Learning Features for Tissue Classification with the Classification Restricted Boltzmann Machine

markdownabstract__Abstract__ Performance of automated tissue classification in medical imaging depends on the choice of descriptive features. In this paper, we show how restricted Boltzmann machines (RBMs) can be used to learn features that are especially suited for texture-based tissue classification. We introduce the convolutional classification RBM, a combination of the existing convolutional RBM and classification RBM, and use it for discriminative feature learning. We evaluate the classification accuracy of convolutional and non-convolutional classification RBMs on two lung CT problems. We find that RBM-learned features outperform conventional RBM-based feature learning, which is unsupervised and uses only a generative learning objective, as well as often-used filter banks. We show that a mixture of generative and discriminative learning can produce filters that give a higher classification accuracy.

[1]  Thomas G. Dietterich.  Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms , 1998, Neural Computation.

[2]  Cordelia Schmid,et al.  Constructing models for content-based image retrieval , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[3]  Yuko Y Palesch,et al.  Analysis of clustered matched‐pair data , 2003, Statistics in medicine.

[4]  Jitendra Malik,et al.  Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons , 2001, International Journal of Computer Vision.

[5]  Mohammad Norouzi,et al.  Stacks of convolutional Restricted Boltzmann Machines for shift-invariant feature learning , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Honglak Lee,et al.  Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations , 2009, ICML '09.

[7]  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.

[8]  Andrew Zisserman,et al.  A Statistical Approach to Material Classification Using Image Patch Exemplars , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  J. Hardin,et al.  A note on the tests for clustered matched‐pair binary data , 2010, Biometrical journal. Biometrische Zeitschrift.

[10]  Zhenghao Chen,et al.  On Random Weights and Unsupervised Feature Learning , 2011, ICML.

[11]  Marleen de Bruijne,et al.  Optimal Graph Based Segmentation Using Flow Lines with Application to Airway Wall Segmentation , 2011, IPMI.

[12]  Honglak Lee,et al.  Unsupervised learning of hierarchical representations with convolutional deep belief networks , 2011, Commun. ACM.

[13]  Razvan Pascanu,et al.  Learning Algorithms for the Classification Restricted Boltzmann Machine , 2012, J. Mach. Learn. Res..

[14]  Antoine Geissbühler,et al.  Building a reference multimedia database for interstitial lung diseases , 2012, Comput. Medical Imaging Graph..

[15]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[16]  Dimitri Van De Ville,et al.  Near-Affine-Invariant Texture Learning for Lung Tissue Analysis Using Isotropic Wavelet Frames , 2012, IEEE Transactions on Information Technology in Biomedicine.

[17]  Roger C. Tam,et al.  Manifold Learning of Brain MRIs by Deep Learning , 2013, MICCAI.

[18]  Joachim Hornegger,et al.  Self-gated Radial MRI for Respiratory Motion Compensation on Hybrid PET/MR Systems , 2013, MICCAI.

[19]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  David Dagan Feng,et al.  Lung image patch classification with automatic feature learning , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).