@misc{RueckertRiederRauberetal., author = {R{\"u}ckert, Tobias and Rieder, Maximilian and Rauber, David and Xiao, Michel and Humolli, Eg and Feussner, Hubertus and Wilhelm, Dirk and Palm, Christoph}, title = {Augmenting instrument segmentation in video sequences of minimally invasive surgery by synthetic smoky frames}, series = {International Journal of Computer Assisted Radiology and Surgery}, volume = {18}, journal = {International Journal of Computer Assisted Radiology and Surgery}, number = {Suppl 1}, publisher = {Springer Nature}, doi = {10.1007/s11548-023-02878-2}, pages = {S54 -- S56}, language = {en} } @inproceedings{RueckertRiederFeussneretal., author = {Rueckert, Tobias and Rieder, Maximilian and Feussner, Hubertus and Wilhelm, Dirk and Rueckert, Daniel and Palm, Christoph}, title = {Smoke Classification in Laparoscopic Cholecystectomy Videos Incorporating Spatio-temporal Information}, series = {Bildverarbeitung f{\"u}r die Medizin 2024: Proceedings, German Workshop on Medical Image Computing, March 10-12, 2024, Erlangen}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2024: Proceedings, German Workshop on Medical Image Computing, March 10-12, 2024, Erlangen}, editor = {Maier, Andreas and Deserno, Thomas M. and Handels, Heinz and Maier-Hein, Klaus and Palm, Christoph and Tolxdorff, Thomas}, publisher = {Springeer}, address = {Wiesbaden}, doi = {10.1007/978-3-658-44037-4_78}, pages = {298 -- 303}, abstract = {Heavy smoke development represents an important challenge for operating physicians during laparoscopic procedures and can potentially affect the success of an intervention due to reduced visibility and orientation. Reliable and accurate recognition of smoke is therefore a prerequisite for the use of downstream systems such as automated smoke evacuation systems. Current approaches distinguish between non-smoked and smoked frames but often ignore the temporal context inherent in endoscopic video data. In this work, we therefore present a method that utilizes the pixel-wise displacement from randomly sampled images to the preceding frames determined using the optical flow algorithm by providing the transformed magnitude of the displacement as an additional input to the network. Further, we incorporate the temporal context at evaluation time by applying an exponential moving average on the estimated class probabilities of the model output to obtain more stable and robust results over time. We evaluate our method on two convolutional-based and one state-of-the-art transformer architecture and show improvements in the classification results over a baseline approach, regardless of the network used.}, language = {en} }