Deep Learning for Low-Dose CT Denoising Using Perceptual Loss and Edge Detection Layer.
Low-dose CT denoising is a challenging task that has been studied by many researchers. Some studies have used deep neural networks to improve the quality of low-dose CT images and achieved fruitful results. In this paper, we propose a deep neural network that uses dilated convolutions with different...
| Publicado en: | Journal of Digital Imaging Vol. 33; no. 2; pp. 504 - 516 |
|---|---|
| Autores principales: | , , |
| Formato: | diagnostic images equations & formulas research tables/charts Journal Article |
| Publicado: |
Springer Nature
Apr2020
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=142764014&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 142764014 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 08971889 DOQ jtl: Journal of Digital Imaging issn: 08971889 maglogo: N pubinfo: dt: Apr2020 vid: 33 iid: 2 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 142764014 142764014 142764014 10.1007/s10278-019-00274-4 142764014 ppf: 504 ppct: 12 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Deep Learning for Low-Dose CT Denoising Using Perceptual Loss and Edge Detection Layer. aug: au: Gholizadeh-Ansari, Maryam Alirezaie, Javad Babyn, Paul affil: Department of Electrical and Computer Engineering, Ryerson University, 350 Victoria Street, M5B2K3, Toronto, ON, Canada sug: subj: Artifacts Deep Learning Neural Networks (Computer) Radiation Dosage Radiographic Image Enhancement Methods Tomography, X-Ray Computed Methods Human ab: Low-dose CT denoising is a challenging task that has been studied by many researchers. Some studies have used deep neural networks to improve the quality of low-dose CT images and achieved fruitful results. In this paper, we propose a deep neural network that uses dilated convolutions with different dilation rates instead of standard convolution helping to capture more contextual information in fewer layers. Also, we have employed residual learning by creating shortcut connections to transmit image information from the early layers to later ones. To further improve the performance of the network, we have introduced a non-trainable edge detection layer that extracts edges in horizontal, vertical, and diagonal directions. Finally, we demonstrate that optimizing the network by a combination of mean-square error loss and perceptual loss preserves many structural details in the CT image. This objective function does not suffer from over smoothing and blurring effects causing by per-pixel loss and grid-like artifacts resulting from perceptual loss. The experiments show that each modification to the network improves the outcome while changing the complexity of the network, minimally. pubtype: Academic Journal doctype: diagnostic images equations & formulas research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|