Visual discrimination of tissue during surgery can be challenging since different tissues appear similar to the human eye. Hyperspectral imaging (HSI) removes this limitation by associating each pixel with high-dimensional spectral information. While previous work has shown its general potential to discriminate tissue, clinical translation has been limited due to the method’s current lack of robustness and generalizability. Specifically, the scientific community is lacking a comprehensive spectral tissue atlas, and it is unknown whether variability in spectral reflectance is primarily explained by tissue type rather than the recorded individual or specific acquisition conditions. The contribution of this work is threefold: (1) Based on an annotated medical HSI data set (9059 images from 46 pigs), we present a tissue atlas featuring spectral fingerprints of 20 different porcine organs and tissue types. (2) Using the principle of mixed model analysis, we show that the greatest source of variability related to HSI images is the organ under observation. (3) We show that HSI-based fully-automatic tissue differentiation of 20 organ classes with deep neural networks is possible with high accuracy (> 95%). We conclude from our study that automatic tissue discrimination based on HSI data is feasible and could thus aid in intraoperative decisionmaking and pave the way for context-aware computer-assisted surgery systems and autonomous robotics.

No abstract

Background: The ultimate goal of haemodynamic therapy is to improve microcirculatory tissue and organ perfusion. Hyperspectral imaging (HSI) has the potential to enable noninvasive microcirculatory monitoring at bedside. Methods: HSI (Tivita® Tissue System) measurements of tissue oxygenation, haemoglobin, and water content in the skin (ear) and kidney were evaluated in a double-hit porcine model of major abdominal surgery and haemorrhagic shock. Animals of the control group (n = 7) did not receive any resuscitation regime. The interventional groups were treated exclusively with either crystalloid (n = 8) or continuous norepinephrine infusion (n = 7). Results: Haemorrhagic shock led to a drop in tissue oxygenation parameters in all groups. These correlated with established indirect markers of tissue oxygenation. Fluid therapy restored tissue oxygenation parameters. Skin and kidney measurements correlated well. High dose norepinephrine therapy deteriorated tissue oxygenation. Tissue water content increased both in the skin and the kidney in response to fluid therapy. Conclusions: HSI detected dynamic changes in tissue oxygenation and perfusion quality during shock and was able to indicate resuscitation effectivity. The observed correlation between HSI skin and kidney measurements may offer an estimation of organ oxygenation impairment from skin monitoring. HSI microcirculatory monitoring could open up new opportunities for the guidance of haemodynamic management.