Detection and Segmentation of Early Gastric Cancer using Graph Learning Based Improved U-Net Architecture
Abstract
It is difficult to identify Early Gastric Cancer (EGC) through common gastroscopy because of its sharpness and low contrast with the mucous membrane. To enhance EGC detection and segmentation, a GLIU-NET is proposed, using a graph learning enhanced U-Net model, which adopts a bi-directional feature extraction and fusion module. It adopts a composite loss function to promote lesion segmentation. The experimental results demonstrate that the GLIU-NET performs better than conventional models. The model reaches a Dice of 0.89, IoU of 0.83, and F1-score of 0.88. The ablation study verifies the effectiveness of the graph spatial modelling and feature fusion. Analysis of the research results showed a marked improvement in segmentation accuracy and boundary accuracy with GLIU-NET. Medical professionals showed positive feedback about the lesion boundary clarity. This is a positive indication of the clinical practicability of the GLIU-NET for early gastric cancer detection.
Cite this article
Kumar, Alok, and Mahendran N.. "Detection and Segmentation of Early Gastric Cancer using Graph Learning Based Improved U-Net Architecture." Journal of Innovative Image Processing 8, no. 1 (2026): 295-316. doi: 10.36548/jiip.2026.1.016
Copy Citation
Kumar, A., & N., M. (2026). Detection and Segmentation of Early Gastric Cancer using Graph Learning Based Improved U-Net Architecture. Journal of Innovative Image Processing, 8(1), 295-316. https://doi.org/10.36548/jiip.2026.1.016
Copy Citation
Kumar, Alok, et al. "Detection and Segmentation of Early Gastric Cancer using Graph Learning Based Improved U-Net Architecture." Journal of Innovative Image Processing, vol. 8, no. 1, 2026, pp. 295-316. DOI: 10.36548/jiip.2026.1.016.
Copy Citation
Kumar A, N. M. Detection and Segmentation of Early Gastric Cancer using Graph Learning Based Improved U-Net Architecture. Journal of Innovative Image Processing. 2026;8(1):295-316. doi: 10.36548/jiip.2026.1.016
Copy Citation
A. Kumar, and M. N., "Detection and Segmentation of Early Gastric Cancer using Graph Learning Based Improved U-Net Architecture," Journal of Innovative Image Processing, vol. 8, no. 1, pp. 295-316, Mar. 2026, doi: 10.36548/jiip.2026.1.016.
Copy Citation
Kumar, A. and N., M. (2026) 'Detection and Segmentation of Early Gastric Cancer using Graph Learning Based Improved U-Net Architecture', Journal of Innovative Image Processing, vol. 8, no. 1, pp. 295-316. Available at: https://doi.org/10.36548/jiip.2026.1.016.
Copy Citation
@article{kumar2026,
author = {Alok Kumar and Mahendran N.},
title = {{Detection and Segmentation of Early Gastric Cancer using Graph Learning Based Improved U-Net Architecture}},
journal = {Journal of Innovative Image Processing},
volume = {8},
number = {1},
pages = {295-316},
year = {2026},
publisher = {IRO Journals},
doi = {10.36548/jiip.2026.1.016},
url = {https://doi.org/10.36548/jiip.2026.1.016}
}
Copy Citation
Keywords
Medical Image Segmentation
Early Gastric Cancer (EGC)
Gastroscopy
Graph Learning
Improved U-Net
Deep Learning
Feature Fusion
Lesion Detection
Computer-Aided Diagnosis (CAD)
Biomedical Image Analysis
References
- Sung, Hyuna, Jacques Ferlay, Rebecca L. Siegel, Mathieu Laversanne, Isabelle Soerjomataram, Ahmedin Jemal, and Freddie Bray. "Global Cancer Statistics 2020: GLOBOCAN estimates Of Incidence and Mortality Worldwide For 36 Cancers In 185 Countries." CA: a cancer journal for clinicians 71, no. 3 (2021): 209-249.
- Toupchi, M., and S. A. Abolghasempur. "Modify Improved Ant Colony for Fuzzy Clustering in Image Segmentation." International Academic Journal of Science and Engineering, 2 (4), 19 28 (2015).
- Litjens, Geert, Thijs Kooi, Babak Ehteshami Bejnordi, Arnaud Arindra Adiyoso Setio, Francesco Ciompi, Mohsen Ghafoorian, Jeroen Awm Van Der Laak, Bram Van Ginneken, and Clara I. Sánchez. "A survey on deep learning in medical image analysis." Medical image analysis 42 (2017): 60-88.
- Shyamala, B., Y. Vamsidhar, and S. H. Brahmananda. "An Ensemble Multi Fusion based U-Net with Short Learning Technique for Brain Tumor Classification." J. Wirel. Mob. Networks Ubiquitous Comput. Dependable Appl. 15, no. 4 (2024): 226-242.
- Gao, Hongyang, and Shuiwang Ji. "Graph U-Nets." In international conference on machine learning, PMLR, 2019, 2083-2092.
- Shibata, Tomoyuki, Atsushi Teramoto, Hyuga Yamada, Naoki Ohmiya, Kuniaki Saito, and Hiroshi Fujita. "Automated Detection and Segmentation of Early Gastric Cancer from Endoscopic Images Using Mask R-CNN." Applied Sciences 10, no. 11 (2020): 3842.
- Necula, Laura, Lilia Matei, Denisa Dragu, Ana I. Neagu, Cristina Mambet, Saviana Nedeianu, Coralia Bleotu, Carmen C. Diaconu, and Mihaela Chivu-Economescu. "Recent Advances in Gastric Cancer Early Diagnosis." World journal of gastroenterology 25, no. 17 (2019): 2029.
- Rani, SARITHA R., and R. Gunasundari. "Enhanced Transformer-Based Deep Kernel Fused Self Attention Model for Lung Nodule Segmentation and Classification." Archives for Technical Sciences 31, no. 2 (2024): 175-191.
- Zhou, Zongwei, Md Mahfuzur Rahman Siddiquee, Nima Tajbakhsh, and Jianming Liang. "Uet++: A Nested U-Net Architecture for Medical Image Segmentation." In International workshop on deep learning in medical image analysis, Cham: Springer International Publishing, 2018, 3-11.
- Esteva, Andre, Alexandre Robicquet, Bharath Ramsundar, Volodymyr Kuleshov, Mark DePristo, Katherine Chou, Claire Cui, Greg Corrado, Sebastian Thrun, and Jeff Dean. "A Guide to Deep Learning in Healthcare." Nature medicine 25, no. 1 (2019): 24-29.
- Ma, Haichao, Chao Xu, Chao Nie, Jubao Han, Yingjie Li, and Chuanxu Liu. "DBE-Net: Dual Boundary-Guided Attention Exploration Network for Polyp Segmentation." Diagnostics 13, no. 5 (2023): 896.
- Ronneberger, Olaf, Philipp Fischer, and Thomas Brox. "U-net: Convolutional Networks for Biomedical Image Segmentation." In International Conference on Medical image computing and computer-assisted intervention, Cham: Springer international publishing, 2015, 234-241.
- Lafraxo, Samira, Meryem Souaidi, Mohamed El Ansari, and Lahcen Koutti. "Semantic Segmentation of Digestive Abnormalities from Wce Images by Using Attresu-Net Architecture." Life 13, no. 3 (2023): 719.
- Hirasawa, Toshiaki, Kazuharu Aoyama, Tetsuya Tanimoto, Soichiro Ishihara, Satoki Shichijo, Tsuyoshi Ozawa, Tatsuya Ohnishi et al. "Application of Artificial Intelligence Using a Convolutional Neural Network for Detecting Gastric Cancer in Endoscopic Images." Gastric cancer 21, no. 4 (2018): 653-660.
- Setio, Arnaud Arindra Adiyoso, Francesco Ciompi, Geert Litjens, Paul Gerke, Colin Jacobs, Sarah J. Van Riel, Mathilde Marie Winkler Wille, Matiullah Naqibullah, Clara I. Sánchez, and Bram Van Ginneken. "Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks." IEEE transactions on medical imaging 35, no. 5 (2016): 1160-1169.
