GUNet: Duplex Global Graph Relationship Mining for Polyp Segmentation
DOI:
https://doi.org/10.62051/vsz9hp74Keywords:
Convolutional Neural Network; Semantic Segmentation; Graph Convolutional Network.Abstract
Colorectal Cancer is one of the most common cancers worldwide, and as the probability of cure decreases as the stages progress, the early-stage detection of possible indications of colorectal cancer (i.e., polyps) during colonoscopy exams can contribute greatly to its prevention and curation. Since some of the indications of colorectal cancer are hard to identify by the human eye, it becomes crucial to develop an algorithm that can assist in the early identification of abnormal tissue walls that may be signs of early-stage cancer. This paper proposes the GUNet, where duplex global graph relationships are mined through graph convolution operations. The core of this framework is the extraction and utilization of both spatial and semantic information from diverse encoded feature maps to acquire contextual semantic information, done so to construct a fuller and more diverse global representation. We also train the GUNet on a combination of three public datasets to enhance its generalization abilities. Experiments show that the GUNet can serve as a competitive alternative to the U-Net, achieving a 64.47% IOU on the combined dataset.
Downloads
References
[1] Rebecca L. Siegel et al. “Colorectal cancer statistics, 2023”. In: CA: A Cancer Journal for Clinicians 73.3 (2023), pp. 233 – 254. issn: 1542 - 4863. doi: 10.3322/caac.21772.
[2] Lou Guo-chun et al. “A retrospective study on endoscopic missing diagnosis of colorectal polyp and its related factors”. In: The Turkish Journal of Gastroenterology 25.1 (Apr. 22, 2015), pp. 182 – 186. issn: 13004948, 21485607. doi: 10.5152/tjg.2014.4664.
[3] A. Leufkens et al. “Factors influencing the miss rate of polyps in a back to-back colonoscopy study”. In: Endoscopy 44.5 (May 2012), pp. 470 – 475. issn: 0013 - 726X, 1438-8812. doi: 10.1055/s-0031-1291666.
[4] V Prasath. “Polyp Detection and Segmentation from Video Capsule Endoscopy: A Review”. In: Journal of Imaging 3.1 (Mar. 2017). Number: 1 Publisher: Multidisciplinary Digital Publishing Institute, p. 1. issn: 2313 - 433X. doi: 10.3390/jimaging3010001.
[5] Stavros A. Karkaniset al. “Computer-aided tumor detection in endoscopic video using color wavelet features”. In: IEEE transactions on information technology in biomedicine: a publication of the IEEE Engineering in Medicine and Biology Society 7.3 (Sept. 2003), pp. 141 – 152. issn: 1089 - 7771. doi: 10.1109/titb.2003.813794.
[6] Lu´ıs Alexandre, Nuno Nobre, and Jo˜ao Casteleiro. “Color and Position versus Texture Features for Endoscopic Polyp Detection”. In: 2008 International Conference on BioMedical Engineering and Informatics. 2008 International Conference on BioMedical Engineering and Informatics. Vol. 2. ISSN: 1948 - 2922. May 2008, pp. 38 – 42. doi: 10.1109/BMEI.2008.246.
[7] Alain S´anchez-Gonz´alez et al. “Automatized colon polyp segmentation via contour region analysis”. In: Computers in biology and medicine 100 (Jan. 9, 2018). Publisher: Comput Biol Med. issn: 1879-0534. doi: 10. 1016/j.compbiomed.2018.07.002.
[8] Geert Litjenset al. “A survey on deep learning in medical image analysis”. In: Medical Image Analysis 42 (Dec. 2017), pp. 60 – 88. issn: 13618415. doi: 10.1016/j.media.2017.07.005.
[9] Syed Muhammad Anwar et al. “Medical Image Analysis using Convolutional Neural Networks: A Review”. In: Journal of Medical Systems 42.11 (Nov. 2018), p. 226. issn: 0148-5598, 1573-689X. doi: 10.1007/s10916 - 018 - 1088 - 1.
[10] Jonathan Long, Evan Shelhamer, and Trevor Darrell. Fully Convolutional Networks for Semantic Segmentation. Mar. 8, 2015. arXiv: 1411.4038 [cs].
[11] Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-Net: Convolutional Networks for Biomedical Image Segmentation. May 18, 2015. arXiv: 1505.04597 [cs].
[12] Debesh Jha et al. ResUNet++: An Advanced Architecture for Medical Image Segmentation. Nov. 16, 2019. arXiv: 1911.07067 [cs, eess].
[13] Debesh Jha et al. “Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning”. In: IEEE Access 9 (2021), pp. 40496 – 40510. issn: 2169-3536. doi: 10.1109/ACCESS.2021.3063716.
[14] Zongwei Zhou et al. “UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation”. In: IEEE Transactions on Medical Imaging 39.6 (June 2020), pp. 1856–1867. issn: 0278 - 0062, 1558 - 254X. doi: 10.1109/TMI.2019.2959609.
[15] Huimin Huang et al. UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation. Apr. 19, 2020. arXiv: 2004.08790 [cs, eess].
[16] Tanvir Mahmud, Bishmoy Paul, and Shaikh Anowarul Fattah. “PolypSeg-Net: A modified encoder-decoder architecture for automated polyp seg-mentation from colonoscopy images”. In: Computers in Biology and Medicine 128 (Jan. 2021), p. 104119. issn: 00104825. doi: 10.1016/j.compbiomed.2020.104119.
[17] Ozan Oktay et al. Attention U-Net: Learning Where to Look for the Pancreas. May 20,2018. arXiv: 1804.03999 [cs].
[18] Zijin Yin et al. Duplex Contextual Relation Network for Polyp Segmentation. Jan. 19, 2022.arXiv: 2103.06725 [cs, eess].
[19] Francesco Visinetal. ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation. May 24, 2016. arXiv: 1511.07053 [cs].
[20] Mahmood Haithami et al. “An Embedded Recurrent Neural Network based Model for Endoscopic Semantic Segmentation”. In: (2021).
[21] Sae Hwang et al. “Polyp Detection in Colonoscopy Video using Elliptical Shape Feature”. In: 2007 IEEE International Conference on Image Processing. 2007 IEEE International Conference on Image Processing. San Antonio, TX, USA: IEEE, 2007, pp. II – 465 – II – 468. isbn: 978-1-4244 – 1436 - 9. doi: 10.1109/ICIP.2007.4379193.
[22] C. Van Wijk et al. “Detection and Segmentation of Colonic Polyps on Implicit Isosurfaces by Second Principal Curvature Flow”. In: IEEE Transactions on Medical Imaging 29.3 (Mar. 2010), pp. 688–698. issn: 0278 - 0062, 1558 - 254X. doi: 10.1109/TMI.2009.2031323.
[23] Juan Silva et al. “Toward embedded detection of polyps in WCE images for early diagnosis of colorectal cancer”. In: International Journal of Computer Assisted Radiology and Surgery 9.2 (Mar. 2014), pp. 283 – 293. issn: 1861-6410, 1861-6429. doi: 10.1007/s11548 - 013 - 0926 - 3.
[24] Alexander V. Mamonovetal. “Automated Polyp Detection in Colon Capsule Endoscopy”. In: IEEE Transactions on Medical Imaging 33.7 (July 2014), pp. 1488–1502. issn: 0278-0062, 1558-254X. doi: 10.1109/TMI. 2014.2314959.
[25] Yuji Iwahori et al. “Automatic Detection of Polyp Using Hessian Filter and HOG Features”. In:Procedia Computer Science 60 (2015), pp. 730 – 739. issn: 18770509. doi: 10.1016/j.procs.2015.08.226.
[26] Jorge Bernal et al. “WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validationvs. saliency maps from physicians”. In: Computerized Medical Imaging and Graphics 43 (July 2015), pp. 99 – 111. issn: 08956111. doi: 10.1016/j.compmedimag.2015.02.007.
[27] Foivos I. Diakogiannis et al. “ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data”. In: ISPRS Journal of Photogrammetry and Remote Sensing 162 (Apr. 2020), pp. 94–114. issn: 09242716. doi: 10.1016/j. isprsjprs.2020.01.013. arXiv: 1904. 00592 [cs].
[28] Jiahuan Song et al. “Global and Local Feature Reconstruction for Medical Image Segmentation”. In: IEEE Transactions on Medical Imaging 41.9 (Sept. 2022), pp. 2273–2284. issn: 0278-0062, 1558-254X. doi: 10.1109/ TMI.2022.3162111.
[29] Debapriya Banik et al. “Polyp-Net: A Multimodel Fusion Network for Polyp Segmentation”. In: IEEE Transactions on Instrumentation and Measurement 70 (2021), pp. 1–12. issn: 0018-9456, 1557 - 9662. doi: 10. 1109/TIM.2020.3015607.
[30] Xinzi Sun et al. Colorectal Polyp Segmentation by U-Net with Dilation Convolution. Dec. 26, 2019. arXiv: 1912.11947 [cs, eess].
[31] Krushi Patel, Andres M. Bur, and Guanghui Wang. “Enhanced U-Net: A Feature Enhancement Network for Polyp Segmentation”. In: 2021 18th Conference on Robots and Vision (CRV). 2021 18th Conference on Robots and Vision (CRV). Burnaby, BC, Canada: IEEE, May 2021, pp. 181 – 188. isbn: 978 - 1 - 66541 - 413 - 5. doi: 10.1109/CRV52889.2021.00032.
[32] Xiaoqi Zhao, Lihe Zhang, and Huchuan Lu. Automatic Polyp Segmentation via Multi-scaleSubtraction Network. Aug. 11, 2021. arXiv: 2108. 05082 [cs].
[33] Abhishek Srivastava et al. GMSRF-Net: An improved generalizability with global multi-scale residual fusion network for polyp segmentation. Nov. 20, 2021. arXiv: 2111.10614 [cs, eess].
[34] Guanghui Yue et al. “Boundary Constraint Network with Cross Layer Feature Integration for Polyp Segmentation”. In: IEEE Journal of Biomedical and Health Informatics 26.8 (Aug. 2022), pp. 4090 – 4099. issn: 2168 - 2194, 2168 - 2208. doi: 10.1109/JBHI.2022.3173948.
[35] Guanghui Yue et al. “Attention-Guided Pyramid Context Network for Polyp Segmentation in Colonoscopy Images”. In: IEEE Transactions on Instrumentation and Measurement 72 (2023), pp. 1 – 13. issn: 0018 - 9456, 1557 - 9662. doi: 10.1109/TIM.2023.3244219.
[36] Ruifei Zhang et al. Adaptive Context Selection for Polyp Segmentation. Jan. 11, 2023. arXiv: 2301.04799 [cs].
[37] Thomas N. Kipf and Max Welling. “Semi-Supervised Classification with Graph Convolutional Networks”. In: (Feb. 22, 2017). doi: 10.48550/ arXiv.1609.02907.
Downloads
Published
Conference Proceedings Volume
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.