Comparison of Shallow and Deep Learning Methods on Classifying the Regional Pattern of Diffuse Lung Disease

This study aimed to compare shallow and deep learning of classifying the patterns of interstitial lung diseases (ILDs). Using high-resolution computed tomography images, two experienced radiologists marked 1200 regions of interest (ROIs), in which 600 ROIs were each acquired using a GE or Siemens scanner and each group of 600 ROIs consisted of 100 ROIs for subregions that included normal and five regional pulmonary disease patterns (ground-glass opacity, consolidation, reticular opacity, emphysema, and honeycombing). We employed the convolution neural network (CNN) with six learnable layers that consisted of four convolution layers and two fully connected layers. The classification results were compared with the results classified by a shallow learning of a support vector machine (SVM). The CNN classifier showed significantly better performance for accuracy compared with that of the SVM classifier by 6–9%. As the convolution layer increases, the classification accuracy of the CNN showed better performance from 81.27 to 95.12%. Especially in the cases showing pathological ambiguity such as between normal and emphysema cases or between honeycombing and reticular opacity cases, the increment of the convolution layer greatly drops the misclassification rate between each case. Conclusively, the CNN classifier showed significantly greater accuracy than the SVM classifier, and the results implied structural characteristics that are inherent to the specific ILD patterns.

[1]  Daniel Rueckert,et al.  Multi-atlas segmentation with augmented features for cardiac MR images , 2015, Medical Image Anal..

[2]  Ye Xu,et al.  MDCT-based 3-D texture classification of emphysema and early smoking related lung pathologies , 2006, IEEE Transactions on Medical Imaging.

[3]  Tatsuya Fujisaki,et al.  Effects of density changes in the chest on lung stereotactic radiotherapy. , 2004, Radiation medicine.

[4]  E. Hoffman,et al.  Characterization of the interstitial lung diseases via density-based and texture-based analysis of computed tomography images of lung structure and function. , 2003, Academic radiology.

[5]  Xiaogang Wang,et al.  Medical image classification with convolutional neural network , 2014, 2014 13th International Conference on Control Automation Robotics & Vision (ICARCV).

[6]  Joon Beom Seo,et al.  Performance testing of several classifiers for differentiating obstructive lung diseases based on texture analysis at high-resolution computerized tomography (HRCT) , 2009, Comput. Methods Programs Biomed..

[7]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Sang Min Lee,et al.  Quantitative assessment of change in regional disease patterns on serial HRCT of fibrotic interstitial pneumonia with texture-based automated quantification system , 2012, European Radiology.

[9]  Fabio A. González,et al.  A Deep Learning Architecture for Image Representation, Visual Interpretability and Automated Basal-Cell Carcinoma Cancer Detection , 2013, MICCAI.

[10]  Elliot K Fishman,et al.  Utility of high-resolution CT for management of diffuse lung disease: results of a survey of U.S. pulmonary physicians. , 2003, Academic radiology.

[11]  Joon Beom Seo,et al.  Comparison of Usual Interstitial Pneumonia and Nonspecific Interstitial Pneumonia: Quantification of Disease Severity and Discrimination between Two Diseases on HRCT Using a Texture-Based Automated System , 2011, Korean journal of radiology.

[12]  Dandan Mo,et al.  A survey on deep learning: one small step toward AI , 2012 .

[13]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[14]  D. Hansell,et al.  Obstructive lung diseases: texture classification for differentiation at CT. , 2003, Radiology.

[15]  Marleen de Bruijne,et al.  Combining Generative and Discriminative Representation Learning for Lung CT Analysis With Convolutional Restricted Boltzmann Machines , 2016, IEEE Transactions on Medical Imaging.

[16]  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.

[17]  Ronald M. Summers,et al.  Holistic classification of CT attenuation patterns for interstitial lung diseases via deep convolutional neural networks , 2018, Comput. methods Biomech. Biomed. Eng. Imaging Vis..

[18]  E. Hoffman,et al.  Computer recognition of regional lung disease patterns. , 1999, American journal of respiratory and critical care medicine.

[19]  Yaroslav Bulatov,et al.  Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks , 2013, ICLR.

[20]  Joon Beom Seo,et al.  A support vector machine classifier reduces interscanner variation in the HRCT classification of regional disease pattern in diffuse lung disease: comparison to a Bayesian classifier. , 2013, Medical physics.

[21]  G. van Kaick,et al.  Usual interstitial pneumonia. Quantitative assessment of high-resolution computed tomography findings by computer-assisted texture-based image analysis. , 1997, Investigative radiology.

[22]  W A Kalender,et al.  Measurement of pulmonary parenchymal attenuation: use of spirometric gating with quantitative CT. , 1990, Radiology.

[23]  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.

[24]  Kunio Doi,et al.  Computerized detection of diffuse lung disease in MDCT: the usefulness of statistical texture features , 2009, Physics in medicine and biology.

[25]  E. V. van Beek,et al.  Computer-aided classification of interstitial lung diseases via MDCT: 3D adaptive multiple feature method (3D AMFM). , 2006, Academic radiology.

[26]  Marios Anthimopoulos,et al.  Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network , 2016, IEEE Transactions on Medical Imaging.

[27]  Stephen Lam,et al.  The effects of radiation dose and CT manufacturer on measurements of lung densitometry. , 2007, Chest.

[28]  P. Grenier,et al.  Chronic diffuse interstitial lung disease: diagnostic value of chest radiography and high-resolution CT. , 1991, Radiology.

[29]  Ganesh Raghu.  Epidemiology, survival, incidence and prevalence of idiopathic pulmonary fibrosis in the USA and Canada , 2017, European Respiratory Journal.

[30]  Giovanni Montana,et al.  Deep neural networks for anatomical brain segmentation , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).