients with chronic obstructive pulmonary disease (COPD) that does not require manually annotated scans for training is presented. Methods HRCT scans of controls and of COPD patients with diverse disease severity are acquired at two different centers. Textural features from co-occurrence matrices and Gaussian filter banks are used to characterize the lung parenchyma in the scans. Two robust versions of multiple instance learning (MIL) classifiers that can handle weakly labeled data, miSVM and MILES, are investigated. Weak labels give information relative to the emphysema without indicating the location of the lesions. The classifiers are trained with the weak labels extracted from the forced expiratory volume in one minute (FEV1) and diffusing capacity of the lungs for carbon monoxide (DLCO). At test time, the classifiers output a patient label indicating overall COPD diagnosis and local labels indicating the presence of emphysema. The classifier performance is compared with manual annotations made by two radiologists, a classical density based method, and pulmonary function tests (PFTs). Results The miSVM classifier performed better than MILES on both patient and emphysema classification. The classifier has a stronger correlation with PFT than the density based method, the percentage of emphysema in the intersection of annotations from both radiologists, and the percentage of emphysema annotated by one of the radiologists. The correlation between the classifier and the PFT is only outperformed by the second radiologist. Conclusions The presented method uses MIL classifiers to automatically identify emphysema regions in HRCT scans. Furthermore, this approach has been demonstrated to correlate better with DLCO than a classical density based method or a radiologist, which is known to be affected in emphysema. Therefore, it is relevant to facilitate assessment of emphysema and to reduce inter-observer variability.

UR - http://www.scopus.com/inward/record.url?scp=85055074550&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0205397

DO - 10.1371/journal.pone.0205397

M3 - Article

C2 - 30321206

VL - 13

JO - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

IS - 10

M1 - e0205397

ER -

Pena IP, Cheplygina V, Paschaloudi S, Vuust M, Carl J, Weinreich UM et al. Automatic emphysema detection using weakly labeled HRCT lung images. PLoS ONE. 2018 Oct 15;13(10). e0205397. https://doi.org/10.1371/journal.pone.0205397