Services on Demand
Journal
Article
Indicators
Cited by SciELO
Access statistics
Related links
Similars in SciELO
Share
Computación y Sistemas
On-line version ISSN 2007-9737Print version ISSN 1405-5546
Abstract
RAMIREZ-SANCHEZ, Jairo Enrique; MARTINEZ-BARRON, Pedro A.; MEDINA-AGUILAR, Hannia and SANCHEZ-NIGENDA, Romeo. Weighted U-NET++ and 2D-HMM Ensemble for Gastrointestinal Image Segmentation. Comp. y Sist. [online]. 2023, vol.27, n.4, pp.991-1002. Epub May 17, 2024. ISSN 2007-9737. https://doi.org/10.13053/cys-27-4-4771.
One of the most widely used treatments for cancer of the gastrointestinal (GI) tract is radiotherapy, which requires manual segmentation of the affected organs to deliver radiation without affecting healthy cells. Deep learning techniques have been used, especially variants of U-Net, to automate the organ segmentation process, increasing the efficiency of medical treatment. However, the effective segmentation of the GI tract organs remains an open research problem due to their high capacity to deform because of body movement and respiratory function. This work proposes a methodology that develops a weighted ensemble integrating U-Net++ models and Hidden Markov Models (2D-HMM) for semantic segmentation of the stomach and bowels. Our empirical evaluation reports a score of 0.811 for the Dice coefficient using Leave-One-Out Cross-Validation, which provides robustness to the results.
Keywords : Image segmentation; U-NET architecture; machine learning; hidden Markov models.