Citation
Sim, Kok Swee and Sammani, Fawaz (2019) Deep convolutional networks for magnification of DICOM Brain Images. International Journal of Innovative Computing, Information and Control (IJICIC), 15 (2). pp. 725-739. ISSN 1349-418X
Text
99.pdf - Published Version Restricted to Repository staff only Download (3MB) |
Abstract
Convolutional neural networks have recently achieved great success in Single Image Super-Resolution (SISR). SISR is the action of reconstructing a high-quality image from a low-resolution one. In this paper, we propose a deep Convolutional Neural Network (CNN) for the enhancement of Digital Imaging and ommunications in Medicine (DICOM) brain images. The network learns an end-to-end mapping between the low and high resolution images. We first extract features from the image, where each new layer is connected to all previous layers. We then adopt residual learning and the mixture of convolutions to reconstruct the image. Our network is designed to work with grayscale images, since brain images are originally in grayscale. We further compare our method with previous works, trained on the same brain images, and show that our method outperforms them.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | Convolutional neural networks , deep convolutional networks, Single image super-resolution, Magnification, DICOM images |
Subjects: | Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science |
Divisions: | Faculty of Engineering and Technology (FET) |
Depositing User: | Ms Suzilawati Abu Samah |
Date Deposited: | 17 Feb 2022 01:25 |
Last Modified: | 17 Feb 2022 01:25 |
URII: | http://shdl.mmu.edu.my/id/eprint/9155 |
Downloads
Downloads per month over past year
Edit (login required) |