Abstract
Gastrointestinal (GI) cancer is a fatal malignancy that affects the organs of the GI tract. The rising prevalence of GI cancer has recently influenced the health of millions of people. To treat GI cancer, radiation oncologists must carefully focus X-rays on tumors while avoiding other unaffected organs in the GI tract. This research proposes a novel approach to segment healthy organs within the GI tract from magnetic resonance imaging (MRI) scans using a multi-level attention DeepLab V3 + model. The proposed model aims to enhance segmentation performance by incorporating state-of-the-art approaches, such as atrous convolutions and EfficientNet B0 as an encoder, by leveraging hierarchical information present in the data. Here, the attention mechanism is applied at multiple levels of features, i.e., low, medium, and high, to capture and leverage hierarchical information present in the data. At the same time, EfficientNet B0 extracts deep and meaningful features from input images, providing a robust representation of GI tract structures. Hierarchical feature fusion combines local and global contextual information, resulting in more accurate segmentation with fine-grained details. The model is implemented using the UW-Madison dataset, comprising MRI scans from 85 patients with gastrointestinal cancer. To optimize the model, it has been simulated with different parameters, including optimizers, the number of epochs, and cross-validation folds. The model has achieved performance metrics such as a model loss of 0.0044, a dice coefficient of 0.9378, and an Intersection over Union (IoU) of 0.921.
Data availability
The dataset used in this study, the “UW-Madison GI Tract Image Segmentation” dataset, is publicly available on Kaggle. It can be accessed at https://www.kaggle.com/competitions/uw-madison-gi-tract-image-segmentation/data.
Abbreviations
- GI:
-
Gastrointestinal
- CNN:
-
Convolutional neural network
- ASPP:
-
Atrous spatial pyramid pooling
- RLE:
-
Run-length encoding
- MBConv:
-
Mobile inverted bottleneck convolution
- ReLU:
-
Rectified linear unit
- IoU:
-
Intersection over Union
- Adam:
-
Adaptive moment estimation
- SGD:
-
Stochastic gradient descent
- CBAM:
-
Convolutional block attention module
- PSE:
-
Permute squeeze-and-excitation
- SE:
-
Squeeze-and-excitation
- MRI:
-
Magnetic resonance imaging
References
Zhou, S. et al. (ed, K.) A review of deep learning in medical imaging: imaging traits, technology trends, case studies with progress highlights, and future promises. Proc. IEEE Inst. Electr. Electron. Eng. 109 820–838 (2021).
Ozdemir, B., Aslan, E. & Pacal, I. Attention Enhanced InceptionNeXt Based Hybrid Deep Learning Model for Lung Cancer Detection (IEEE Access, 2025).
Pacal, I., Ozdemir, B., Zeynalov, J., Gasimov, H. & Pacal, N. A novel CNN-ViT-based deep learning model for early skin cancer diagnosis. Biomed. Signal. Process. Control. 104, 107627 (2025).
Ozdemir, B. & Pacal, I. A robust deep learning framework for multiclass skin cancer classification. Sci. Rep. 15, 4938 (2025).
Ozdemir, B. & Pacal, I. An innovative deep learning framework for skin cancer detection employing ConvNeXtV2 and focal self-attention mechanisms. Results Eng. 25, 103692 (2025).
Yi, S. et al. IDC-Net: breast cancer classification network based on BI-RADS 4. Pattern Recognit. 150, 110323 (2024).
Bayram, B., Kunduracioglu, I., Ince, S. & Pacal, I. A systematic review of deep learning in MRI-based cerebral vascular occlusion-based brain diseases. Neuroscience 568, 76–94 (2025).
İnce, S., Kunduracioglu, I., Bayram, B. & Pacal, I. U-Net-based models for precise brain stroke segmentation. Chaos Theory Appl. 7, 50–60 (2025).
Heavey, S. F., Roeland, E. J., Tipps, A. M. P., Datnow, B. & Sicklick, J. K. Rapidly progressive subcutaneous metastases from gallbladder cancer: insight into a rare presentation in Gastrointestinal malignancies. J. Gastrointest. Oncol. 5, E58–64 (2014).
Rawla, P. & Barsouk, A. Epidemiology of gastric cancer: global trends, risk factors, and prevention. Gastroenterol. Review/Przegląd Gastroenterologiczny. 14, 26–38 (2019).
Jaffray, D. A. & Gospodarowicz, M. K. Radiation therapy for cancer. Cancer: Disease Control Priorities. 3, 239–248 (2015).
Yi, S., Qin, S., She, F. & Shao, D. B. S. D. A multi-task framework for pulmonary disease classification using deep learning. Expert Syst. Appl. 259, 125355 (2025).
Du, S., Du, S., Liu, B. & Zhang, X. Incorporating DeepLabv3 + and object-based image analysis for semantic segmentation of very high-resolution remote sensing images. Int. J. Digit. Earth. 14, 357–378 (2021).
Choudhury, R., Vanguri, A., Jambawalikar, R. & Kumar, S. R. Segmentation of brain tumors using DeepLabv3+. in Brainlesion: Glioma, Multiple Sclerosis, Stroke, and Traumatic Brain Injuries. In 4th International Workshop, BrainLes 154–167 (Springer International Publishing, Granada, Spain, 2018).
Azad, R., Asadi-Aghbolaghi, M., Fathy, M. & Escalera, S. Attention Deeplabv3+: Multi-level Context Attention Mechanism for Skin Lesion Segmentation 251–266. In Lecture Notes in Computer Science (Springer International Publishing, 2020).
da Cruz, L. B. et al. Kidney tumor segmentation from computed tomography images using DeepLabv3 + 2.5D model. Expert Syst. Appl. 192, 116270 (2022).
Bernal, J., Sánchez, J. & Vilarino, F. Towards automatic polyp detection with a polyp appearance model. Pattern Recogn. 45 (9), 3166–3182 (2012).
Poorneshwaran, J. M., Kumar, S., Ram, S., Joseph, K. & Sivaprakasam, M. J. Polyp Segmentation using generative adversarial network. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. 7201–7204 (2019).
Lafraxo, S., El Ansari, M., GastroNet & Communications, M. Abnormalities recognition in gastrointestinal tract through endoscopic imagery using deep learning techniques. In 2020 8th International Conference on Wireless Networks and (WINCOM) (IEEE, 2020).
Ye, R., Wang, R., Guo, Y. & Chen, L. SIA-Unet: A Unet with Sequence Information for Gastrointestinal Tract Segmentation. In Pacific Rim International Conference on Artificial Intelligence 316–326 (Springer, Cham, 2022).
Nemani, P. & Vollala, S. Medical image segmentation using LeViT-UNet++: A case study on GI tract data. arXiv [cs.NE] (2022).
Chou, A., Li, W. & Roman, E. GI Tract Image Segmentation with U-Net and Mask R-CNN. Image Segmentation with U-Net and Mask R-CNN.
Niu, H., Lin, Y. & SER-UNet: A Network for Gastrointestinal Image Segmentation. in Proceedings of the 2022 2nd International Conference on Control and Intelligent RoboticsACM, New York, NY, USA, (2022).
Li, H., Liu, J. & Intelligence, A. Multi-view unet for automated GI tract segmentation. In 2022 5th International Conference on Pattern Recognition and (PRAI) (IEEE, 2022).
Chia, B., Gu, H. & Lui, N. Gastrointestinal tract segmentation using multi-task learning.
Georgescu, M. I., Ionescu, R. T. & Miron A.-I. Diversity-promoting ensemble for medical image segmentation. arXiv [eess.IV] (2022).
Jiang, X. et al. BiFTransNet: A unified and simultaneous segmentation network for Gastrointestinal images of CT & MRI. Comput. Biol. Med. 165, 107326 (2023).
Qiu, Y. & Upernet-based deep learning method for the segmentation of gastrointestinal tract images. In Proceedings of the 2023 8th International Conference on Multimedia and Image Processing 34–39 (2023).
John, S. V. & Benifa, B. Automated segmentation of tracking healthy organs from gastrointestinal tumor images. In Smart Innovation, Systems and Technologies 363–373 (Springer Nature Singapore, Singapore, 2023).
Wang, B. et al. Low-friction soft robots for targeted bacterial infection treatment in Gastrointestinal tract. Cyborg Bionic Syst. 5, 0138 (2024).
Li, H. et al. UCFNNet: ulcerative colitis evaluation based on fine-grained lesion learner and noise suppression gating. Comput. Methods Programs Biomed. 247, 108080 (2024).
Song, W. et al. CenterFormer: A novel cluster center enhanced transformer for unconstrained dental plaque segmentation. IEEE Trans. Multimedia. 26, 10965–10978 (2024).
Nobel, S. M. N., Sifat, O. F., Islam, M. R., Sayeed, M. S. & Amiruzzaman, M. Enhancing GI cancer radiation therapy: advanced organ segmentation with ResECA-U-Net model. Emerg. Sci. J. 8, 999–1015 (2024).
Sharma, N. et al. UMobileNetV2 model for semantic segmentation of Gastrointestinal tract in MRI scans. Plos One 19(5), e0302880 (2024).
https://www.kaggle.com/competitions/uw-madison-gi-tract-image-segmentation/data.
Wu, Z. et al. Segmentation of abnormal leaves of hydroponic lettuce based on DeepLabV3 + for robotic sorting. Comput. Electron. Agric. 190, 106443 (2021).
Koonce, B. EfficientNet. In Convolutional Neural Networks with Swift for Tensorflow 109–123 (2021).
Hu, J., Shen, L. & Sun, G. Squeeze-and-Excitation Networks. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 7132–7141, Salt Lake City, UT, USA, 2018, pp. 7132–7141. https://doi.org/10.1109/CVPR.2018.00745 (2018).
Zhang, Z. IEEE,. Improved Adam optimizer for deep neural networks. In 2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS) (2018).
Wichrowska, O. et al. Learned Optimizers that Scale and Generalize. arXiv [cs.LG] (2017).
Keskar, N. S. & Socher, R. Improving generalization performance by switching from Adam to SGD. (2017). arXiv [cs.LG].
Wang, B. et al. Low-Friction soft robots for targeted bacterial infection treatment in Gastrointestinal tract. Cyborg Bionic Syst. 5, 0138. https://doi.org/10.34133/cbsystems.0138 (2024).
Li, H. et al. UCFNNet: ulcerative colitis evaluation based on fine-grained lesion learner and noise suppression gating. Comput. Methods Programs Biomed. 247, 108080. https://doi.org/10.1016/j.cmpb.2024.108080 (2024).
Woo, S., Park, J., Lee, J. Y. & Kweon, I. S. CBAM: convolutional block attention module. In: (eds Ferrari, V., Hebert, M., Sminchisescu, C. & Weiss, Y.) Computer Vision – ECCV 2018. ECCV 2018. Lecture Notes in Computer Science(), vol 11211. Springer, Cham. https://doi.org/10.1007/978-3-030-01234-2_1 (2018).
Misra, D., Nalamada, T., Arasanipalai, A. U. & Hou, Q. Rotate to attend: Convolutional triplet attention module. In 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, pp. 3138–3147. https://doi.org/10.1109/WACV48630.2021.00318 (2021).
Yiran Wang, Y., Bian, S., Jiang, P. S. E. & Part, B. Enhancing structural contextual awareness of networks in medical imaging with Permute Squeeze-and-Excitation module. Biomed. Signal Process. Control 100, 107052. https://doi.org/10.1016/j.bspc.2024.107052 (2025).
Luu, H. M. & Park, S. H. September. Extending nn-UNet for brain tumor segmentation. In International MICCAI Brainlesion Workshop (173–186). Cham: Springer International Publishing. (2021).
Acknowledgements
The authors extend their appreciation to the Deanship of Research and Graduate Studies at King Khalid University for funding this work through the Large Research Project under grant number RGP2/607/46.
Author information
Authors and Affiliations
Contributions
Neha Sharma : Conceived the study, designed the model architecture, and led the experimental implementation and manuscript writing.Sheifali Gupta : Contributed to data preprocessing, model optimization, and assisted in drafting and reviewing the manuscript.Fuad Ali Mohammed Al-Yarimi: was responsible for literature review, dataset preprocessing, and assisted in the formulation of the evaluation metrics and performance analysisUpinder Kaur: Participated in literature review, performance evaluation, and analysis of segmentation results.Salil Bharany : Provided technical guidance, contributed to model evaluation metrics, and reviewed the manuscript for technical accuracy.Ateeq Ur Rehman : Supported model tuning, cross-validation experiments, and interpretation of results from a clinical perspective.Belayneh Matebie Taye : Supervised the research, provided critical revisions to the manuscript, and managed overall coordination, communication, and final submission.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethics approval
No animals or human subjects were involved in this study. The study utilized publicly available datasets, and all methods were carried out in accordance with relevant guidelines and regulations.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Sharma, N., Gupta, S., Al-Yarimi, F.A.M. et al. Multi-level attention DeepLab V3+ with EfficientNetB0 for GI tract organ segmentation in MRI scans. Sci Rep (2026). https://doi.org/10.1038/s41598-026-38247-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-38247-7
