Feature Representation Analysis of Deep Convolutional Neural Network using Two-stage Feature Transfer -An Application for Diffuse Lung Disease Classification-

Transfer learning is a machine learning technique designed to improve generalization performance by using pre-trained parameters obtained from other learning tasks. For image recognition tasks, many previous studies have reported that, when transfer learning is applied to deep neural networks, performance improves, despite having limited training data. This paper proposes a two-stage feature transfer learning method focusing on the recognition of textural medical images. During the proposed method, a model is successively trained with massive amounts of natural images, some textural images, and the target images. We applied this method to the classification task of textural X-ray computed tomography images of diffuse lung diseases. In our experiment, the two-stage feature transfer achieves the best performance compared to a from-scratch learning and a conventional single-stage feature transfer. We also investigated the robustness of the target dataset, based on size. Two-stage feature transfer shows better robustness than the other two learning methods. Moreover, we analyzed the feature representations obtained from DLDs imagery inputs for each feature transfer models using a visualization method. We showed that the two-stage feature transfer obtains both edge and textural features of DLDs, which does not occur in conventional single-stage feature transfer models.

[1]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Hayaru Shouno,et al.  Connected character recognition in cursive handwriting using selective attention model with bend processing , 1994, Systems and Computers in Japan.

[3]  K. Fukushima Neural network model for selective attention in visual pattern recognition and associative recall. , 1987, Applied optics.

[4]  Song Han,et al.  Learning both Weights and Connections for Efficient Neural Network , 2015, NIPS.

[5]  Kunihiko Fukushima,et al.  Neocognitron: A hierarchical neural network capable of visual pattern recognition , 1988, Neural Networks.

[6]  Andrea Vedaldi,et al.  Salient Deconvolutional Networks , 2016, ECCV.

[7]  Kunihiko Fukushima,et al.  Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position , 1980, Biological Cybernetics.

[8]  Marios Anthimopoulos,et al.  Multi-source Transfer Learning with Convolutional Neural Networks for Lung Pattern Analysis , 2016, IEEE journal of biomedical and health informatics.

[9]  Atsuto Maki,et al.  Factors of Transferability for a Generic ConvNet Representation , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  D. Hubel,et al.  Receptive fields, binocular interaction and functional architecture in the cat's visual cortex , 1962, The Journal of physiology.

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

[12]  Rich Caruana,et al.  Do Deep Nets Really Need to be Deep? , 2013, NIPS.

[13]  K. Doi,et al.  Quantitative computerized analysis of diffuse lung disease in high-resolution computed tomography. , 2003, Medical physics.

[14]  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..

[15]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[16]  Nima Tajbakhsh,et al.  Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning? , 2016, IEEE Transactions on Medical Imaging.

[17]  Satoshi Suzuki,et al.  A Transfer Learning Method with Deep Convolutional Neural Network for Diffuse Lung Disease Classification , 2015, ICONIP.