Stammdaten

Titel: Evaluating the Generalization Performance of Instrument Classification in Cataract Surgery Videos
Untertitel:
Kurzfassung:

In the field of ophthalmic surgery, many clinicians nowadays record their microscopic procedures with a video camera and use the recorded footage for later purpose, such as forensics, teaching, or training. However, in order to efficiently use the video material after surgery, the video content needs to be analyzed automatically. Important semantic content to be analyzed and indexed in these short videos are operation instruments, since they provide an indication of the corresponding operation phase and surgical action. Related work has already shown that it is possible to accurately detect instruments in cataract surgery videos. However, their underlying dataset (from the CATARACTS challenge) has very good visual quality, which is not reflecting the typical quality of videos acquired in general hospitals. In this paper, we therefore analyze the generalization performance of deep learning models for instrument recognition in terms of dataset change. More precisely, we trained such models as ResNet-50, Inception v3 and NASNet Mobile using a dataset of high visual quality (CATARACT) and test it on another dataset with low visual quality (Cataract-101), and vice versa. Our results show that the generalizability is rather low in general, but clearly worse for the model trained on the high-quality dataset. Another important observation is the fact that the trained models are able to detect similar instruments in the other dataset even if their appearance is different.

Schlagworte: Instrument classification, Cataract surgery videos, Deep learning
Publikationstyp: Beitrag in Proceedings (Autorenschaft)
Art der Veröffentlichung Online Publikation
Erschienen in: Proceedings of the 26th International Conference in MultiMedia Modeling (MMM 2020) (Part II)
Proceedings of the 26th International Conference in MultiMedia Modeling (MMM 2020) (Part II)
zur Publikation
 ( Springer; W. Cheng, J. Kim, W. Chu, P. Cui, J. Choi, M. Hu, W. De Neve )
Erscheinungsdatum: 24.12.2019
Titel der Serie: Lecture Notes in Computer Science
Bandnummer: 11962
Erstveröffentlichung: Ja
Version: -
Seite: S. 626 - 636

Identifikatoren

Zuordnung

Organisation Adresse
Fakultät für Technische Wissenschaften
 
Institut für Informationstechnologie
Universitaetsstr. 65-67
9020  Klagenfurt am Wörthersee
Österreich
  -3699
   martina.steinbacher@uni-klu.ac.at
http://itec.aau.at/
zur Organisation
Universitaetsstr. 65-67
AT - 9020  Klagenfurt am Wörthersee

Kategorisierung

Sachgebiete
  • 102020 - Medizinische Informatik (305905)
Forschungscluster Kein Forschungscluster ausgewählt
Peer Reviewed
  • Ja
Publikationsfokus
  • Science to Science (Qualitätsindikator: II)
Klassifikationsraster der zugeordneten Organisationseinheiten:
Arbeitsgruppen
  • Distributed Multimedia Systems

Kooperationen

Organisation Adresse
KABEG Klinikum Klagenfurt
Feschnigstraße 11
9020  Klagenfurt
Österreich
http://www.klinikum-klagenfurt.at/
Feschnigstraße 11
AT - 9020  Klagenfurt

Beiträge der Publikation

Keine verknüpften Publikationen vorhanden