Medical imaging has evolved into a standard in diagnosis and treatment for the visual portrayal of organ and tissue functioning. For clinical diagnosis, processing and analysis of these medical images are therefore crucial. According to WHO (World Health Organisation), CVDs (cardiovascular diseases) are major causes for mortalities in people.; DL (deep learning) based image segmentation has attracted a lot of interest over the past several years, which emphasises the need for a thorough analysis of it. Carotid Plaque is not correctly segmented by current U-Net Models. Improved U-Nets are presented for semantic segmentations for precise comprehensions in this study to address the problem. To achieve a more precise detection, the semantic segmentation is carried out using the Improved U-Net Model, which is modified using the optimisation method known as Particle Swarm Optimisation (PSO) algorithm. Improved U-Net Model outperforms such cutting-edge techniques in the plaque segmentation challenge, demonstrating the usefulness and strong explanatory power of the suggested approach.
Keywords: Medical imaging, Carotid Plaque image segmentation, U-Net Architecture, Particle Swarm Optimization (PSO) algorithm and Plaque segmentation.
How to cite this article: Jonnala P, Reddy GS, An Improvedu-Net Model for Carotid Plaque Segmentation. Int J Drug Deliv Technol. 2026;16(5s): 191-200. DOI: 10.25258/ijddt.16.5s.23