Review on the Application and Optimization of Unsupervised Edge Generation in Polyp Segmentation

Authors

  • Lufei Zhu
  • Min Jiang
  • Lixia He
  • Botao Liu

DOI:

https://doi.org/10.54097/kxf0rk79

Keywords:

Unsupervised Learning; Edge Ground Truth Generation; Deep Machine Learning; Computer-Aided Diagnosis and Treatment; Medical Image Analysis.

Abstract

Colorectal Cancer (CRC) is a malignant tumor arising from glandular epithelium, and it ranks among the malignancies with the highest incidence and mortality rates worldwide. Colonoscopy serves as a reliable method for the detection and resection of colorectal polyps, which are precancerous lesions. However, colorectal polyps are associated with high rates of missed diagnosis and misdiagnosis, posing a significant challenge to clinical diagnosis. Computer algorithms and models based on deep learning are expected to play a crucial role in polyp diagnosis and segmentation, as well as in assisting physicians to automatically and accurately diagnose lesions, thereby reducing the rates of missed diagnosis and misdiagnosis. Nevertheless, these models require hundreds or thousands of standardized images for training. Medical image annotation is not only costly but also subject to significant subjective variability. Particularly for segmentation tasks, the useful information at image edges often suffers from inaccuracies or ambiguity. In recent years, as an emerging medical auxiliary technology, unsupervised edge ground truth generation technology automatically extracts edge information from existing images via algorithms. This technology avoids cumbersome and inconsistent manual edge annotation, thereby providing a more accurate tool for medical treatment.

References

[1] Sung, H., et al. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA: A Cancer Journal for Clinicians, 2021.

[2] Leufkens, A. M., et al. Factors influencing the miss rate of polyps in a back-to-back colonoscopy study. Endoscopy, 2012.

[3] Wang, P., et al. Development and validation of a deep-learning system for polyp detection during colonoscopy. Nature Biomedical Engineering, 2020.

[4] Ronneberger, O., Fischer, P., & Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. MICCAI, 2015.

[5] Zhou, Z., et al. UNet++: A Nested U-Net Architecture for Medical Image Segmentation. IEEE TMI, 2018.

[6] Jha, D., et al. ResUNet++: An Advanced Architecture for Medical Image Segmentation. ISM, 2019.

[7] Fan, D. P., et al. PraNet: Parallel Reverse Attention Network for Polyp Segmentation. MICCAI, 2020.

[8] Xu, J., et al. TGA-Net: Token-Guided Attention Network for Polyp Segmentation. MICCAI, 2021.

[9] Tajbakhsh, N., et al. Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation. Medical Image Analysis, 2020.

[10] Bideau, P., & Eriksson, A. (2019). The Best of Both Worlds: Combining Data-Driven and Model-Based Edge Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[11] Fortun, D., Bouthemy, P., & Kervrann, C. (2015). Optical Flow Modeling and Computation: A Survey. Computer Vision and Image Understanding, 134, 1-21.

[12] Xie, S., & Tu, Z. (2015). Holistically-Nested Edge Detection. In Proceedings of the IEEE International Conference on Computer Vision (ICCV).

[13] Luo, Z., Mishra, B., Achkar, A., Eichel, J., Li, S., & Jodoin, P. M. (2021). Non-Local Deep Features for Salient Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14] Szeliski, R. Computer Vision: Algorithms and Applications. Springer, 2010

[15] Gonzalez,R. C.,& Woods, R. E. (2018).Digital Image Processing (4th ed.).Pearson. p. 182.

[16] Canny, J. A Computational Approach to Edge Detection. IEEE TPAMI, 1986.

[17] Wei, J., et al. Shallow Attention Network for Polyp Segmentation. MICCAI, 2021.

[18] Canny, J. (1986). A Computational Approach to Edge Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, *PAMI-8*(6), 679–698.

[19] Szelski, R. (2010). Computer Vision: Algorithms and Applications. Springer Science & Business Media.

[20] Xie, S., & Tu, Z. Holistically-Nested Edge Detection. ICCV, 2015.

[21] Liu, Y., et al. Richer Convolutional Features for Edge Detection. IEEE TPAMI, 2019.

[22] Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative Adversarial Nets. In Advances in Neural Information Processing Systems (Vol. 27).

[23] Zhu, J., Park, T., Isola, P., & Efros, A. A. (2017). Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. In Proceedings of the IEEE International Conference on Computer Vision (pp. 2223-2232).

[24] Murugesan, B., et al. PGAN: A Progressive Generative Adversarial Network for Medical Image Segmentation. Medical Image Analysis, 2021.

[25] Takikawa, T., Acuna, D., Jampani, V., & Fidler, S. (2019). Gated-SCNN: Gated Shape CNNs for Semantic Segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 5229-5238).

[26] Yu, Z., Feng, C., Liu, M. Y., & Ramalingam, S. (2017). CASENet: Deep Category-Aware Semantic Edge Detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 5964-5973).

[27] Woo, S., Park, J., Lee, J. Y., & Kweon, I. S. (2018). CBAM: Convolutional Block Attention Module. In Proceedings of the European Conference on Computer Vision (pp. 3-19).

[28] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is All You Need. In Advances in Neural Information Processing Systems (Vol. 30).

[29] Lin, T. Y., Dollár, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature Pyramid Networks for Object Detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2117-2125).

[30] Deng, R., Shen, C., Liu, S., Wang, H., & Liu, X. (2018). Learning to predict crisp boundaries. In Proceedings of the European Conference on Computer Vision (pp. 570-586).

[31] Bertasius, G., Shi, J., & Torresani, L. (2015). DeepEdge: A multi-scale bifurcated deep network for top-down contour detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 4380-4389).

[32] Northcutt, C. G., Jiang, L., & Chuang, I. L. (2021). Confident learning: Estimating uncertainty in dataset labels. Journal of Artificial Intelligence Research, 70, 1373-1411.

[33] He, T., Zhang, Z., Zhang, H., Zhang, Z., Xie, J., & Li, M. (2019). Bag of tricks for image classification with convolutional neural networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 558-567).

[34] Radosavovic, I., Kosaraju, R. P., Girshick, R., He, K., & Dollár, P. (2020). Designing network design spaces. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 10428-10436).

[35] Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning (pp. 6105-6114). PMLR.

[36] Howard, A., Sandler, M., Chu, G., Chen, L. C., Chen, B., Tan, M., ... & Adam, H. (2019). Searching for mobilenetv3. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 1314-1324).

[37] Wang, Y., Zhang, J., Kan, M., Shan, S., & Chen, X. (2020). Self-supervised scale-recurrent network for crowd counting. IEEE Transactions on Image Processing, 29, 8151-8163

[38] Hospedales, T., Antoniou, A., Micaelli, P., & Storkey, A. (2021). Meta-learning in neural networks: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(9), 5149-5169.

[39] Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., ... & Zhou, Y. (2021). TransUNet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306.

[40] Wolleb, J., Sandkühler, R., Bieder, F., Valmaggia, P., & Cattin, P. C. (2022). Diffusion Models for Implicit Image Segmentation Ensembles. In International Conference on Medical Imaging with Deep Learning (pp. 1336-1348).

Downloads

Published

21-01-2026

Issue

Section

Articles

How to Cite

Zhu, L., Jiang, M., He, L., & Liu, B. (2026). Review on the Application and Optimization of Unsupervised Edge Generation in Polyp Segmentation. Mathematical Modeling and Algorithm Application, 8(1), 27-31. https://doi.org/10.54097/kxf0rk79