RGB to Hyperspectral: Spectral Reconstruction for Enhanced Surgical Imaging

TL;DR

This paper explores reconstructing hyperspectral images from RGB data using CNNs and transformers to improve surgical imaging, demonstrating superior spectral prediction and potential for real-time clinical applications.

Contribution

It introduces the use of transformer models for spectral reconstruction in surgical imaging, showing improved accuracy over traditional CNN approaches.

Findings

Transformers outperform CNNs in spectral reconstruction metrics.

Spectral profiles are accurately predicted for surgical decision-making.

Challenges in capturing extended spectral ranges are identified.

Abstract

This study investigates the reconstruction of hyperspectral signatures from RGB data to enhance surgical imaging, utilizing the publicly available HeiPorSPECTRAL dataset from porcine surgery and an in-house neurosurgery dataset. Various architectures based on convolutional neural networks (CNNs) and transformer models are evaluated using comprehensive metrics. Transformer models exhibit superior performance in terms of RMSE, SAM, PSNR and SSIM by effectively integrating spatial information to predict accurate spectral profiles, encompassing both visible and extended spectral ranges. Qualitative assessments demonstrate the capability to predict spectral profiles critical for informed surgical decision-making during procedures. Challenges associated with capturing both the visible and extended hyperspectral ranges are highlighted using the MAE, emphasizing the complexities involved. The findings open up the new research direction of hyperspectral reconstruction for surgical applications and clinical use cases in real-time surgical environments.