Deep learning of multi-resolution X-Ray micro-CT images for multi-scale modelling

Jackson, Samuel J.; Niu, Yufu; Manoorkar, Sojwal; Mostaghimi, Peyman; Armstrong, Ryan T.

doi:10.48550/arxiv.2111.01270

Cited by 2 publications

(2 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the advantages of multi-scale image fusion have led to great interest in resolution improvement. Inspired by multi-scale reconstruction [2,46], we will investigate multi-scale fusion instead of reconstructing SR with single-scale images. The reconstructed image properties will be evaluated on the real rock images.…”

Section: Discussion and Future Workmentioning

confidence: 99%

“…In the field of geological petroleum, limited by the detector hardware in the process of acquiring rock imaging, it is challenging to make a win-win for both the receptive field and its resolution, which means the reservoir characteristics cannot be clearly obtained [1][2][3]. In this case, X-ray computed tomography (CT) technology is commonly used in reservoir geology studies due to its fast, non-destructive, three-dimensional (3D) characterization and ease of integration with computer simulations [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Rock CT Image Super-Resolution Using Residual Dual-Channel Attention Generative Adversarial Network

Shan

Liu

et al. 2022

Energies

View full text Add to dashboard Cite

Because of its benefits in terms of high speed, non-destructiveness, and three-dimensionality, as well as ease of integration with computer simulation, computed tomography (CT) technology is widely applied in reservoir geology research. However, rock imaging is restricted by the device used as there is not a win–win for both the image receptive field and corresponding resolution. Convolutional neural network-based super-resolution reconstruction has become a hot topic in improving the performance of CT images. With the help of a convolution kernel, it can effectively extract characteristics and ignore disturbance information. The dismal truth is that convolutional neural networks still have numerous issues, particularly unclear texture details. To address these challenges, a generative adversarial network (RDCA-SRGAN) was designed to improve rock CT image resolution using the combination of residual learning and a dual-channel attention mechanism. Specifically, our generator employs residual attention to extract additional features; similarly, the discriminator builds on dual-channel attention and residual learning to distinguish generated contextual information and decrease computational consumption. Quantitative and qualitative analyses demonstrate that the proposed model is superior to earlier advanced frameworks and is capable to constructure visually indistinguishable high-frequency details. The quantitative analysis shows our model contributes the highest value of structural similarity, enriching the more detailed texture information. From the qualitative analysis, in enlarged details of the reconstructed images, the edges of the images generated by the RDCA-SRGAN can be shown to be clearer and sharper. Our model not only performs well in subtle coal cracks but also enriches more dissolved carbonate and carbon minerals. The RDCA-SRGAN has substantially enhanced the reconstructed image resolution and our model has great potential to be used in geomorphological study and exploration.

show abstract

Section: Discussion and Future Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Rock CT Image Super-Resolution Using Residual Dual-Channel Attention Generative Adversarial Network

Shan

Liu

et al. 2022

Energies

View full text Add to dashboard Cite

show abstract

Deep-learning models enable high-resolution reconstruction of large-volume x-ray microscopy datasets

Johnson,

Trenikhina,

Bale

et al. 2024

Developments in X-Ray Tomography XV

View full text Add to dashboard Cite

A critical challenge in modern x-ray imaging is achieving high-resolution for large volumes. Countless material applications demand statistically relevant samplings of defects, encompassing secondary phases, inclusions, phase segregation, cracks, pores, and more. There is an inherent tradeoff between the volume that can be imaged and the resolution of the image. Imaging a large volume may yield a statistically relevant sample size but at low resolution, rendering it inadequate for detecting the smallest defects. Conversely, high spatial resolution imaging captures intricate details over a small volume, raising questions about statistical relevance. This paper demonstrates the application of a commercial deep-learning-based x-ray tomography reconstruction method for solid state battery analysis. By harnessing the power of two distinct datasets-a high-volume scan and a high-resolution scan -a deep neural network is trained on correspondences between low and high-resolution images. Following training, the model performs reconstruction of the large-volume dataset at high-resolution. The model is demonstrated for defect detection in a commercial solid state battery. A 3mm 2 battery sample is imaged at a 3-micron pixel resolution. A second interior tomography is captured at 1.5-micron pixel resolution. The DL model reconstructs the battery volume at 1.5-micron resolution, revealing defects and particle inclusions previously concealed by low-resolution, largevolume scans. Reconstruction is validated using direct comparisons between the deep-learning-based XCT reconstruction and traditional high-resolution imaging. A femtosecond laser was employed to cut the sample, exposing these defects for imaging with scanning electron microscopy (SEM). Multiple defects and microstructural features revealed in the deep-learning-based reconstructions were confirmed during this validation process.

show abstract

Deep learning of multi-resolution X-Ray micro-CT images for multi-scale modelling

Cited by 2 publications

References 58 publications

Rock CT Image Super-Resolution Using Residual Dual-Channel Attention Generative Adversarial Network

Rock CT Image Super-Resolution Using Residual Dual-Channel Attention Generative Adversarial Network

Deep-learning models enable high-resolution reconstruction of large-volume x-ray microscopy datasets

Contact Info

Product

Resources

About