Impact of a generalised SVG-based large-scale super-resolution algorithm on the design of light-weight medical image segmentation DNNs

Abstract

ABSTRACTSetting up a complex CNN requires a powerful platform, several hours of run-time, and a lot of data for training. Here, we propose a generalised lightweight solution that exploits super-resolution and scalable vector graphics and uses a small-scale UNet as the baseline framework to segment different organs in MR and CT data. We selected the UNet since many researchers use it as the baseline, modify it in their proposal, and perform an ablation study to show the effectiveness of the proposed modification. First, we downsample the input 2D CT slices by bicubic interpolation. Using the architecture of the conventional UNet, we reduce the size of the network’s input, and the number of layers and filters to construct a lightweight UNet. The network segments the low-resolution images and prepares the mask of an organ. Then, we upscale the boundary of the output mask by the Support Vector Graphics technique to obtain the final border. This design reduces the number of parameters and the run-time by a factor of two. We segmented several tissues to prove the stability of our method to the type of organ. The experiments proved the feasibility of setting up complex deep neural networks with conventional platforms.KEYWORDS: light-weight deep neural networksscalable vector graphicsgeneralised segmentation frameworksmedical image segmentation Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationNotes on contributorsMina EsfandiarkhaniMina Esfandiarkhani received a B.Sc. degree from the Azad University of Qazvin in 2013 and an M.Sc. degree in Biomedical Engineering from the Shahed University of Tehran in 2016. She is currently pursuing a Ph.D. degree in the Biomedical Engineering faculty of Shahed University. Her research interests include machine learning, computer vision, medical image processing, and artificial intelligence.Amir Hossein ForuzanAmir Hossein Foruzan received his B.S. from the Sharif University of Technology in Telecommunication Engineering. He received his M.S. and Ph.D. from Tehran University in Biomedical Engineering. Since 2011, he has been a faculty member of Shahed University. His research interest is medical image processing.