A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images

Abstract

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.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 38

1. 1.

   Colorectal cancer. 2016.

   Not in our library

2. 2.

   Leufkens A., Van Oijen M., Vleggaar F. P., Siersema P. D. Factors inuencing the miss rate of polyps in a back-to-back colonoscopy study. Endoscopy. 2012;44(5):470-475.

   Not in our library10.1055/s-0031-1291666

3. 3.

   Machida H., Sano Y., Hamamoto Y., et al. Narrow-band imaging in the diagnosis of colorectal mucosal lesions: a pilot study. Endoscopy. 2004;36(12):1094-1098.

   Not in our library10.1055/s-2004-826040

4. 4.

   Bruno M. Magnification endoscopy, high resolution endoscopy, and chromoscopy; towards a better optical diagnosis. Gut. 2003;52(Supplement 4):iv7-iv11.

   Not in our library10.1136/gut.52.suppl_4.iv7

5. 5.

   Roy H. K., Goldberg M. J., Bajaj S., Backman V. Colonoscopic optical biopsy: bridging technological advances to clinical practice. Gastroenterology. 2011;140(7):p. 1863.

   Not in our library10.1053/j.gastro.2011.04.027

6. 6.

   Bernal J., Sánchez F. J., Fernández-Esparrach G., Gil D., Rodríguez C., Vilariño F. WM-DOVA maps for accurate polyp highlighting in colonoscopy: validation vs. saliency maps from physicians. Computerized Medical Imaging and Graphics. 2015;43:99-111.

   Not in our library10.1016/j.compmedimag.2015.02.007

7. 7.

   Gross S., Stehle T., Behrens A., et al. A comparison of blood vessel features and local binary patterns for colorectal polyp classification. SPIE Medical Imaging. 2009.

   Not in our library

8. 8.

   Park S. Y., Sargent D. Colonoscopic polyp detection using convolutional neural networks. SPIE Medical Imaging. 2016.

   Not in our library

9. 9.

   Ribeiro E., Uhl A., Häfner M. Colonic polyp classification with convolutional neural networks. 253-258.

   Not in our library10.1109/cbms.2016.39

10. 10.

    Silva J., Histace A., Romain O., Dray X., Granado B. Toward embedded detection of polyps in wce images for early diagnosis of colorectal cancer. International Journal of Computer Assisted Radiology and Surgery. 2014;9(2):283-293.

    Not in our library10.1007/s11548-013-0926-3

11. 11.

    Tajbakhsh N., Gurudu S., Liang J. Automated polyp detection in colonoscopy videos using shape and context information. IEEE Transactions on Medical Imaging. 2015;35(2):630-644.

    Not in our library10.1109/tmi.2015.2487997

12. 12.

    Bernal J., Gil D., Sánchez C., Sánchez F. J. Discarding non informative regions for efficient colonoscopy image analysis. International Workshop on Computer-Assisted and Robotic Endoscopy. 2014;1-10.

    Not in our library

13. 13.

    Bernal J., Núñez J. M., Sánchez F. J., Vilariño F. Polyp segmentation method in colonoscopy videos by means of MSA-DOVA energy maps calculation. MICCAI 2014 Workshop on Clinical Image-Based Procedures. 2014;41-49.

    Not in our library

14. 14.

    Núñez J. M., Bernal J., Ferrer M., Vilariño F. Impact of keypoint detection on graph-based characterization of blood vessels in colonoscopy videos. International Workshop on Computer-Assisted and Robotic Endoscopy. 2014;22-33.

    Not in our library

15. 15.

    Bernal J., Sánchez J., Vilarino F. Impact of image preprocessing methods on polyp localization in colonoscopy frames. 7350-7354.

    Not in our library10.1109/embc.2013.6611256

16. 16.

    Deng J., Dong W., Socher R., Li L. J., Li K., Fei-Fei L. ImageNet: a large-scale hierarchical image database. CVPR09. 2009.

    Not in our library

17. 17.

    Lin T. Y., Maire M., Belongie S., et al. Microsoft coco: common objects in context.

    Not in our library

18. 18.

    Drozdzal M., Vorontsov E., Chartrand G., Kadoury S., Pal C. The importance of skip connections in biomedical image segmentation.

    Not in our library

19. 19.

    Ronneberger O., Fischer P., Brox T. U-net: convolutional networks for biomedical image segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention. 2015;234-241.

    Not in our library

20. 20.
    Crowdsourcing the creation of image segmentation algorithms for connectomics · 2015

    No notice
21. 21.

    Menze B., Jakab A., Bauer S., et al. The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Transactions on Medical Imaging. 2014;34(10):1993-2024.

    Not in our library10.1109/tmi.2014.2377694

22. 22.

    Styner M., Lee J., Chin B., et al. 3d segmentation in the clinic: a grand challenge ii: Ms lesion segmentation. Midas Journal. 2008;2008:1-6.

    Not in our library

23. 23.

    Brosch T., Tang L. Y. W., Yoo Y., Li D. K., Traboulsee A., Tam R. Deep 3d convolutional encoder networks with shortcuts for multiscale feature integration applied to multiple sclerosis lesion segmentation. IEEE Transactions on Medical Imaging. 2016;35(5):1229-1239.

    Not in our library10.1109/tmi.2016.2528821

24. 24.

    Chen H., Qi X., Cheng J., Heng P. A. Deep contextual networks for neuronal structure segmentation. 1167-1173.

    Not in our library

25. 25.

    Havaei M., Davy A., Warde-Farley D., et al. Brain tumor segmentation with deep neural networks.

    Not in our library10.1016/j.media.2016.05.004

26. 26.

    Bernal J., Sánchez J., Vilarino F. Towards automatic polyp detection with a polyp appearance model. Pattern Recognition. 2012;45(9):3166-3182.

    Not in our library10.1016/j.patcog.2012.03.002

27. 27.

    Long J., Shelhamer E., Darrell T. Fully convolutional networks for semantic segmentation. 2015;3431-3440.

    Not in our library10.1109/cvpr.2015.7298965

28. 28.

    Bernal J., Tajbakhsh N., Sanchez F. J., et al. Comparative validation of polyp detection methods in video colonoscopy: results from the miccai 2015 endoscopic vision challenge. IEEE Transactions on Medical Imaging. 2017;36(6):1231-1249.

    Not in our library10.1109/tmi.2017.2664042

29. 29.

    Cha K. H., Hadjiiski L., Samala R. K., Chan H. P., Caoili E. M., Cohan R. H. Urinary bladder segmentation in ct urography using deep-learning convolutional neural network and level sets. Medical Physics. 2016;43(4):1882-1896.

    Not in our library10.1118/1.4944498

30. 30.

    Prastawa M., Bullitt E., Ho S., Gerig G. A brain tumor segmentation framework based on outlier detection. Medical Image Analysis. 2004;8(3):275-283.

    Not in our library10.1016/j.media.2004.06.007

31. 31.

    Everingham M., Van Gool L., Williams C. K. I., Winn J., Zisserman A. The pascal visual object classes (voc) challenge. International Journal of Computer Vision. 2010;88(2):303-338.

    Not in our library10.1007/s11263-009-0275-4

32. 32.

    Tieleman T., Hinton G. rmsprop adaptive learning. COURSERA: Neural Networks for Machine Learning. 2012.

    Not in our library

33. 33.

    Srivastava N., Hinton G., Krizhevsky A., Sutskever I., Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research. 2014;15(1):1929-1958.

    Not in our library

34. 34.

    Eigen D., Fergus R. Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture.

    Not in our library

35. 35.

    Romero A., Ballas N., Kahou S. E., Chassang A., Gatta C., Bengio Y. Fitnets: hints for thin deep nets.

    Not in our library

36. 36.

    Huang G., Liu Z., Weinberger K. Q., van der Maaten L. Densely connected convolutional networks.

    Not in our library

37. 37.

    Theano: a python framework for fast computation of mathematical expressions.

    Not in our library

38. 38.

    Chollet F. Keras.

    Not in our library

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.