@InProceedings{Leibetseder2017, author = {Leibetseder, Andreas and Primus, Manfred Jürgen and Petscharnig, Stefan and Schoeffmann, Klaus}, booktitle = {Computer Assisted and Robotic Endoscopy and Clinical Image-Based Procedures: 4th International Workshop, CARE 2017, and 6th International Workshop, CLIP 2017, Held in Conjunction with MICCAI 2017, Qu{\'e}bec City, QC, Canada, September 14, 2017, Proceedings}, title = {Image-Based Smoke Detection in Laparoscopic Videos}, year = {2017}, address = {Cham, Schweiz}, editor = {Cardoso, M Jorge and Arbel, Tal and Luo, Xiongbiao and Wesarg, Stefan and Reichl, Tobias and Gonzalez Ballester, Miguel Angel and McLeod, Jonathan and Drechsler, Klaus and Peters, Terry and Erdt, Marius and Mori, Kensaku and Linguraru, Marius George and Uhl, Andreas and Oyarzun Laura, Cristina and Shekhar, Raj}, month = {jan}, pages = {70--87}, publisher = {Springer International Publishing}, abstract = {The development and improper removal of smoke during minimally invasive surgery (MIS) can considerably impede a patient's treatment, while additionally entailing serious deleterious health effects. Hence, state-of-the-art surgical procedures employ smoke evacuation systems, which often still are activated manually by the medical staff or less commonly operate automatically utilizing industrial, highly-specialized and operating room (OR) approved sensors. As an alternate approach, video analysis can be used to take on said detection process -- a topic not yet much researched in aforementioned context. In order to advance in this sector, we propose utilizing an image-based smoke classification task on a pre-trained convolutional neural network (CNN). We provide a custom data set of over 30 000 laparoscopic smoke/non-smoke images, part of which served as training data for GoogLeNet-based [41] CNN models. To be able to compare our research for evaluation, we separately developed a non-CNN classifier based on observing the saturation channel of a sample picture in the HSV color space. While the deep learning approaches yield excellent results with Receiver Operating Characteristic (ROC) curves enclosing areas of over 0.98, the computationally much less costly analysis of an image's saturation histogram under certain circumstances can, surprisingly, as well be a good indicator for smoke with areas under the curves (AUCs) of around 0.92--0.97.}, doi = {10.1007/978-3-319-67543-5_7}, edition = {LNCS}, language = {EN}, location = {Québec City, Kanada}, talkdate = {2017.09.14}, talktype = {registered}, url = {https://doi.org/10.1007/978-3-319-67543-5_7} }