Transfer learning for multi-center classification of chronic obstructive pulmonary disease

Chronic obstructive pulmonary disease (COPD) is a lung disease which can be quantified using chest computed tomography (CT) scans. Recent studies have shown that COPD can be automatically diagnosed using weakly supervised learning of intensity and texture distributions. However, up till now such classifiers have only been evaluated on scans from a single domain, and it is unclear whether they would generalize across domains, such as different scanners or scanning protocols. To address this problem, we investigate classification of COPD in a multi-center dataset with a total of 803 scans from three different centers, four different scanners, with heterogenous subject distributions. Our method is based on Gaussian texture features, and a weighted logistic classifier, which increases the weights of samples similar to the test data. We show that Gaussian texture features outperform intensity features previously used in multi-center classification tasks. We also show that a weighting strategy based on a classifier that is trained to discriminate between scans from different domains, can further improve the results. To encourage further research into transfer learning methods for classification of COPD, upon acceptance of the paper we will release two feature datasets used in this study on http://bigr.nl/research/projects/copd.

[1]  E. DeLong,et al.  Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. , 1988, Biometrics.

[2]  Matti Pietikäinen,et al.  A comparative study of texture measures with classification based on featured distributions , 1996, Pattern Recognit..

[3]  Thomas G. Dietterich,et al.  Solving the Multiple Instance Problem with Axis-Parallel Rectangles , 1997, Artif. Intell..

[4]  H. Shimodaira,et al.  Improving predictive inference under covariate shift by weighting the log-likelihood function , 2000 .

[5]  R. Pauwels,et al.  Global strategy for the diagnosis, management, and prevention of chronic obstructive pulmonary disease: National Heart, Lung, and Blood Institute and World Health Organization Global Initiative for Chronic Obstructive Lung Disease (GOLD): executive summary. , 2001, Respiratory care.

[6]  Bram van Ginneken,et al.  Static posterior probability fusion for signal detection: applications in the detection of interstitial diseases in chest radiographs , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[7]  Janez Demsar,et al.  Statistical Comparisons of Classifiers over Multiple Data Sets , 2006, J. Mach. Learn. Res..

[8]  Bernhard Schölkopf,et al.  Correcting Sample Selection Bias by Unlabeled Data , 2006, NIPS.

[9]  J. Seo,et al.  Texture-Based Quantification of Pulmonary Emphysema on High-Resolution Computed Tomography: Comparison With Density-Based Quantification and Correlation With Pulmonary Function Test , 2008, Investigative radiology.

[10]  A. Dirksen,et al.  The Danish Randomized Lung Cancer CT Screening Trial—Overall Design and Results of the Prevalence Round , 2009, Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer.

[11]  Karsten M. Borgwardt,et al.  Covariate Shift by Kernel Mean Matching , 2009, NIPS 2009.

[12]  Marleen de Bruijne,et al.  Vessel-guided airway tree segmentation: A voxel classification approach , 2010, Medical Image Anal..

[13]  E. Regan,et al.  Genetic Epidemiology of COPD (COPDGene) Study Design , 2011, COPD.

[14]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[15]  Lauge Sørensen,et al.  Quantitative Analysis of Pulmonary Emphysema Using Local Binary Patterns , 2010, IEEE Transactions on Medical Imaging.

[16]  Gwénolé Quellec,et al.  A multiple-instance learning framework for diabetic retinopathy screening , 2012, Medical Image Anal..

[17]  Raúl San José Estépar,et al.  Emphysema quantification in a multi-scanner HRCT cohort using local intensity distributions , 2012, 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI).

[18]  Jorge Luís Machado do Amaral,et al.  Machine learning algorithms and forced oscillation measurements applied to the automatic identification of chronic obstructive pulmonary disease , 2012, Comput. Methods Programs Biomed..

[19]  Reyer Zwiggelaar,et al.  Machine learning methods on exhaled volatile organic compounds for distinguishing COPD patients from healthy controls , 2012, Journal of breath research.

[20]  Pascal Fua,et al.  Transfer Learning by Sharing Support Vectors , 2012 .

[21]  Lauge Sørensen,et al.  Texture-Based Analysis of COPD: A Data-Driven Approach , 2012, IEEE Transactions on Medical Imaging.

[22]  F. Martinez,et al.  Global strategy for the diagnosis, management, and prevention of chronic obstructive pulmonary disease: GOLD executive summary. , 2007, American journal of respiratory and critical care medicine.

[23]  Mario Castro,et al.  Improved CT-based estimate of pulmonary gas trapping accounting for scanner and lung-volume variations in a multicenter asthmatic study. , 2014, Journal of applied physiology.

[24]  Georg Langs,et al.  Unsupervised Pre-training Across Image Domains Improves Lung Tissue Classification , 2014, MCV.

[25]  Daniel Rueckert,et al.  Manifold Alignment and Transfer Learning for Classification of Alzheimer's Disease , 2014, MLMI.

[26]  Lauge Sørensen,et al.  Classification of COPD with Multiple Instance Learning , 2014, 2014 22nd International Conference on Pattern Recognition.

[27]  Philip F. Judy,et al.  Normalizing computed tomography data reconstructed with different filter kernels: effect on emphysema quantification , 2015, European Radiology.

[28]  Marleen de Bruijne,et al.  Weighting training images by maximizing distribution similarity for supervised segmentation across scanners , 2015, Medical Image Anal..

[29]  Pascal Fua,et al.  Domain Adaptation for Microscopy Imaging , 2015, IEEE Transactions on Medical Imaging.

[30]  Jesper Carl,et al.  The use of atlas registration and graph cuts for prostate segmentation in magnetic resonance images. , 2015, Medical physics.

[31]  Daoqiang Zhang,et al.  Multimodal manifold-regularized transfer learning for MCI conversion prediction , 2015, Brain Imaging and Behavior.

[32]  Marleen de Bruijne,et al.  Transfer Learning Improves Supervised Image Segmentation Across Imaging Protocols , 2015, IEEE Trans. Medical Imaging.

[33]  Klaus H. Maier-Hein,et al.  DALSA: Domain Adaptation for Supervised Learning From Sparsely Annotated MR Images , 2024, IEEE Transactions on Medical Imaging.

[34]  Ronald M. Summers,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, IEEE Transactions on Medical Imaging.

[35]  Marleen de Bruijne,et al.  Asymmetric similarity-weighted ensembles for image segmentation , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[36]  Laurens van der Maaten,et al.  Feature-Level Domain Adaptation , 2015, J. Mach. Learn. Res..