BI-GCN: Boundary-Aware Input-Dependent Graph Convolution Network for Biomedical Image Segmentation

Segmentation is an essential operation of image processing. The convolution operation suffers from a limited receptive field, while global modelling is fundamental to segmentation tasks. In this paper, we apply graph convolution into the segmentation task and propose an improved Laplacian. Different from existing methods, our Laplacian is data-dependent, and we introduce two attention diagonal matrices to learn a better vertex relationship. In addition, it takes advantage of both region and boundary information when performing graph-based information propagation. Specifically, we model and reason about the boundary-aware region-wise correlations of different classes through learning graph representations, which is capable of manipulating long range semantic reasoning across various regions with the spatial enhancement along the object’s boundary. Our model is well-suited to obtain global semantic region information while also accommodates local spatial boundary characteristics simultaneously. Experiments on two types of challenging datasets demonstrate that our method outperforms the state-ofthe-art approaches on the segmentation of polyps in colonoscopy images and of the optic disc and optic cup in colour fundus images. © 2021. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms. ar X iv :2 11 0. 14 77 5v 1 [ cs .C V ] 2 7 O ct 2 02 1 2 Y. MENG ET AL.: BOUNDARY-AWARE INPUT-DEPENDENT GCN

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

[2]  Ross B. Girshick,et al.  Boundary IoU: Improving Object-Centric Image Segmentation Evaluation , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Yitian Zhao,et al.  Graph-Based Region and Boundary Aggregation for Biomedical Image Segmentation , 2021, IEEE Transactions on Medical Imaging.

[4]  Kaamran Raahemifar,et al.  Retinal fundus images for glaucoma analysis: the RIGA dataset , 2018, Medical Imaging.

[5]  Xiaochun Cao,et al.  Joint Optic Disc and Cup Segmentation Based on Multi-Label Deep Network and Polar Transformation , 2018, IEEE Transactions on Medical Imaging.

[6]  Ling Shao,et al.  PraNet: Parallel Reverse Attention Network for Polyp Segmentation , 2020, MICCAI.

[7]  Chi-Keung Tang,et al.  Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Francisco Fumero,et al.  RIM-ONE: An open retinal image database for optic nerve evaluation , 2011, 2011 24th International Symposium on Computer-Based Medical Systems (CBMS).

[9]  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.

[10]  Thomas de Lange,et al.  Kvasir-SEG: A Segmented Polyp Dataset , 2019, MMM.

[11]  Yalin Zheng,et al.  CNN-GCN Aggregation Enabled Boundary Regression for Biomedical Image Segmentation , 2020, MICCAI.

[12]  Eric P. Xing,et al.  Symbolic Graph Reasoning Meets Convolutions , 2018, NeurIPS.

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[14]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[16]  Antonio M. López,et al.  A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images , 2016, Journal of healthcare engineering.

[17]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[18]  Christopher Joseph Pal,et al.  Delving Deeper into Convolutional Networks for Learning Video Representations , 2015, ICLR.

[19]  Shuguang Cui,et al.  Adaptive Context Selection for Polyp Segmentation , 2020, MICCAI.

[20]  Wei Meng,et al.  Regression of Instance Boundary by Aggregated CNN and GCN , 2020, ECCV.

[21]  Kai Zhao,et al.  Res2Net: A New Multi-Scale Backbone Architecture , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

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

[24]  Huiguang He,et al.  Boundary Aware U-Net for Retinal Layers Segmentation in Optical Coherence Tomography Images , 2021, IEEE Journal of Biomedical and Health Informatics.

[25]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[26]  Hong Liu,et al.  Spatial Pyramid Based Graph Reasoning for Semantic Segmentation , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  T. Wong,et al.  Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis. , 2014, Ophthalmology.

[28]  Shuicheng Yan,et al.  Graph-Based Global Reasoning Networks , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Nima Tajbakhsh,et al.  UNet++: A Nested U-Net Architecture for Medical Image Segmentation , 2018, DLMIA/ML-CDS@MICCAI.

[30]  Keerthi Ram,et al.  Psi-Net: Shape and boundary aware joint multi-task deep network for medical image segmentation , 2019, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[31]  Trevor Darrell,et al.  Deep Layer Aggregation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[32]  Xiaoxiao Li,et al.  REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs , 2019, Medical Image Anal..

[33]  Tien Yin Wong,et al.  ORIGA-light: An online retinal fundus image database for glaucoma analysis and research , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[34]  Jayanthi Sivaswamy,et al.  Drishti-GS: Retinal image dataset for optic nerve head(ONH) segmentation , 2014, 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI).

[35]  Philip H. S. Torr,et al.  Dual Graph Convolutional Network for Semantic Segmentation , 2019, BMVC.

[36]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[37]  Xirong Li,et al.  Oval Shape Constraint based Optic Disc and Cup Segmentation in Fundus Photographs , 2019, BMVC.

[38]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[39]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Abhinav Gupta,et al.  Beyond Grids: Learning Graph Representations for Visual Recognition , 2018, NeurIPS.

[41]  Cheng Chen,et al.  Selective Feature Aggregation Network with Area-Boundary Constraints for Polyp Segmentation , 2019, MICCAI.