Uncertainty-aware organ classification for surgical data science applications in laparoscopy

• Verfasst von: Moccia, Sara [VerfasserIn]
• Verfasst von: Wirkert, Sebastian J. [VerfasserIn]
• Verfasst von: Kenngott, Hannes Götz [VerfasserIn]
• Verfasst von: Vemuri, Anant S. [VerfasserIn]
• Verfasst von: Apitz, Martin [VerfasserIn]
• Verfasst von: Mayer, Benjamin [VerfasserIn]
• Verfasst von: De Momi, Elena [VerfasserIn]
• Verfasst von: Mattos, Leonardo S. [VerfasserIn]
• Verfasst von: Maier-Hein, Lena [VerfasserIn]
• Titel: Uncertainty-aware organ classification for surgical data science applications in laparoscopy
• Verf.angabe: Sara Moccia, Sebastian J. Wirkert, Hannes Kenngott, Anant S. Vemuri, Martin Apitz, Benjamin Mayer, Elena De Momi, Senior Member, IEEE, Leonardo S. Mattos, Member, IEEE, and Lena Maier-Hein
• E-Jahr: 2018
• Jahr: 9 March 2018
• Umfang: 11 S.
• Fussnoten: Gesehen am 30.04.2020
• Titel Quelle: Enthalten in: Institute of Electrical and Electronics EngineersIEEE transactions on biomedical engineering
• Ort Quelle: New York, NY : IEEE, 1964
• Jahr Quelle: 2018
• Band/Heft Quelle: 65(2018), 11, Seite 2649-2659
• ISSN Quelle: 1558-2531
• DOI: doi:10.1109/TBME.2018.2813015
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: Animals
• Sach-SW: Digestive System
• Sach-SW: Digestive System Surgical Procedures
• Sach-SW: Image Processing, Computer-Assisted
• Sach-SW: Laparoscopy
• Sach-SW: Spleen
• Sach-SW: Swine
• Sach-SW: Video Recording
• K10plus-PPN: 1696943191

Abstract

OBJECTIVE: Surgical data science is evolving into a research field that aims to observe everything occurring within and around the treatment process to provide situation-aware data-driven assistance. In the context of endoscopic video analysis, the accurate classification of organs in the field of view of the camera proffers a technical challenge. Herein, we propose a new approach to anatomical structure classification and image tagging that features an intrinsic measure of confidence to estimate its own performance with high reliability and which can be applied to both RGB and multispectral imaging (MI) data. - METHODS: Organ recognition is performed using a superpixel classification strategy based on textural and reflectance information. Classification confidence is estimated by analyzing the dispersion of class probabilities. Assessment of the proposed technology is performed through a comprehensive in vivo study with seven pigs. - RESULTS: When applied to image tagging, mean accuracy in our experiments increased from 65% (RGB) and 80% (MI) to 90% (RGB) and 96% (MI) with the confidence measure. - CONCLUSION: Results showed that the confidence measure had a significant influence on the classification accuracy, and MI data are better suited for anatomical structure labeling than RGB data. - SIGNIFICANCE: This paper significantly enhances the state of art in automatic labeling of endoscopic videos by introducing the use of the confidence metric, and by being the first study to use MI data for in vivo laparoscopic tissue classification. The data of our experiments will be released as the first in vivo MI dataset upon publication of this paper.