Abstract
U-Net is the most cited and widely-used deep learning model for biomedical image segmentation. In this paper, we propose a new enhanced version of a ubiquitous U-Net architecture, which improves upon the original one in terms of generalization capabilities, while addressing several immanent shortcomings, such as constrained resolution and non-resilient receptive fields of the main pathway. Our novel multi-path architecture introduces a notion of an individual receptive field pathway, which is merged with other pathways at the bottom-most layer by concatenation and subsequent application of Layer Normalization and Spatial Dropout, which can improve generalization performance for small datasets. In general, our experiments show that the proposed multi-path architecture outperforms other state-of-the-art approaches that embark on similar ideas of pyramid structures, skip-connections, and encoder–decoder pathways. A significant improvement of the Dice similarity coefficient is attained at our proprietary colony-forming unit dataset, where a score of was achieved for the foreground class.
Highlights
U-Net [1] is arguably the most famous example of an extremely simple deep learning architecture in the biomedical domain
Many successful applications of the U-Net architecture could be found in cell and nuclei segmentations for digital pathology [3], tumor and organ segmentations [4,5] as well as colony-forming units (CFUs) and other cell segmentation tasks [6,7,8]
CFU segmentation seems to suffer from drifting image acquisition conditions, background noise, an extreme diversity of backgrounds, bacteria types, and possible shapes and textures since agar plates are collected in different labs, environments, and conditions [10]
Summary
U-Net [1] is arguably the most famous example of an extremely simple (but working) deep learning architecture in the biomedical domain. It uses encoder–decoder pathways alleviated with skip-connections [2] while visually resembling a U-shaped pathway. Many successful applications of the U-Net architecture could be found in cell and nuclei segmentations for digital pathology [3], tumor and organ segmentations [4,5] as well as colony-forming units (CFUs) and other cell segmentation tasks [6,7,8]. Microbial cell counting is one of the basic quantitative measurements in microbiology
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
