11
IRUS Total
Downloads

Estimation of tissue oxygen saturation from RGB images and sparse hyperspectral signals based on conditional generative adversarial network

File Description SizeFormat 
Li2019_Article_EstimationOfTissueOxygenSatura.pdfPublished version1.2 MBAdobe PDFView/Open
Title: Estimation of tissue oxygen saturation from RGB images and sparse hyperspectral signals based on conditional generative adversarial network
Authors: Li, Q
Lin, J
Clancy, NT
Elson, DS
Item Type: Journal Article
Abstract: Purpose: Intra-operative measurement of tissue oxygen saturation (StO 2 ) is important in detection of ischaemia, monitoring perfusion and identifying disease. Hyperspectral imaging (HSI) measures the optical reflectance spectrum of the tissue and uses this information to quantify its composition, including StO 2 . However, real-time monitoring is difficult due to capture rate and data processing time. Methods: An endoscopic system based on a multi-fibre probe was previously developed to sparsely capture HSI data (sHSI). These were combined with RGB images, via a deep neural network, to generate high-resolution hypercubes and calculate StO 2 . To improve accuracy and processing speed, we propose a dual-input conditional generative adversarial network, Dual2StO2, to directly estimate StO 2 by fusing features from both RGB and sHSI. Results: Validation experiments were carried out on in vivo porcine bowel data, where the ground truth StO 2 was generated from the HSI camera. Performance was also compared to our previous super-spectral-resolution network, SSRNet in terms of mean StO 2 prediction accuracy and structural similarity metrics. Dual2StO2 was also tested using simulated probe data with varying fibre number. Conclusions: StO 2 estimation by Dual2StO2 is visually closer to ground truth in general structure and achieves higher prediction accuracy and faster processing speed than SSRNet. Simulations showed that results improved when a greater number of fibres are used in the probe. Future work will include refinement of the network architecture, hardware optimization based on simulation results, and evaluation of the technique in clinical applications beyond StO 2 estimation.
Issue Date: 1-Jun-2019
Date of Acceptance: 7-Mar-2019
URI: http://hdl.handle.net/10044/1/68361
DOI: 10.1007/s11548-019-01940-2
ISSN: 1861-6410
Publisher: Springer
Start Page: 987
End Page: 995
Journal / Book Title: International Journal of Computer Assisted Radiology and Surgery
Volume: 14
Issue: 6
Copyright Statement: © 2019 The Author(s). This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
Sponsor/Funder: Medical Research Council (MRC)
Deutsche Forschungsgemeinschaft ( German Research
Cancer Research UK
Imperial College Healthcare NHS Trust- BRC Funding
Imperial College Healthcare NHS Trust- BRC Funding
Funder's Grant Number: MC_PC_13064
637960
25147
RDB04 79560
RD207
Keywords: Science & Technology
Technology
Life Sciences & Biomedicine
Engineering, Biomedical
Radiology, Nuclear Medicine & Medical Imaging
Surgery
Engineering
Intro-operative imaging
Optical imaging
Tissue oxygen saturation
Generative adversarial network
IN-VIVO
PROBE
Generative adversarial network
Intro-operative imaging
Optical imaging
Tissue oxygen saturation
Animals
Intestines
Ischemia
Optical Imaging
Oxygen
Swine
Intestines
Animals
Swine
Ischemia
Oxygen
Optical Imaging
1103 Clinical Sciences
Nuclear Medicine & Medical Imaging
Publication Status: Published
Open Access location: https://www.springermedizin.de/estimation-of-tissue-oxygen-saturation-from-rgb-images-and-spars/16566634
Online Publication Date: 2019-03-21
Appears in Collections:Department of Surgery and Cancer



Unless otherwise indicated, items in Spiral are protected by copyright and are licensed under a Creative Commons Attribution NonCommercial NoDerivatives License.

Creative Commons