Investigating Cross-Dataset Abnormality Detection in Endoscopy with A Weakly-Supervised Multiscale Convolutional Neural Network

The detection of abnormalities in endoscopic video frames can contribute in the early and more accurate detection of pathologic conditions. In this paper we present a novel Convolutional Neural Network (CNN) architecture for automatic detection of abnormal images in endoscopic video sequences. It features multiscale representation of the endoscopic images in its structure, and peephole connections contributing in enhanced generalization with less computational requirements. An important aspect of the proposed architecture is that it enables weakly-supervised learning, using only semantically annotated images. A novel cross-dataset experimental study is performed to investigate its generalization performance on various publicly available datasets. The results validate that the proposed architecture outperforms recent approaches, with results reaching up to 90.66% in terms of the area under the receiver operating characteristic.

[1]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

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

[3]  Huaici Zhao,et al.  Computer aided endoscope diagnosis via weakly labeled data mining , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[4]  Dimitris K. Iakovidis,et al.  Weakly-supervised Convolutional learning for detection of inflammatory gastrointestinal lesions , 2016, 2016 IEEE International Conference on Imaging Systems and Techniques (IST).

[5]  Dimitris K. Iakovidis,et al.  KID Project: an internet-based digital video atlas of capsule endoscopy for research purposes , 2017, Endoscopy International Open.

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

[7]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[8]  Max Q.-H. Meng,et al.  A study on automated segmentation of blood regions in Wireless Capsule Endoscopy images using fully convolutional networks , 2017, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).

[9]  Dimitris K. Iakovidis,et al.  Automatic lesion detection in capsule endoscopy based on color saliency: closer to an essential adjunct for reviewing software. , 2014, Gastrointestinal endoscopy.

[10]  Nima Tajbakhsh,et al.  Automated Polyp Detection in Colonoscopy Videos Using Shape and Context Information , 2016, IEEE Transactions on Medical Imaging.

[11]  Anirban Mukhopadhyay,et al.  Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015 , 2015 .

[12]  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.

[13]  Aymeric Histace,et al.  Toward embedded detection of polyps in WCE images for early diagnosis of colorectal cancer , 2014, International Journal of Computer Assisted Radiology and Surgery.

[14]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[16]  Dimitris A. Karras,et al.  Computer-aided tumor detection in endoscopic video using color wavelet features , 2003, IEEE Transactions on Information Technology in Biomedicine.

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

[18]  Evaggelos Spyrou,et al.  Weakly-Supervised Lesion Detection in Video Capsule Endoscopy Based on a Bag-of-Colour Features Model , 2016, CARE@MICCAI.

[19]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

[20]  D. Iakovidis,et al.  Software for enhanced video capsule endoscopy: challenges for essential progress , 2015, Nature Reviews Gastroenterology &Hepatology.

[21]  Anastasios Koulaouzidis,et al.  Blood detection in wireless capsule endoscope images based on salient superpixels , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[22]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[23]  Miguel Tavares Coimbra,et al.  Invariant Gabor Texture Descriptors for Classification of Gastroenterology Images , 2012, IEEE Transactions on Biomedical Engineering.

[24]  Fernando Vilariño,et al.  WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians , 2015, Comput. Medical Imaging Graph..

[25]  Carmen C. Y. Poon,et al.  Automatic Detection and Classification of Colorectal Polyps by Transferring Low-Level CNN Features From Nonmedical Domain , 2017, IEEE Journal of Biomedical and Health Informatics.

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

[27]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

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

[29]  Jiebo Luo,et al.  Deep sparse feature selection for computer aided endoscopy diagnosis , 2015, Pattern Recognit..