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
N1 - M1 - e0205397
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.
KW - Humans
KW - Image Interpretation, Computer-Assisted/methods
KW - Lung/diagnostic imaging
KW - Normal Distribution
KW - Pulmonary Emphysema/diagnosis
KW - Respiratory Function Tests
KW - Tomography, X-Ray Computed
KW - Humans
KW - Image Interpretation, Computer-Assisted/methods
KW - Lung/diagnostic imaging
KW - Normal Distribution
KW - Pulmonary Emphysema/diagnosis
KW - Respiratory Function Tests
KW - Tomography, X-Ray Computed
U2 - 10.1371/journal.pone.0205397
DO - 10.1371/journal.pone.0205397
M3 - Journal article
SN - 1932-6203
VL - 13
JO - PLOS ONE
JF - PLOS ONE
IS - 10
ER -