KIT | KIT-Bibliothek | Impressum | Datenschutz

Evaluation of Methods for Semantic Segmentation of Endoscopic Images

Bopp, Bastian; Scheikl, Paul Maria; Kunz, Christian; Mathis-Ullrich, Franziska

Abstract (englisch):
We examined multiple semantic segmentation methods, which consider the information contained in endoscopic images at different levels of abstraction in order to predict semantic segmentation masks. These segmentations can be used to obtain position information of surgical instruments in endoscopic images, which is the foundation for many computer assisted systems, such as automatic instrument tracking systems. The methods in this paper were examined and compared in regard to their accuracy, effort to create the data set, and inference time. Of all the investigated approaches, the LinkNet34 encoder-decoder network scored best, achieving an Intersection over Union score of 0.838 with an inference time of 30.25 ms on a 640 x 480 pixel input image with a NVIDIA GTX 1070Ti GPU.

Open Access Logo


Volltext §
DOI: 10.5445/IR/1000097120
Veröffentlicht am 16.09.2019
Coverbild
Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Sonstiges
Jahr 2019
Sprache Englisch
Identifikator KITopen-ID: 1000097120
Bemerkung zur Veröffentlichung IEEE International Conference on Robotics and Automation - Workshop: Open Challenges and State-of-the-Art in Control System Design and Technology Development for Surgical Robotic Systems (ICRA 2019), Montreal, Kanada, 20 - 24 Mai 2019
Schlagworte robot-assisted surgery, computer vision, semantic image segmentation, deep learning
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page