RT Journal Article
SR Electronic
T1 Spectral organ fingerprints for intraoperative tissue classification with hyperspectral imaging
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2021.11.24.469943
DO 10.1101/2021.11.24.469943
A1 A. Studier-Fischer
A1 S. Seidlitz
A1 J. Sellner
A1 M. Wiesenfarth
A1 L. Ayala
A1 B. Özdemir
A1 J. Odenthal
A1 S. Knödler
A1 K.F. Kowalewski
A1 C.M. Haney
A1 I. Camplisson
A1 M. Dietrich
A1 K. Schmidt
A1 G.A. Salg
A1 H.G. Kenngott
A1 T.J. Adler
A1 N. Schreck
A1 A. Kopp-Schneider
A1 K. Maier-Hein
A1 L. Maier-Hein
A1 B.P. Müller-Stich
A1 F. Nickel
YR 2021
UL http://biorxiv.org/content/early/2021/11/25/2021.11.24.469943.abstract
AB 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, it had been 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 (9,059 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 decision making and pave the way for context-aware computer-assisted surgery systems and autonomous robotics.Competing Interest StatementThe authors have declared no competing interest.HIShyperspectral imagingMSImultispectral imagingNASANational Aeronautics and Space AdministrationROIregion of interestSDstandard deviationt-SNEt-distributed Stochastic Neighbor Embedding