Effect of noise on the robustness of MobileNetV2+U-Net semantic segmentation model for MRI images

Authors

  • Gunawan Nur Cahyo  Department of Physics, Faculty of Sciences and Mathematics, Diponegoro University, Jl. Prof. Soedarto SH, Tembalang, Semarang 50275, Central Java, Indonesia
  • Choirul Anam  Department of Physics, Faculty of Sciences and Mathematics, Diponegoro University, Jl. Prof. Soedarto SH, Tembalang, Semarang 50275, Central Java, Indonesia
  • Kusworo Adi  Department of Physics, Faculty of Sciences and Mathematics, Diponegoro University, Jl. Prof. Soedarto SH, Tembalang, Semarang 50275, Central Java, Indonesia

DOI:

https://doi.org//10.32628/IJSRST52310631

Keywords:

Semantic Segmentation, MobileNetV2+U-Net, U-Net, Noise

Abstract

This study aims to evaluate effect of noise on the robustness of semantic segmentation models for Magnetic Resonance Imaging (MRI) head images with tumor. We implemented the MobileNetV2+U-Net architectural model. We tested the segmentation model with Gaussian and Poisson noises in various levels. The addition of noise was performed five iterations with a variance of 0.01 each iteration. We carried out evaluations by examining the segmentation results, loss function values, accuracy and dice score. Based on the results, increase in noise affects model performance. Evaluation using loss function shows that graph instability is influenced by the noise level. The accuracy results on the highest and lowest validation data were 99.47% and 98.99% for Gaussian noise and 99.64% and 99.5% for Poisson noise. Apart from that, the highest and lowest dice scores were 82.80% and 69.18% for Gaussian noise and 87.83% and 83.10% for Poisson noise. We recommend training the segmentation model using noisy data so that the model can adapt to noisy images.

References

  1. Z. Luo, W. Yang, Y. Yuan, R. Gou, and X. Li, “Semantic segmentation of agricultural images: A survey,” Inf. Process. Agric., pp. 1–15, 2023, doi: 10.1016/j.inpa.2023.02.001.
  2. M. Thoma, “A Survey of Semantic Segmentation,” pp. 1–16, 2016, [Online]. Available: http://arxiv.org/abs/1602.06541
  3. A. Mueed, H. Ghulam, and M. Bhat, “A survey on instance segmentation : state of the art,” Int. J. Multimed. Inf. Retr., vol. 9, no. 3, pp. 171–189, 2020, doi: 10.1007/s13735-020-00195-x.
  4. J. Long, E. Shelhamer, and T. Darrell, “Fully Convolutional Networks for Semantic Segmentation,” Nov. 2014, [Online]. Available: http://arxiv.org/abs/1411.4038
  5. O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” May 2015, [Online]. Available: http://arxiv.org/abs/1505.04597
  6. V. Badrinarayanan, A. Kendall, R. Cipolla, and S. Member, “SegNet : A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation,” November 2015, [Online]. Available: https://arxiv.org/abs/1511.00561.
  7. H. Huang, L. Lin, R. Tong, H. Hu, Q. Zhang, and Y. Iwamoto, “UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation,” April 2020, [Online]. Available: https://arxiv.org/abs/2004.08790.
  8. R. Wang, S. Chen, C. Ji, J. Fan, and Y. Li, “Boundary-aware context neural network for medical image segmentation,” Med. Image Anal., vol. 78, no. 8, pp. 1–10, 2022, doi: 10.1016/j.media.2022.102395.
  9. Z. Lu, Z. Fu, T. Xiang, P. Han, L. Wang, and X. Gao, “Learning from weak and noisy labels for semantic segmentation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 3, pp. 486–500, 2017, doi: 10.1109/TPAMI.2016.2552172.
  10. G. Cheng, H. Ji, and Y. Tian, “Walking on two legs: Learning image segmentation with noisy labels,” Proc. 36th Conf. Uncertain. Artif. Intell. UAI 2020, vol. 124, pp. 330–339, 2020.
  11. R. Yi, Y. Huang, Q. Guan, M. Pu, and R. Zhang, “Learning from Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentation,” IEEE Transactions on Image Processing, vol. 31, pp. 623–635, Jan. 2022, doi: 10.1109/tip.2021.3134142.
  12. M. Nickparvar, “Brain Tumor MRI Dataset,” 2021. https://www.kaggle.com/datasets/masoudnickparvar/brain-tumor-mri-dataset
  13. J. Cheng, “Brain Tumor Dataset,” 2016. https://figshare.com/articles/dataset/brain_tumor_dataset/1512427?file=7953679
  14. K. Wada, “Labelme,” 2022. https://github.com/wkentaro/labelme
  15. H. Bi et al., “BPAT-UNet: Boundary Preserving Assembled Transformer UNet for Ultrasound Thyroid Nodule Segmentation,” Comput. Methods Programs Biomed., p. 107614, 2023, doi: 10.1016/j.cmpb.2023.107614.
  16. Z. Zhou, M. M. Rahman Siddiquee, N. Tajbakhsh, and J. Liang, “Unet++: A nested u-net architecture for medical image segmentation,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 11045 LNCS, pp. 3–11, 2018, doi: 10.1007/978-3-030-00889-5_1.
  17. D. Lopes, L. Coelho, and M. F. Silva, “Development of a Collaborative Robotic Platform for Autonomous Auscultation,” Appl. Sci., vol. 13, no. 3, 2023, doi: 10.3390/app13031604.
  18. J. Jing, Z. Wang, M. Rätsch, and H. Zhang, “Mobile-Unet: An efficient convolutional neural network for fabric defect detection,” Text. Res. J., vol. 92, no. 1–2, pp. 30–42, 2022, doi: 10.1177/0040517520928604.
  19. Y. Lau, W. Sim, K. Chew, Y. Ng, Z. Arabee, and A. Salam, “Understanding how noise affects the accuracy of CNN image classification,” J. Appl. Technol. Innov., vol. 5, no. 2, pp. 2600–7304, 2021.
  20. T. H. Pranto, A. A. Noman, A. Noor, U. H. Deepty, and R. M. Rahman, “Effect of Label Noise on Multi-Class Semantic Segmentation: A Case Study on Bangladesh Marine Region,” Appl. Artif. Intell., vol. 36, no. 1, 2022, doi: 10.1080/08839514.2022.2039348.
  21. H. Jang, D. McCormack, and F. Tong, “Noise-trained deep neural networks effectively predict human vision and its neural responses to challenging images,” PLoS Biol., vol. 19, no. 12, pp. 1–27, 2021, doi: 10.1371/journal.pbio.3001418.
  22. A. Mortazi, N. Khosravan, D. A. Torigian, S. Kurugol, and U. Bağcı, “Weakly supervised segmentation by a deep geodesic prior,” in Lecture Notes in Computer Science, 2019, pp. 238–246. doi: 10.1007/978-3-030-32692-0_28..
  23. A. Kascenas, N. Pugeault, and A. Q. O’neil, “Denoising Autoencoders for Unsupervised Anomaly Detection in Brain MRI,” Proc. Mach. Learn. Res. Rev., vol. 172, pp. 1–12, 2022.

International Journal of Scientific Research in Science and Technology

Downloads

Published

2023-12-30

Issue

Volume 10, Issue 6, November-December-2023

Section

Research Articles

License

Copyright (c) IJSRST

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Gunawan Nur Cahyo, Choirul Anam, Kusworo Adi, " Effect of noise on the robustness of MobileNetV2+U-Net semantic segmentation model for MRI images, International Journal of Scientific Research in Science and Technology(IJSRST), Online ISSN : 2395-602X, Print ISSN : 2395-6011, Volume 10, Issue 6, pp.209-217, November-December-2023. Available at doi : https://doi.org/10.32628/IJSRST52310631