CNN-SVM for Microvascular Morphological Type Recognition with Data Augmentation

This paper focuses on the problem of feature extraction and the classification of microvascular morphological types to aid esophageal cancer detection. We present a patch-based system with a hybrid SVM model with data augmentation for intraepithelial papillary capillary loop recognition. A greedy patch-generating algorithm and a specialized CNN named NBI-Net are designed to extract hierarchical features from patches. We investigate a series of data augmentation techniques to progressively improve the prediction invariance of image scaling and rotation. For classifier boosting, SVM is used as an alternative to softmax to enhance generalization ability. The effectiveness of CNN feature representation ability is discussed for a set of widely used CNN models, including AlexNet, VGG-16, and GoogLeNet. Experiments are conducted on the NBI-ME dataset. The recognition rate is up to 92.74% on the patch level with data augmentation and classifier boosting. The results show that the combined CNN-SVM model beats models of traditional features with SVM as well as the original CNN with softmax. The synthesis results indicate that our system is able to assist clinical diagnosis to a certain extent.

[1]  Doreen Eichel,et al.  Learning And Soft Computing Support Vector Machines Neural Networks And Fuzzy Logic Models , 2016 .

[2]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[3]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Ching Y. Suen,et al.  A novel hybrid CNN-SVM classifier for recognizing handwritten digits , 2012, Pattern Recognit..

[5]  Andrew Zisserman,et al.  Image Classification using Random Forests and Ferns , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[6]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[7]  Jaime G. Carbonell,et al.  A theory of transfer learning with applications to active learning , 2013, Machine Learning.

[8]  Joshua Powell.  Pedestrian Detection with Convolutional Neural Networks , 2017 .

[9]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

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

[11]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[12]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[13]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[14]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[15]  John Tran,et al.  cuDNN: Efficient Primitives for Deep Learning , 2014, ArXiv.

[16]  Haruhiro Inoue,et al.  Magnification endoscopy in esophageal squamous cell carcinoma: a review of the intrapapillary capillary loop classification , 2015, Annals of gastroenterology.

[17]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[18]  Marimuthu Palaniswami,et al.  Support Vector Machines for Automated Recognition of Obstructive Sleep Apnea Syndrome From ECG Recordings , 2009, IEEE Transactions on Information Technology in Biomedicine.

[19]  Yoshinori Morita,et al.  ROLE OF NARROW BAND IMAGING FOR DIAGNOSIS OF EARLY‐STAGE ESOPHAGOGASTRIC CANCER: CURRENT CONSENSUS OF EXPERIENCED ENDOSCOPISTS IN ASIA–PACIFIC REGION , 2011, Digestive endoscopy : official journal of the Japan Gastroenterological Endoscopy Society.

[20]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

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

[22]  Andrew Zisserman,et al.  Return of the Devil in the Details: Delving Deep into Convolutional Nets , 2014, BMVC.

[23]  M. Szarvas,et al.  Pedestrian detection with convolutional neural networks , 2005, IEEE Proceedings. Intelligent Vehicles Symposium, 2005..

[24]  Stefan Winkler,et al.  Deep Learning for Emotion Recognition on Small Datasets using Transfer Learning , 2015, ICMI.

[25]  Japan Esophageal Society.  Japanese Classification of Esophageal Cancer, tenth edition: part I , 2009, Esophagus.

[26]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[27]  Stefan Carlsson,et al.  CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

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

[29]  Ioannis Kompatsiaris,et al.  GPU acceleration for support vector machines , 2011, WIAMIS 2011.

[30]  Feng Chu,et al.  Applications of support vector machines to cancer classification with microarray data , 2005, Int. J. Neural Syst..

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

[32]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[33]  Akira Matsui,et al.  Utility of magnifying endoscopy with narrow band imaging in determining the invasion depth of superficial pharyngeal cancer , 2015, Head & neck.

[34]  Xiang Zhang,et al.  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks , 2013, ICLR.