Semantic Segmentation of Digestive Abnormalities from WCE Images by Using AttResU-Net Architecture
Author:
Lafraxo Samira1ORCID, Souaidi Meryem1ORCID, El Ansari Mohamed12ORCID, Koutti Lahcen1
Affiliation:
1. LabSIV, Department of Computer Science, Faculty of Sciences, Ibn Zohr University, Agadir 80000, Morocco 2. Informatics and Applications Laboratory, Department of Computer Science, Faculty of Sciences, Moulay Ismail University, Meknes 52000, Morocco
Abstract
Colorectal cancer is one of the most common malignancies and the leading cause of cancer death worldwide. Wireless capsule endoscopy is currently the most frequent method for detecting precancerous digestive diseases. Thus, precise and early polyps segmentation has significant clinical value in reducing the probability of cancer development. However, the manual examination is a time-consuming and tedious task for doctors. Therefore, scientists have proposed many computational techniques to automatically segment the anomalies from endoscopic images. In this paper, we present an end-to-end 2D attention residual U-Net architecture (AttResU-Net), which concurrently integrates the attention mechanism and residual units into U-Net for further polyp and bleeding segmentation performance enhancement. To reduce outside areas in an input image while emphasizing salient features, AttResU-Net inserts a sequence of attention units among related downsampling and upsampling steps. On the other hand, the residual block propagates information across layers, allowing for the construction of a deeper neural network capable of solving the vanishing gradient issue in each encoder. This improves the channel interdependencies while lowering the computational cost. Multiple publicly available datasets were employed in this work, to evaluate and verify the proposed method. Our highest-performing model was AttResU-Net, on the MICCAI 2017 WCE dataset, which achieved an accuracy of 99.16%, a Dice coefficient of 94.91%, and a Jaccard index of 90.32%. The experiment findings show that the proposed AttResU-Net overcomes its baselines and provides performance comparable to existing polyp segmentation approaches.
Funder
Ministry of National Education, Vocational Training, Higher Education and Scientific Research Ministry of Industry, Trade and Green and Digital Economy Digital Development Agency Centre National de la Recherche Scientifique
Subject
Paleontology,Space and Planetary Science,General Biochemistry, Genetics and Molecular Biology,Ecology, Evolution, Behavior and Systematics
Reference46 articles.
1. Ramamurthy, K., George, T.T., Shah, Y., and Sasidhar, P. (2022). A Novel Multi-Feature Fusion Method for Classification of Gastrointestinal Diseases Using Endoscopy Images. Diagnostics, 12. 2. Mahmood, S., Fareed, M.M.S., Ahmed, G., Dawood, F., Zikria, S., Mostafa, A., Jilani, S.F., Asad, M., and Aslam, M. (2022). A Robust Deep Model for Classification of Peptic Ulcer and Other Digestive Tract Disorders Using Endoscopic Images. Biomedicines, 10. 3. EndoSLAM dataset and an unsupervised monocular visual odometry and depth estimation approach for endoscopic videos;Ozyoruk;Med. Image Anal.,2021 4. Using single-cell technologies to map the human immune system—Implications for nephrology;Stewart;Nat. Rev. Nephrol.,2020 5. Endoscopic submucosal dissection comparing with surgical resection in patients with early gastric cancer–a single center experience in Taiwan;Hong;J. Formos. Med. Assoc.,2020
Cited by
7 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|