Towards Real-Time Hyperspectral Multi-Image Super-Resolution Reconstruction Applied to Histological Samples

Abstract

Hyperspectral Imaging (HSI) is increasingly adopted in medical applications for the usefulness of understanding the spectral signature of specific organic and non-organic elements. The acquisition of such images is a complex task, and the commercial sensors that can measure such images is scarce down to the point that some of them have limited spatial resolution in the bands of interest. This work proposes an approach to enhance the spatial resolution of hyperspectral histology samples using super-resolution. As the data volume associated to HSI has always been an inconvenience for the image processing in practical terms, this work proposes a relatively low computationally intensive algorithm. Using multiple images of the same scene taken in a controlled environment (hyperspectral microscopic system) with sub-pixel shifts between them, the proposed algorithm can effectively enhance the spatial resolution of the sensor while maintaining the spectral signature of the pixels, competing in performance with other state-of-the-art super-resolution techniques, and paving the way towards its use in real-time applications.

TNT++: A Spectral Super-Resolution Method Based on the Entropy of Pathological Images

“…In practical situations, this is more costly compared to obtaining high-resolution RGB images. Carlos Urbina Ortega et al [35] proposed a computationally efficient super-resolution method to enhance spatial resolution, which holds tremendous application value. However, this also necessitates the use of spectral imaging equipment to capture low-resolution hyperspectral images.…”