A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images

Colorectal cancer (CRC) is the third cause of cancer death worldwide. Currently, the standard approach to reduce CRC-related mortality is to perform regular screening in search for polyps and colonoscopy is the screening tool of choice. The main limitations of this screening procedure are polyp miss rate and the inability to perform visual assessment of polyp malignancy. These drawbacks can be reduced by designing decision support systems (DSS) aiming to help clinicians in the different stages of the procedure by providing endoluminal scene segmentation. Thus, in this paper, we introduce an extended benchmark of colonoscopy image segmentation, with the hope of establishing a new strong benchmark for colonoscopy image analysis research. The proposed dataset consists of 4 relevant classes to inspect the endoluminal scene, targeting different clinical needs. Together with the dataset and taking advantage of advances in semantic segmentation literature, we provide new baselines by training standard fully convolutional networks (FCNs). We perform a comparative study to show that FCNs significantly outperform, without any further postprocessing, prior results in endoluminal scene segmentation, especially with respect to polyp segmentation and localization.

[1]  Fernando Vilariño,et al.  Polyp Segmentation Method in Colonoscopy Videos by Means of MSA-DOVA Energy Maps Calculation , 2014, CLIP@MICCAI.

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

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

[4]  Fernando Vilariño,et al.  Towards automatic polyp detection with a polyp appearance model , 2012, Pattern Recognit..

[5]  Debora Gil,et al.  Discarding Non Informative Regions for Efficient Colonoscopy Image Analysis , 2014, CARE@MICCAI.

[6]  Fernando Vilariño,et al.  Impact of Keypoint Detection on Graph-Based Characterization of Blood Vessels in Colonoscopy Videos , 2014, CARE@MICCAI.

[7]  Andreas Uhl,et al.  Colonic Polyp Classification with Convolutional Neural Networks , 2016, 2016 IEEE 29th International Symposium on Computer-Based Medical Systems (CBMS).

[8]  Christopher Joseph Pal,et al.  The Importance of Skip Connections in Biomedical Image Segmentation , 2016, LABELS/DLMIA@MICCAI.

[9]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[10]  Rob Fergus,et al.  Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[11]  Fernando Vilariño,et al.  Impact of image preprocessing methods on polyp localization in colonoscopy frames , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[12]  Joachim M. Buhmann,et al.  Crowdsourcing the creation of image segmentation algorithms for connectomics , 2015, Front. Neuroanat..

[13]  J. Hardcastle,et al.  Colorectal cancer , 1993, Europe Against Cancer European Commission Series for General Practitioners.

[14]  Sun Young Park,et al.  Colonoscopic polyp detection using convolutional neural networks , 2016, SPIE Medical Imaging.

[15]  K. Lundin,et al.  HLA-DQ8 as an Ir gene in coeliac disease , 2003, Gut.

[16]  Lubomir M. Hadjiiski,et al.  Urinary bladder segmentation in CT urography using deep-learning convolutional neural network and level sets. , 2016, Medical physics.

[17]  Guido Gerig,et al.  A brain tumor segmentation framework based on outlier detection , 2004, Medical Image Anal..

[18]  Christopher Joseph Pal,et al.  Brain tumor segmentation with Deep Neural Networks , 2015, Medical Image Anal..

[19]  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.

[20]  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.

[21]  Brian B. Avants,et al.  The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) , 2015, IEEE Transactions on Medical Imaging.

[22]  Lisa Tang,et al.  Deep 3D Convolutional Encoder Networks With Shortcuts for Multiscale Feature Integration Applied to Multiple Sclerosis Lesion Segmentation , 2016, IEEE Transactions on Medical Imaging.

[23]  Hao Chen,et al.  Deep Contextual Networks for Neuronal Structure Segmentation , 2016, AAAI.

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

[25]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[26]  A. M. Leufkens,et al.  Factors influencing the miss rate of polyps in a back-to-back colonoscopy study , 2012, Endoscopy.

[27]  B. Ginneken,et al.  3D Segmentation in the Clinic: A Grand Challenge , 2007 .

[28]  Vadim Backman,et al.  Colonoscopy and optical biopsy: bridging technological advances to clinical practice. , 2011, Gastroenterology.

[29]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[30]  John Salvatier,et al.  Theano: A Python framework for fast computation of mathematical expressions , 2016, ArXiv.

[31]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Til Aach,et al.  A comparison of blood vessel features and local binary patterns for colorectal polyp classification , 2009, Medical Imaging.

[33]  H. Tajiri,et al.  Narrow-band imaging in the diagnosis of colorectal mucosal lesions: a pilot study. , 2004, Endoscopy.

[34]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[35]  Yoshua Bengio,et al.  FitNets: Hints for Thin Deep Nets , 2014, ICLR.

[36]  M J Bruno,et al.  Magnification endoscopy, high resolution endoscopy, and chromoscopy; towards a better optical diagnosis , 2003, Gut.