Deep Neural Networks for Ring Artifacts Segmentation and Corrections in Fragments of CT Images
| Autor: | Ivan Yakimchuk, Iryna Reimers, Anton Kornilov, Ilia V. Safonov |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Artifact (error)
Ring (mathematics) Artificial neural network Computer science business.industry Ring Artifact inpainting segmentation Inpainting ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION convolutional neural network Image segmentation ring artifacts correction Convolutional neural network lcsh:Telecommunication lcsh:TK5101-6720 Computer vision Segmentation Artificial intelligence business digital rock |
| Zdroj: | Proceedings of the XXth Conference of Open Innovations Association FRUCT, Vol 28, Iss 1, Pp 181-193 (2021) FRUCT |
| ISSN: | 2343-0737 2305-7254 |
| Popis: | Ring artifacts are typical defects of computed tomography (CT) that degrade the quality of a 3D reconstructed image. Existing techniques for a ring reduction have various shortcomings and limitations, in particular, a lot of them are unable to process arbitrary fragments of the image and blur artifact-free regions. We propose an algorithm for ring artifacts segmentation and reduction by deep convolutional neural networks that correct 3D fragments of the CT image by inpainting. We compare 2D and 3D architectures of networks. For the creation of a dataset with a big number of ring artifacts, we propose a procedure that is able to transfer an artifact from one image to an arbitrary place of another image. The appearance of the transferred artifact changes. For ring artifact segmentation and correction in images of sandstones and sand, the proposed networks demonstrate good visual results and outperform existing methods. The proposed technique concentrates on the Digital Rock workflow, but the networks can be adjusted for the processing of other CT images as well. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|