- All Journals
- Al-Qadisiyah University
- Basrah University
- Kirkuk University
- Mosul University
- The Iraqi Borad for Medical Specialization
- University of Anbar
- University of Technology
- Al Mustafa University
- Al-Zahraa University for Women
- Alnoor University
- Kunooz University
- Misan University
- Ninevah University
- Tikrit University
- University of Al-Hamdaniya
- University of Kerbala
Developing an efficient polyp segmentation using residual learning in asymmetric non-local neural networks | ||
| Journal of University of Anbar for Pure Science | ||
| Volume 19, Issue 2, November and December 2025, Pages 177-191 PDF (2.67 M) | ||
| Document Type: Research Paper | ||
| DOI: 10.37652/juaps.2025.161190.1421 | ||
| Authors | ||
| Mahmoud H Farhan1; Akeel Abdulraheem Thulnoon* 2; Farah Maath Jasem2 | ||
| 1Department of Information Technology, College of CS & IT, University of Anbar, Ramadi, Iraq. | ||
| 2Department of Information Technology, College of CS & IT, University of Anbar, Ramadi, Iraq | ||
| Abstract | ||
| Colorectal cancer is among the leading causes of death by cancer worldwide. Thus, colorectal cancer needs early diagnosis to help in the management of the disease. Colonoscopy remains the main tool for polyp detection, yet the procedure sometimes fails because of the problem of vastly different structures and of very tiny polyps, rendering a possible overlook. To overcome the limitation, we propose a new image segmentation framework based on an Asymmetric Non-local Neural Network (ANN). Having considerably enhanced the accuracy of polyp detection in colonoscopy images, the ANN presents the best features of the non-local operation that considers subtle local features and long-range dependencies of an image for its segmentation and hence better polyp identifications. Upon evaluation of the framework over the Kvasir-SEG dataset, higher results were obtained with a Dice score of 0.947 and an average IoU (Intersection over Union) of 0.901. These metrics are beyond any known methods available today. It is believed that this breakthrough will provide major support for colorectal-cancer screening by reducing misdiagnoses and improving overall patient care, thereby ushering new possibilities for the early detection and effective treatment of this devastating disease. | ||
| Keywords | ||
| Asymmetric non-local neural network (ANN); Colorectal cancer; Medical image; Non-local attention; Polyp segmentation | ||
| References | ||
|
[1] Wang R, Lei T, Cui R, Zhang B, Meng H, Nandi AK. Medical image segmentation using deep learning: A survey.IET Image Processing. 2022;16(5):1243–1267.10.1049/ipr2.12419 [2] Jozdani SE, Johnson BA, Chen D. Comparing Deep Neural Networks, Ensemble Classifiers, and Support Vector Machine Algorithms for Object-Based Urban Land Use/Land Cover Classification. Remote Sensing. 2019;11(14):1713.10.3390/rs11141713 [3] Dang T, Nguyen TT, McCall J, Elyan E, Moreno-García CF. Two-layer Ensemble of Deep Learning Models for Medical Image Segmentation.Cognitive Computation. 2024;16(3):1141–1160. 10.1007/s12559-024-10257-5 [4] Farhan MH, Shaker K, Al-Janabi S.Efficient Approach for the Localization of Copy-Move Forgeries Using PointRend with RegNetX.Baghdad Science Journal. 2024;21(4):1416.10.21123/bsj.2023.8304 [5] Mattiuzzi C, Sanchis-Gomar F, Lippi G.Concise update on colorectal cancer epidemiology.Annals of Translational Medicine. 2019;7(21):609–609.10.21037/atm.2019.07.91 [6] Zhang R, Li G, Li Z, Cui S, Qian D, Yu Y.In: Adaptive Context Selection for Polyp Segmentation. Springer International Publishing; 2020. p. 253–262.10.1007/978-3-030-59725-2_25 [7] Wang J, Lim CS. Synergistic Multi-Granularity Rough Attention UNet for Polyp Segmentation. Journal of Imaging. 2025;11(4):92.10.3390/jimaging11040092 [8] Takano D, Omura H, Minamoto T.Detection and Classification Method for Early-Stage Colorectal Cancer Using Dyadic Wavelet Packet Transform. IEEE Access. 2025;13:9276–9289. 10.1109/access.2025.3526786 [9] Blanes-Vidal V, Baatrup G, Nadimi ES.Addressing priority challenges in the detection and assessment of colorectal polyps from capsule endoscopy and colonoscopy in colorectal cancer screening using machine learning.Acta Oncologica. 2019;58(sup1):S29–S36.10.1080/0284186x.2019.1584404 [10] Afify HM, Mohammed KK, Hassanien AE.An improved framework for polyp image segmentation based on SegNet architecture.International Journal of Imaging Systems and Technology. 2021;31(3):1741–1751.10.1002/ima.22568 [11] Jha D, Smedsrud PH, Riegler MA, Halvorsen P, de Lange T, Johansen D, et al.In: Kvasir-SEG: A Segmented Polyp Dataset. Springer International Publishing; 2019. p. 451–462.10.1007/978-3-03037734-2_37 [12] Khalaf M, Dhannoon BN. MSRD-Unet: Multiscale Residual Dilated U-Net for Medical Image Segmentation.Baghdad Science Journal. 2022;19(6(Suppl.)):1603.10.21123/bsj.2022.7559 [13] Mukhlif AA, Al-Khateeb B, Mohammed MA.An extensive review of state-of-the-art transfer learning techniques used in medical imaging: Open issues and challenges. Journal of Intelligent Systems. 2022;31(1):1085–1111.10.1515/jisys-2022-0198 [14] Al-Waisy AS, Al-Fahdawi S, Mohammed MA, Abdulkareem KH, Mostafa SA, Maashi MS, et al. RETRACTED ARTICLE: COVID-CheXNet: hybrid deep learning framework for identifying COVID-19 virus in chest X-rays images.Soft Computing. 2020;27(5):2657–2672.10.1007/s00500020-05424-3 [15] Branch MVL, Carvalho AS. Polyp Segmentation in Colonoscopy Images using U-Net-MobileNetV2. arXiv; 2021.10.48550/ARXIV.2103.15715 [16] Hazzaa F, Udoidiong I, Qashou A, Yousef S.Segment Anything: A Review.Mesopotamian Journal of Computer Science. 2024;2024:150–161.10.58496/mjcsc/2024/012 [17] Mamonov AV, Figueiredo IN, Figueiredo PN, Richard Tsai YH. Automated Polyp Detection in Colon Capsule Endoscopy. IEEE Transactions on Medical Imaging. 2014;33(7):1488–1502. 10.1109/tmi.2014.2314959 [18] Tajbakhsh N, Gurudu SR, Liang J. Automated Polyp Detection in Colonoscopy Videos Using Shape and Context Information. IEEE Transactions on Medical Imaging. 2016;35(2):630–644. 10.1109/tmi.2015.2487997 [19] Akbari M, Mohrekesh M, Nasr-Esfahani E, Soroushmehr SMR, Karimi N, Samavi S, et al.. Polyp Segmentation in Colonoscopy Images Using Fully Convolutional Network. arXiv; 2018. 10.48550/ARXIV.1802.00368 [20] Fan DP, Ji GP, Zhou T, Chen G, Fu H, Shen J, et al.In: PraNet: Parallel Reverse Attention Network for Polyp Segmentation. Springer International Publishing; 2020. p. 263–273.10.1007/978-3-03059725-2_26 [21] Safarov S, Whangbo TK.A-DenseUNet: Adaptive Densely Connected UNet for Polyp Segmentation in Colonoscopy Images with Atrous Convolution.Sensors. 2021;21(4):1441.10.3390/s21041441 [22] Fan DP, Ji GP, Zhou T, Chen G, Fu H, Shen J, et al.In: PraNet: Parallel Reverse Attention Network for Polyp Segmentation. Springer International Publishing; 2020. p. 263–273.10.1007/978-3-03059725-2_26 [23] Zhang Y, Liu H, Hu Q. In: TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation. Springer International Publishing; 2021. p. 14–24.10.1007/978-3-030-87193-2_2 [24] Dong B, Wang W, Fan DP, Li J, Fu H, Shao L.Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers.arXiv preprint. 2021.10.48550/ARXIV.2108.06932 [25] Kim T, Lee H, Kim D.UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation. In: Proceedings of the 29th ACM International Conference on Multimedia. MM ’21. ACM; 2021. p. 2167–2175.10.1145/3474085.3475375 [26] Lou A, Guan S, Ko H, Loew MH.CaraNet: context axial reverse attention network for segmentation of small medical objects.In: Išgum I, Colliot O, editors. Medical Imaging 2022: Image Processing. SPIE; 2022. p. 11.10.1117/12.2611802 [27] Tomar NK, Jha D, Bagci U, Ali S. In: TGANet: Text-Guided Attention for Improved Polyp Segmentation. Springer Nature Switzerland; 2022. p. 151–160.10.1007/978-3-031-16437-8_15 [28] Wang J, Huang Q, Tang F, Meng J, Su J, Song S.In: Stepwise Feature Fusion: Local Guides Global. Springer Nature Switzerland; 2022. p. 110–120.10.1007/978-3-031-16437-8_11 [29] Rahman MM, Marculescu R.Medical Image Segmentation via Cascaded Attention Decoding.In: 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE; 2023. p. 6211–6220.10.1109/wacv56688.2023.00616 [30] Tomar NK, Jha D, Bagci U. Prototype Learning for Out-of-Distribution Polyp Segmentation. arXiv; 2023.10.48550/ARXIV.2308.03709 [31] Lewis J, Cha YJ, Kim J. Dual encoder–decoder-based deep polyp segmentation network for colonoscopy images.Scientific Reports. 2023;13(1).10.1038/s41598-023-28530-2 [32] Liu G, Yao S, Liu D, Chang B, Chen Z, Wang J, et al. CAFE-Net: Cross-Attention and Feature Exploration Network for polyp segmentation.Expert Systems with Applications. 2024;238:121754. 10.1016/j.eswa.2023.121754 [33] He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. arXiv; 2015. 10.48550/ARXIV.1512.03385 [34] Zhang Y, Liu H, Hu Q. TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation. arXiv; 2021.10.48550/ARXIV.2102.08005 [35] Farhan MH, Shaker K, Al-Janabi S. Double Dual Convolutional Neural Network (D2CNN) for Copy-Move Forgery Detection.In: 2023 15th International Conference on Developments in eSystems Engineering (DeSE). IEEE; 2023. p. 439–444.10.1109/dese58274.2023.10100318 | ||
|
Statistics Article View: 351 PDF Download: 185 |
||