IMPROVED ATTENTION MOBILEU-NET UNTUK SEGMENTASI CITRA MEDIS POLIP

Article Sidebar

PDF
Published Aug 1, 2023

Main Article Content

Abid Ammar Mahdy Abrar Dwi Fairuz Nadhif Muhammad Anang Fathur Rohman

Abstract

The development of deep learning in computer vision has led many researchers to propose methods that not only improve the performance of previous methods but also increase the memory efficiency of the models. One interesting problem is the segmentation of medical polyp images, which has been previously addressed with high-peformance methods but with large numbers of parameters and relatively low memory efficiency. This paper proposes the Improved Attention MobileU-Net method for medical polyp image segementation with significantly fewer parameters than previous methods, resulting in higher memory efficiency. This method is constructed with Sandglass Block and uses an attention framework to achieve performance comparable methods. Test result on the CVC-ClinicDB and Kvasir-Seg datasets show that the proposed method has a small number of parameters, with only 574,579 parameters. The proposed method achieved F1-Score performance of 92.36% and Intersection-over-Union (IoU) value of 86.50% for the CVC-ClinicDB dataset. For the Kvasir-Seg dataset, the proposed method showed an F1-Score performance of 86.59% and IoU of 78.87%. The Improved Attention MobileU-Net outperformed several previous methods, including U-Net, ResU-Net, U-Net++, SFA, and ResU-Net++, with a significantly lower number of parameters.

Article Details

Issue
Vol 7 No 2 (2023): Jurnal Ilmiah Penalaran dan Penelitian Mahasiswa
Section
Articles

References

Al-Masni, M.A. and Kim, D.H., 2021. CMM-Net: Contextual multi-scale multilevel network for efficient biomedical image segmentation. Scientific reports, 11(1), pp.1-18.

Duta, I.C., Liu, L., Zhu, F. and Shao, L., 2021, January. Improved residual networks for image and video recognition. In 2020 25th International Conference on Pattern Recognition (ICPR) (pp. 9415-9422). IEEE.

Fang, Y., Chen, C., Yuan, Y. and Tong, K.Y., 2019. Selective feature aggregation network with area-boundary constraints for polyp segmentation. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part I 22 (pp. 302-310). Springer International Publishing.

Hu, J., Shen, L. and Sun, G., 2018. Squeeze-and-excitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7132-7141).

Ibtehaz, N. and Rahman, M.S., 2020. MultiResUNet: Rethinking the U-Net architecture for multimodal biomedical image segmentation. Neural networks, 121, pp.74-87.

Jha, D., Smedsrud, P.H., Riegler, M.A., Johansen, D., De Lange, T., Halvorsen, P. and Johansen, H.D., 2019, December. Resunet++: An advanced architecture for medical image segmentation. In 2019 IEEE International Symposium on Multimedia (ISM) (pp. 225-2255). IEEE.

Liu, L., Cheng, J., Quan, Q., Wu, F.X., Wang, Y.P. and Wang, J., 2020. A survey on U-shaped networks in medical image segmentations. Neurocomputing, 409, pp.244-258.

Long, J., Shelhamer, E. and Darrell, T., 2015. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3431-3440).

Lou, A., Guan, S. and Loew, M., 2023. Cfpnet-m: A light-weight encoder-decoder based network for multimodal biomedical image real-time segmentation. Computers in Biology and Medicine, 154, p.106579.

Mohapatra, S., Swarnkar, T. and Das, J., 2021. Deep convolutional neural network in medical image processing. In Handbook of deep learning in biomedical engineering (pp. 25-60). Academic Press.

Nishio, M., Fujimoto, K. and Togashi, K., 2021. Lung segmentation on chest Xray images in patients with severe abnormal findings using deep learning. International Journal of Imaging Systems and Technology, 31(2), pp.10021008.

Ronneberger, O., Fischer, P. and Brox, T., 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18 (pp. 234-241). Springer International Publishing.

Sandler, M., Howard, A., Zhu, M., Zhmoginov, A. and Chen, L.C., 2018. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4510-4520).

Stoyanov, D., Taylor, Z., Carneiro, G., Syeda-Mahmood, T., Martel, A., MaierHein, L., Tavares, J.M.R., Bradley, A., Papa, J.P., Belagiannis, V. and Nascimento, J.C. eds., 2018. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings (Vol. 11045). Springer.

Wang, D. and Liu, Y., 2021. An Improved Neural Network Based on UNet for Surface Defect Segmentation. In 3D Imaging Technologies— Multidimensional Signal Processing and Deep Learning: Methods, Algorithms and Applications, Volume 2 (pp. 27-33). Springer Singapore.

Zeng, Z., Xie, W., Zhang, Y. and Lu, Y., 2019. RIC-Unet: An improved neural network based on Unet for nuclei segmentation in histology images. Ieee Access, 7, pp.21420-21428.

Zhang, Y., He, M., Chen, Z., Hu, K., Li, X. and Gao, X., 2022. Bridge-Net: Context-involved U-net with patch-based loss weight mapping for retinal blood vessel segmentation. Expert Systems with Applications, 195, p.116526.

Zhang, Z., Liu, Q. and Wang, Y., 2018. Road extraction by deep residual u-net. IEEE Geoscience and Remote Sensing Letters, 15(5), pp.749-753.

Zhou, D., Hou, Q., Chen, Y., Feng, J. and Yan, S., 2020. Rethinking bottleneck structure for efficient mobile network design. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part III 16 (pp. 680-697). Springer International Publishing.

Zhou, Z., Rahman Siddiquee, M.M., Tajbakhsh, N. and Liang, J., 2018. Unet++: A nested u-net architecture for medical image segmentation. In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4 (pp. 3-11). Springer International Publishing.