GIANA Polyp Segmentation with Fully Convolutional Dilation Neural Networks

Yun Bo Guo, Bogdan J. Matuszewski

2019

Abstract

Polyp detection and segmentation in colonoscopy images plays an important role in early detection of colorectal cancer. The paper describes methodology adopted for the EndoVisSub2017/2018 Gastrointestinal Image ANAlysis – (GIANA) polyp segmentation sub-challenges. The developed segmentation algorithms are based on the fully convolutional neural network (FCNN) model. Two novel variants of the FCNN have been investigated, implemented and evaluated. The first one, combines the deep residual network and the dilation kernel layers within the fully convolutional network framework. The second proposed architecture is based on the U-net network augmented by the dilation kernels and “squeeze and extraction” units. The proposed architectures have been evaluated against the well-known FCN8 model. The paper describes the adopted evaluation metrics and presents the results on the GIANA dataset. The proposed methods produced competitive results, securing the first place for the SD and HD image segmentation tasks at the 2017 GIANA challenge and the second place for the SD images at the 2018 GIANA challenge.

Paper Citation

in Harvard Style

Guo Y. and Matuszewski B. (2019). GIANA Polyp Segmentation with Fully Convolutional Dilation Neural Networks.In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: GIANA, ISBN 978-989-758-354-4, pages 632-641. DOI: 10.5220/0007698806320641

in Bibtex Style

@conference{giana19,
author={Yun Guo and Bogdan Matuszewski},
title={GIANA Polyp Segmentation with Fully Convolutional Dilation Neural Networks},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: GIANA,},
year={2019},
pages={632-641},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007698806320641},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: GIANA,
TI - GIANA Polyp Segmentation with Fully Convolutional Dilation Neural Networks
SN - 978-989-758-354-4
AU - Guo Y.
AU - Matuszewski B.
PY - 2019
SP - 632
EP - 641
DO - 10.5220/0007698806320641