Spectral organ fingerprints for machine learning-based intraoperative tissue classification with hyperspectral imaging in a porcine model

• Verfasst von: Studier-Fischer, Alexander [VerfasserIn]
• Verfasst von: Seidlitz, Silvia [VerfasserIn]
• Verfasst von: Sellner, Jan [VerfasserIn]
• Verfasst von: Özdemir, Berkin [VerfasserIn]
• Verfasst von: Wiesenfarth, Manuel [VerfasserIn]
• Verfasst von: Ayala, Leonardo [VerfasserIn]
• Verfasst von: Odenthal, Jan [VerfasserIn]
• Verfasst von: Knödler, Samuel [VerfasserIn]
• Verfasst von: Kowalewski, Karl-Friedrich [VerfasserIn]
• Verfasst von: Haney, Caelán Max [VerfasserIn]
• Verfasst von: Camplisson, Isabella [VerfasserIn]
• Verfasst von: Dietrich, Maximilian [VerfasserIn]
• Verfasst von: Schmidt, Karsten [VerfasserIn]
• Verfasst von: Salg, Gabriel Alexander [VerfasserIn]
• Verfasst von: Kenngott, Hannes Götz [VerfasserIn]
• Verfasst von: Adler, Tim [VerfasserIn]
• Verfasst von: Schreck, Nicholas [VerfasserIn]
• Verfasst von: Kopp-Schneider, Annette [VerfasserIn]
• Verfasst von: Maier-Hein, Klaus H. [VerfasserIn]
• Verfasst von: Maier-Hein, Lena [VerfasserIn]
• Verfasst von: Müller, Beat P. [VerfasserIn]
• Verfasst von: Nickel, Felix [VerfasserIn]
• Titel: Spectral organ fingerprints for machine learning-based intraoperative tissue classification with hyperspectral imaging in a porcine model
• Verf.angabe: Alexander Studier-Fischer, Silvia Seidlitz, Jan Sellner, Berkin Özdemir, Manuel Wiesenfarth, Leonardo Ayala, Jan Odenthal, Samuel Knödler, Karl Friedrich Kowalewski, Caelan Max Haney, Isabella Camplisson, Maximilian Dietrich, Karsten Schmidt, Gabriel Alexander Salg, Hannes Götz Kenngott, Tim Julian Adler, Nicholas Schreck, Annette Kopp-Schneider, Klaus Maier-Hein, Lena Maier-Hein, Beat Peter Müller-Stich and Felix Nickel
• E-Jahr: 2022
• Jahr: 30 June 2022
• Umfang: 14 S.
• Illustrationen: Illustrationen
• Fussnoten: Gesehen am 16.09.2024
• Titel Quelle: Enthalten in: Scientific reports
• Ort Quelle: [London] : Springer Nature, 2011
• Jahr Quelle: 2022
• Band/Heft Quelle: 12(2022), Artikel-ID 11028, Seite 1-14
• ISSN Quelle: 2045-2322
• DOI: doi:10.1038/s41598-022-15040-w
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: Computational biology and bioinformatics
• Sach-SW: Medical research
• K10plus-PPN: 1902605470

Abstract

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.