Feature Space Extrapolation for Ulcer Classification in Wireless Capsule Endoscopy Images

Deep convolutional neural network has shown dramatically improved performance not just in computer vision problems but also in various medical imaging tasks. For improved and meaningful result with deep learning approaches, the quality of training dataset is critical. However, in medical imaging applications, collecting full aspects of lesion samples is quite difficult due to the limited number of patients, privacy and right concerns. In this paper, we propose feature space extrapolation for ulcer data augmentation. We build dual encoder network combining two VGG19 nets integrating them in fully connected encoded feature space. Ulcer data is extrapolated in the encoded feature space based on respective closest normal sample. And then, fully connected layers are fine-tuned for final ulcer classification. Experimental evaluation shows our proposed dual encoder network with feature space extrapolation improves ulcer classification.

[1]  S. T. Devarakonda,et al.  A convolutional neural network approach for abnormality detection in Wireless Capsule Endoscopy , 2017, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).

[2]  Aymeric Histace,et al.  Comparative Validation of Polyp Detection Methods in Video Colonoscopy: Results From the MICCAI 2015 Endoscopic Vision Challenge , 2017, IEEE Transactions on Medical Imaging.

[3]  Marius Pedersen,et al.  Y-Net: A deep Convolutional Neural Network for Polyp Detection , 2018, BMVC.

[4]  Dimitrios K. Iakovidis,et al.  Reduction of capsule endoscopy reading times by unsupervised image mining , 2010, Comput. Medical Imaging Graph..

[5]  Max Q.-H. Meng,et al.  Saliency Based Ulcer Detection for Wireless Capsule Endoscopy Diagnosis , 2015, IEEE Transactions on Medical Imaging.

[6]  Chong-Wah Ngo,et al.  Automatic Hookworm Detection in Wireless Capsule Endoscopy Images , 2016, IEEE Transactions on Medical Imaging.

[7]  P. Swain,et al.  Wireless capsule endoscopy. , 2002, The Israel Medical Association journal : IMAJ.

[8]  Anders Heyden,et al.  Generalization of prostate cancer classification for multiple sites using deep learning , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[9]  Guo-Zheng Li,et al.  An asymmetric classifier based on partial least squares , 2010, Pattern Recognit..

[10]  Gregory D. Hager,et al.  Learning disease severity for capsule endoscopy images , 2009, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[11]  Kuk-Jin Yoon,et al.  Polyp Detection via Imbalanced Learning and Discriminative Feature Learning , 2015, IEEE Transactions on Medical Imaging.

[12]  Isabel N. Figueiredo,et al.  Automated Polyp Detection in Colon Capsule Endoscopy , 2013, IEEE Transactions on Medical Imaging.