Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Multi-Layer Dense Attention Decoder for Polyp Segmentation (2403.18180v1)

Published 27 Mar 2024 in cs.CV

Abstract: Detecting and segmenting polyps is crucial for expediting the diagnosis of colon cancer. This is a challenging task due to the large variations of polyps in color, texture, and lighting conditions, along with subtle differences between the polyp and its surrounding area. Recently, vision Transformers have shown robust abilities in modeling global context for polyp segmentation. However, they face two major limitations: the inability to learn local relations among multi-level layers and inadequate feature aggregation in the decoder. To address these issues, we propose a novel decoder architecture aimed at hierarchically aggregating locally enhanced multi-level dense features. Specifically, we introduce a novel module named Dense Attention Gate (DAG), which adaptively fuses all previous layers' features to establish local feature relations among all layers. Furthermore, we propose a novel nested decoder architecture that hierarchically aggregates decoder features, thereby enhancing semantic features. We incorporate our novel dense decoder with the PVT backbone network and conduct evaluations on five polyp segmentation datasets: Kvasir, CVC-300, CVC-ColonDB, CVC-ClinicDB, and ETIS. Our experiments and comparisons with nine competing segmentation models demonstrate that the proposed architecture achieves state-of-the-art performance and outperforms the previous models on four datasets. The source code is available at: https://github.com/krushi1992/Dense-Decoder.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (33)
  1. Polyp segmentation in colonoscopy images using fully convolutional network. In 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 69–72.
  2. WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians. Computerized medical imaging and graphics 43 (2015), 99–111.
  3. Fully convolutional neural networks for polyp segmentation in colonoscopy. In Medical Imaging 2017: Computer-Aided Diagnosis, Vol. 10134. SPIE, 101–107.
  4. Accumulated trivial attention matters in vision transformers on small datasets. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 3984–3992.
  5. Polyp-pvt: Polyp segmentation with pyramid vision transformers. arXiv preprint arXiv:2108.06932 (2021).
  6. Pranet: Parallel reverse attention network for polyp segmentation. In International conference on medical image computing and computer-assisted intervention. Springer, 263–273.
  7. Selective feature aggregation network with area-boundary constraints for polyp segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 302–310.
  8. SOSD-Net: Joint semantic object segmentation and depth estimation from monocular images. Neurocomputing 440 (2021), 251–263.
  9. Hardnet-mseg: A simple encoder-decoder polyp segmentation neural network that achieves over 0.9 mean dice and 86 fps. arXiv preprint arXiv:2101.07172 (2021).
  10. Kvasir-seg: A segmented polyp dataset. In International Conference on Multimedia Modeling. Springer, 451–462.
  11. Resunet++: An advanced architecture for medical image segmentation. In 2019 IEEE International Symposium on Multimedia (ISM). IEEE, 225–2255.
  12. Wireless capsule endoscopy: A new tool for cancer screening in the colon with deep-learning-based polyp recognition. Proc. IEEE 108, 1 (2019), 178–197.
  13. Colonoscopy polyp detection and classification: Dataset creation and comparative evaluations. Plos one 16, 8 (2021), e0255809.
  14. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision. 10012–10022.
  15. Omid Haji Maghsoudi. 2017. Superpixel based segmentation and classification of polyps in wireless capsule endoscopy. In 2017 IEEE Signal Processing in Medicine and Biology Symposium (SPMB). IEEE, 1–4.
  16. Automated polyp detection in colon capsule endoscopy. IEEE transactions on medical imaging 33, 7 (2014), 1488–1502.
  17. Cancer statistics, 2020: report from national cancer registry programme, India. JCO Global oncology 6 (2020), 1063–1075.
  18. Enhanced u-net: A feature enhancement network for polyp segmentation. In 2021 18th Conference on Robots and Vision (CRV). IEEE, 181–188.
  19. A comparative study on polyp classification using convolutional neural networks. PloS one 15, 7 (2020), e0236452.
  20. Fuzzynet: A fuzzy attention module for polyp segmentation. In NeurIPS’22 Workshop on All Things Attention: Bridging Different Perspectives on Attention.
  21. Basnet: Boundary-aware salient object detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 7479–7489.
  22. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention. Springer, 234–241.
  23. Toward embedded detection of polyps in wce images for early diagnosis of colorectal cancer. International journal of computer assisted radiology and surgery 9, 2 (2014), 283–293.
  24. Automated polyp detection in colonoscopy videos using shape and context information. IEEE transactions on medical imaging 35, 2 (2015), 630–644.
  25. A benchmark for endoluminal scene segmentation of colonoscopy images. Journal of healthcare engineering 2017 (2017).
  26. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In Proceedings of the IEEE/CVF international conference on computer vision. 568–578.
  27. PST-Net: Point Cloud Completion Network Based on Local Geometric Feature Reuse and Neighboring Recovery with Taylor Approximation. In 2023 International Joint Conference on Neural Networks (IJCNN). IEEE, 1–8.
  28. Shallow attention network for polyp segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 699–708.
  29. F33{}^{3}start_FLOATSUPERSCRIPT 3 end_FLOATSUPERSCRIPTNet: fusion, feedback and focus for salient object detection. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 12321–12328.
  30. Edge-aware multi-task network for integrating quantification segmentation and uncertainty prediction of liver tumor on multi-modality non-contrast MRI. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 652–661.
  31. Adaptive context selection for polyp segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 253–262.
  32. Transfuse: Fusing transformers and cnns for medical image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 14–24.
  33. Unet++: A nested u-net architecture for medical image segmentation. In Deep learning in medical image analysis and multimodal learning for clinical decision support. Springer, 3–11.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Krushi Patel (7 papers)
  2. Fengjun Li (13 papers)
  3. Guanghui Wang (179 papers)
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now