Abstract
Medical image segmentation is of important support for clinical medical applications. As most of the current medical image segmentation models are limited in the U-shaped structure, to some extent the deep convolutional neural network (CNN) structure design is hard to be accomplished. The design in this study mimics the way the wave is elastomeric propagating, extending the structure from both the horizontal and spatial dimensions for realizing the Elastomeric UNet (EUNet) structure. The EUNet can be divided into two types: horizontal EUNet and spatial EUNet, based on the propagation direction. The advantages of this design are threefold. First, the training structure can be deepened effectively. Second, the independence brought by each branch (a U-shaped design) makes the flexible design redundancy available. Finally, a horizontal and vertical series-parallel structure helps on feature accumulation and recursion. Researchers can adjust the design according to the requirements to achieve better segmentation performance for the independent structural design. The proposed networks were evaluated on two datasets: a self-built dataset (multi-photon microscopy, MPM) and publicly benchmark retinal datasets (DRIVE). The results of experiments demonstrated that the performance of EUNet outperformed the UNet and its variants.
Highlights
With the popularization of medical imaging technology, such as magnetic resonance imaging (MRI), computed tomography (CT), positron emission tomography (PET), ultrasonic imaging, digital pathology, and microscopy, medical imaging technology plays an important role in clinical medicine to emerge the structure of human organs, tissues, and cells (Taruttis and Ntziachristos, 2015; Papadopoulos et al, 2017; Pang et al, 2020)
All architectures proposed in the study were evaluated on two datasets, namely, the multi-photon microscopy (MPM) publicly benchmark retinal datasets (DRIVE)
The Segmentation Results of the Multi-Photon Microscopy Dataset the proposed Elastomeric UNet (EUNet) was evaluated based on MPM
Summary
With the popularization of medical imaging technology, such as magnetic resonance imaging (MRI), computed tomography (CT), positron emission tomography (PET), ultrasonic imaging, digital pathology, and microscopy, medical imaging technology plays an important role in clinical medicine to emerge the structure of human organs, tissues, and cells (Taruttis and Ntziachristos, 2015; Papadopoulos et al, 2017; Pang et al, 2020). The morphology of in vivo cells is an intuitive reflection of cell structure and function, and the analysis of it is a significant part of histopathology and clinical medicine to carry out clinical medical diagnosis and genetic research on aging, cell, and tissue expression of Alzheimer’s and Parkinson’s diseases (Li et al, 2010; Haft-Javaherian et al, 2019; Ye et al, 2020). Elastomeric UNet for Medical Image Segmentation of Alzheimer’s disease and cellular senescence on capillaries (Haft-Javaherian et al, 2019). Image segmentation is an active research topic within medical image technology, which accounts for 70% of the international image processing competitions. The role of medical image segmentation is to improve the intuitiveness of medical images and reduce man-made mistakes. Accurate medical image segmentation is difficult to achieve, owing to the data scarcity and image complexity, such as noisy background and intensity in-homogeneity
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.