FIGURE 2 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
A fast and shallow convolutional neural network is proposed for hyperspectral image super-resolution inspired by Spatial-Spectral Reconstruction Network (SSR-NET). The feature extraction ability is improved compared to SSR-NET and other state-of-the-art methods, while the proposed network is also shallow. Numerical experiments show both the visual...
Context in source publication
Similar publications
Due to the inability of convolutional neural networks to effectively obtain long-range information, a transformer was recently introduced into the field of pansharpening to obtain global dependencies. However, a transformer does not pay enough attention to the information of channel dimensions. To solve this problem, a local-global-based high-resol...
Citations
... The process involves taking a lower-resolution image as input and producing a higher resolution version of it. Several approaches have been developed, such as Bayesian estimation [25][26][27], matrix factorization [28,29], and deep learning based methods [30][31][32][33]. Although the Bayesian estimation and matrix factorization are showing great improvement in reconstruction, the more recent approach of deep learning methods is outperforming the previous methods. ...
... and 1.64-2.07 on the Pavia Center dataset. Avagyan et al. [32] showed a decrease in PSNR from 37.49 to 35.39 on the same dataset when increasing the downsampling ratio from 4 to 32. The slight decline in performance metrics implies the potential of further downsampling the HSI data so that, in practice, images can be used with even a lower resolution and consequently shorter acquisition time. ...
(1) Background: Hyperspectral imaging has emerged as a promising margin assessment technique for breast-conserving surgery. However, to be implicated intraoperatively, it should be both fast and capable of yielding high-quality images to provide accurate guidance and decision-making throughout the surgery. As there exists a trade-off between image quality and data acquisition time, higher resolution images come at the cost of longer acquisition times and vice versa. (2) Methods: Therefore, in this study, we introduce a deep learning spatial–spectral reconstruction framework to obtain a high-resolution hyperspectral image from a low-resolution hyperspectral image combined with a high-resolution RGB image as input. (3) Results: Using the framework, we demonstrate the ability to perform a fast data acquisition during surgery while maintaining a high image quality, even in complex scenarios where challenges arise, such as blur due to motion artifacts, dead pixels on the camera sensor, noise from the sensor’s reduced sensitivity at spectral extremities, and specular reflections caused by smooth surface areas of the tissue. (4) Conclusion: This gives the opportunity to facilitate an accurate margin assessment through intraoperative hyperspectral imaging.