Retina image segmentation using the three-path Unet model

Abstract

Unsupervised image segmentation is a technique that divides an image into distinct regions or objects without prior labeling. This approach offers flexibility and adaptability to various types of image data. Particularly for large datasets, it eliminates the need for manual labeling, thereby it presents advantages in terms of time and labor costs. However, when applied to retinal image segmentation, challenges arise due to variations in data, presence of noise, and manual threshold adjustments, which can lead to over-segmentation or under-segmentation of small blood vessel boundaries and endpoints. In order to enhance the precision and accuracy of retinal image segmentation, we propose a novel image supervised segmentation network based on three-path Unet model.Firstly, the Haar wavelet transform is employed to extract high-frequency image information, which forms the foundation for the proposed HaarNet, a Unet-inspired architecture. Next, the HaarNet is integrated with the Unet and SegNet frameworks to develop a three-path Unet model, referred to as TP-Unet. Finally, the model is further refined into TP-Unet+AE+DSL by incorporating the advantages of auto-encoding (AE) and deep supervised learning (DSL) techniques, thereby enhancing the overall performance of the system. To evaluate the effectiveness of our proposed model, we conduct experiments using the DRIVE and CHASE public datasets. On the DRIVE dataset, our recommended model achieves a Dice coefficient of 0.8291 and a sensitivity index of 0.8184. These results significantly outperform the Unet model by 1.34%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$1.34\\%$$\\end{document} and 2.60%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$2.60\\%$$\\end{document}, respectively. Furthermore, our model demonstrates excellent performance on the CHASE dataset, with a Dice coefficient of 0.8162, a sensitivity of 0.8242, and an accuracy of 0.9664. These metrics surpass the Unet model by 3.20%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$3.20\\%$$\\end{document}, 6.66%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$6.66\\%$$\\end{document}, and 0.42%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$0.42\\%$$\\end{document}, respectively. Our proposed model provides more accurate and reliable results for retinal vessel segmentation, which holds significant potential for assisting doctors in their diagnosis.