paper-with-me

홈 › Papers

RGB to Hyperspectral: Spectral Reconstruction for Enhanced Surgical Imaging

2024-10-17 · Tobias Czempiel, Alfie Roddan, Maria Leiloglou, Zepeng Hu, Kevin O'Neill, Giulio Anichini, Danail Stoyanov, Daniel Elson

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.

📄 PDF Abstract BibTeX arXiv:2410.13570

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingSpectral ReconstructionSSIM

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Adam 설명 없음
Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

HyKey: Hyperspectral Keypoint Detection and Matching in Minimally Invasive Surgery

2026-04-19 · Alexander Saikia, Chiara Di Vece, Zhehua Mao, Sierra Bonilla 외 arxiv

Purpose: 3D reconstruction in minimally invasive surgery (MIS) enables enhanced surgical guidance through improved visualisation, tool tracking, and augmented reality. However, traditional RGB-based keypoint detection an…

Keypoint Detection3D ReconstructionPose Estimation

A self-supervised and adversarial approach to hyperspectral demosaicking and RGB reconstruction in surgical imaging

2024-07-27 · Peichao Li, Oscar MacCormac, Jonathan Shapey, Tom Vercauteren

Hyperspectral imaging holds promises in surgical imaging by offering biological tissue differentiation capabilities with detailed information that is invisible to the naked eye. For intra-operative guidance, real-time sp…

Demosaicking

Deep Learning Approach for Hyperspectral Image Demosaicking, Spectral Correction and High-resolution RGB Reconstruction

2021-09-03 · Peichao Li, Michael Ebner, Philip Noonan, Conor Horgan 외

Hyperspectral imaging is one of the most promising techniques for intraoperative tissue characterisation. Snapshot mosaic cameras, which can capture hyperspectral data in a single exposure, have the potential to make a r…

Decision MakingDemosaickingHyperspectral Image Super-ResolutionImage Generation+3

Endoscopic Depth Measurement and Super-Spectral-Resolution Imaging

2017-06-19 · Jianyu Lin, Neil T. Clancy, Yang Hu, Ji Qi 외

Intra-operative measurements of tissue shape and multi/ hyperspectral information have the potential to provide surgical guidance and decision making support. We report an optical probe based system to combine sparse hyp…

Decision MakingOptical Flow Estimation

Synthetic white balancing for intra-operative hyperspectral imaging

2023-07-24 · Anisha Bahl, Conor C. Horgan, Mirek Janatka, Oscar J. MacCormac 외

Hyperspectral imaging shows promise for surgical applications to non-invasively provide spatially-resolved, spectral information. For calibration purposes, a white reference image of a highly-reflective Lambertian surfac…