Improving Accuracy and Efficiency of Medical Image Segmentation Using One-Point-Five U-Net Architecture with Integrated Attention and Multi-Scale Mechanisms

Muhammad Anang  Fathur Rohman; Heri Prasetyo; Ery Permana  Yudha; Chih-Hsien  Hsia

doi:10.35882/jeeemi.v7i3.949

Muhammad Anang Fathur Rohman Department of Informatics, Universitas Sebelas Maret, Surakarta, Indonesia https://orcid.org/0009-0007-8511-3002
Heri Prasetyo Department of Informatics, Universitas Sebelas Maret, Surakarta, Indonesia https://orcid.org/0000-0002-1257-4832
Ery Permana Yudha Department of Informatics, Universitas Sebelas Maret, Surakarta, Indonesia https://orcid.org/0009-0007-5509-8585
Chih-Hsien Hsia Department of Computer Science and Information Engineering, National Ilan University, Yilan, Taiwan https://orcid.org/0000-0003-2665-0821

DOI: https://doi.org/10.35882/jeeemi.v7i3.949

Keywords: Medical image segmentation, Deep Learning, One-Point-Five U-net, Efficient Model

Abstract

Medical image segmentation is essential for supporting computer-aided diagnosis (CAD) systems by enabling accurate identification of anatomical and pathological structures across various imaging modalities. However, automated medical image segmentation remains challenging due to low image contrast, significant anatomical variability, and the need for computational efficiency in clinical applications. Furthermore, the scarcity of annotated medical images due to high labelling costs and the requirement of expert knowledge further complicates the development of robust segmentation models. This study aims to address these challenges by proposing One-Point-Five U-Net, a novel deep learning architecture designed to improve segmentation accuracy while maintaining computational efficiency. The main contribution of this work lies in the integration of multiple advanced mechanisms into a compact architecture: ghost modules, Multi-scale Residual Attention (MRA), Enhanced Parallel Attention (EPA) in skip connections, the Convolutional Block Attention Module (CBAM), and Multi-scale Depthwise Convolution (MSDC) in the decoder. The proposed method was trained and evaluated on four public datasets: CVC-ClinicDB, Kvasir-SEG, BUSI, and ISIC2018. One-Point-Five U-Net achieved sensitivity, specificity, accuracy, DSC, and IoU of of 94.89%, 99.63%, 99.23%, 95.41%, and 91.27% on CVC-ClinicDB; 91.11%, 98.60%, 97.33%, 90.93%, and 83.84% on Kvasir-SEG; 85.35%, 98.65%, 96.81%, 87.02%, and 78.18% on BUSI; and 87.67%, 98.11%, 93.68%, 89.27%, and 83.06% on ISIC2018. These results outperform several state-of-the-art segmentation models. In conclusion, One-Point-Five U-Net demonstrates superior segmentation accuracy with only 626,755 parameters and 28.23 GFLOPs, making it a highly efficient and effective model for clinical implementation in medical image analysis.

Downloads

Download data is not yet available.

References

J. Zhang et al., “Advances in attention mechanisms for medical image segmentation,” Comput. Sci. Rev., vol. 56, p. 100721, May 2025, doi: 10.1016/j.cosrev.2024.100721.

X. Shu, J. Wang, A. Zhang, J. Shi, and X.-J. Wu, “CSCA U-Net: A channel and space compound attention CNN for medical image segmentation,” Artif. Intell. Med., vol. 150, p. 102800, Apr. 2024, doi: 10.1016/j.artmed.2024.102800.

M. E. Rayed, S. M. S. Islam, S. I. Niha, J. R. Jim, M. M. Kabir, and M. F. Mridha, “Deep learning for medical image segmentation: State-of-the-art advancements and challenges,” Informatics Med. Unlocked, vol. 47, p. 101504, 2024, doi: 10.1016/j.imu.2024.101504.

R. Wang, T. Lei, R. Cui, B. Zhang, H. Meng, and A. K. Nandi, “Medical image segmentation using deep learning: A survey,” IET Image Process., vol. 16, no. 5, pp. 1243–1267, Apr. 2022, doi: 10.1049/ipr2.12419.

X. Ding, K. Qian, Q. Zhang, X. Jiang, and L. Dong, “Dual-channel compression mapping network with fused attention mechanism for medical image segmentation,” Sci. Rep., vol. 15, no. 1, p. 8906, Mar. 2025, doi: 10.1038/s41598-025-93494-4.

H. Prasetyo, M. A. F. Rohman, A. W. H. Prayuda, and J.-M. Guo, “Enhancing Polyp Segmentation Efficiency Using Pixel Channel Attention HalfU-Net,” in 2024 IEEE 10th Information Technology International Seminar (ITIS), IEEE, Nov. 2024, pp. 381–386. doi: 10.1109/ITIS64716.2024.10845590.

Y. Zhang, Q. Liao, L. Ding, and J. Zhang, “Bridging 2D and 3D segmentation networks for computation-efficient volumetric medical image segmentation: An empirical study of 2.5D solutions,” Comput. Med. Imaging Graph., vol. 99, p. 102088, Jul. 2022, doi: 10.1016/j.compmedimag.2022.102088.

X. Wu, S. Huang, X. Shu, C. Hu, and X.-J. Wu, “MPFC-Net: A multi-perspective feature compensation network for medical image segmentation,” Expert Syst. Appl., vol. 248, p. 123430, Aug. 2024, doi: 10.1016/j.eswa.2024.123430.

J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation,” in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Jun. 2015, pp. 3431–3440. doi: 10.1109/CVPR.2015.7298965.

T. Zhang, Y. Liu, Y. Fan, and M. Lu, “Improvement of park drivable area segmentation method based on STDCSeg network,” Discov. Appl. Sci., vol. 7, no. 4, p. 297, Apr. 2025, doi: 10.1007/s42452-025-06767-y.

O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” 2015, pp. 234–241. doi: 10.1007/978-3-319-24574-4_28.

H. Lu, Y. She, J. Tie, and S. Xu, “Half-UNet: A Simplified U-Net Architecture for Medical Image Segmentation,” Front. Neuroinform., vol. 16, Jun. 2022, doi: 10.3389/fninf.2022.911679.

O. Oktay et al., “Attention U-Net: Learning Where to Look for the Pancreas,” Apr. 2018, doi: https://doi.org/10.48550/arXiv.1804.03999.

M. A. F. Rohman, H. M. Akbar, A. D. A. Firdaus, and H. Prasetyo, “AGU-NET:Attention Ghost U-NetUntuk Segmentasi Penyakit Polip Berbasis Citra Biomedis,” Bul. PAGELARAN Mhs. Nas. Bid. Teknol. Inf. DAN Komun., vol. 1, no. 1, pp. 44–49, 2023.

X. Qin, Z. Wang, Y. Bai, X. Xie, and H. Jia, “FFA-Net: Feature Fusion Attention Network for Single Image Dehazing,” Proc. AAAI Conf. Artif. Intell., vol. 34, no. 07, pp. 11908–11915, Apr. 2020, doi: 10.1609/aaai.v34i07.6865.

L. Lu, Q. Xiong, B. Xu, and D. Chu, “MixDehazeNet: Mix Structure Block For Image Dehazing Network,” in 2024 International Joint Conference on Neural Networks (IJCNN), IEEE, Jun. 2024, pp. 1–10. doi: 10.1109/IJCNN60899.2024.10651326.

Y. Dai, C. Li, X. Su, H. Liu, and J. Li, “Multi-Scale Depthwise Separable Convolution for Semantic Segmentation in Street–Road Scenes,” Remote Sens., vol. 15, no. 10, p. 2649, May 2023, doi: 10.3390/rs15102649.

X. Shu, X. Li, X. Zhang, C. Shao, X. Yan, and S. Huang, “MRAU-net: Multi-scale residual attention U-shaped network for medical image segmentation,” Comput. Electr. Eng., vol. 118, p. 109479, Sep. 2024, doi: 10.1016/j.compeleceng.2024.109479.

J. Bernal, F. J. Sánchez, G. Fernández-Esparrach, D. Gil, C. Rodríguez, and F. Vilariño, “WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians,” Comput. Med. Imaging Graph., vol. 43, pp. 99–111, Jul. 2015, doi: 10.1016/j.compmedimag.2015.02.007.

D. Jha et al., “Kvasir-SEG: A Segmented Polyp Dataset,” 2020, pp. 451–462. doi: 10.1007/978-3-030-37734-2_37.

W. Al-Dhabyani, M. Gomaa, H. Khaled, and A. Fahmy, “Dataset of breast ultrasound images,” Data Br., vol. 28, p. 104863, Feb. 2020, doi: 10.1016/j.dib.2019.104863.

N. Codella et al., “Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC),” Feb. 2019, [Online]. Available: http://arxiv.org/abs/1902.03368

M. A. Fathur Rohman, H. Prasetyo, H. M. Akbar, and A. D. Afan Firdaus, “ACMU-Net: An Efficient Architecture Based on ConvMixer and Attention Mechanism for Colorectal Polyp Segmentation,” in 2024 IEEE International Conference on Smart Mechatronics (ICSMech), IEEE, Nov. 2024, pp. 279–284. doi: 10.1109/ICSMech62936.2024.10812309.

K. Han, Y. Wang, Q. Tian, J. Guo, C. Xu, and C. Xu, “GhostNet: More Features From Cheap Operations,” in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Jun. 2020, pp. 1577–1586. doi: 10.1109/CVPR42600.2020.00165.

A. G. Roy, N. Navab, and C. Wachinger, “Concurrent Spatial and Channel ‘Squeeze & Excitation’ in Fully Convolutional Networks,” 2018, pp. 421–429. doi: 10.1007/978-3-030-00928-1_48.

S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon, “CBAM: Convolutional Block Attention Module,” 2018, pp. 3–19. doi: 10.1007/978-3-030-01234-2_1.

R. Andonie, “Hyperparameter optimization in learning systems,” J. Membr. Comput., vol. 1, no. 4, pp. 279–291, Dec. 2019, doi: 10.1007/s41965-019-00023-0.

Z. Zhou, M. M. R. Siddiquee, N. Tajbakhsh, and J. Liang, “UNet++: A Nested U-Net Architecture for Medical Image Segmentation,” Jul. 2018, [Online]. Available: http://arxiv.org/abs/1807.10165

X. Xiao, S. Lian, Z. Luo, and S. Li, “Weighted Res-UNet for High-Quality Retina Vessel Segmentation,” in 2018 9th International Conference on Information Technology in Medicine and Education (ITME), IEEE, Oct. 2018, pp. 327–331. doi: 10.1109/ITME.2018.00080.

H. Prasetyo, R. B. Ashidiqy, and U. Salamah, “CMAUNeXt: An Efficient Neural Network Based on Large Kernel and Multi-Dimensional Attention Module for Breast Tumor Segmentation,” in 2024 IEEE International Conference on Smart Mechatronics (ICSMech), IEEE, Nov. 2024, pp. 89–94. doi: 10.1109/ICSMech62936.2024.10812276.