A NOVEL CARDIAC IMAGE SEGMENTATION METHOD USING AN OPTIMIZED 3D U-NET MODEL

Abstract

Medical image segmentation holds significant importance for doctors, patients, and the entire health care industry. For doctors, it provides more accurate information about cardiac structures, aiding in improving diagnoses and treatment decisions. For patients, segmentation techniques enable personalized medical care, enhancing treatment outcomes and satisfaction. The entire health care sector benefits from the advancement of this technology, driving the development of medical science and contributing to better health care quality and patient well-being. Additionally, segmentation plays a crucial role in research and education, facilitating the accumulation and dissemination of medical knowledge. In summary, the application of medical image segmentation has profound implications for progress in the medical field and patient welfare. In recent years, with technological advancements and innovative algorithms, medical image quality has greatly improved, with higher resolution and reduced noise and artifacts. Simultaneously, the application of deep learning techniques has made the automatic analysis and diagnosis of medical images more precise and efficient. However, due to the complex structures and diversity often present in medical images, models tend to have limited generalization across different datasets, leading to unstable segmentation performance. Considering the excellent image segmentation performance of the three-dimensional (3D) U-Net model, this study introduces an improved spatial attention mechanism on the basis of the 3D U-Net model to enhance its segmentation performance. The spatial attention mechanism enhances the model’s feature extraction capabilities. The enhanced network can capture dependencies among features across both channel and spatial dimensions in the entire global scope. Additionally, it can strengthen any two correlated features within the input feature vector, thereby enhancing the model’s representational capacity. Through detailed experimental validation, the effectiveness of the proposed model is thoroughly demonstrated. Its superiority in performance and computational efficiency positions it as a significant breakthrough in the medical image segmentation field, providing a strong foundation for future research and clinical practice in medical image processing.