Philipp M, Bacher N, Saur S, Mathis-Ullrich F, Bruhn A (2022)
Publication Type: Conference contribution
Publication year: 2022
Publisher: IEEE Computer Society
Book Volume: 2022-March
Conference Proceedings Title: Proceedings - International Symposium on Biomedical Imaging
Event location: Kolkata, IND
ISBN: 9781665429238
DOI: 10.1109/ISBI52829.2022.9761704
Recent approaches for surgical activity localization rely on motion features derived from the optical flow (OF). However, although they consider state-of-the-art CNNs when computing the OF, they typically resort to pre-trained implementations which are domain-unaware. We address this problem in two ways: (i) Using the pre-trained OF-CNN of recent localization approach, we analyze the impact of video properties such as reflections, motion and blur on the quality of the OF from neurosurgical data. (ii) Based on this analysis, we design a specifically tailored synthetic training dataset which allows us to customize the pre-trained OF-CNN for surgical activity localization. Our evaluation clearly shows the benefit of this customization approach. It not only leads to an improved accuracy of the OF itself but, even more importantly, also to an improved performance for the actual localization task.
APA:
Philipp, M., Bacher, N., Saur, S., Mathis-Ullrich, F., & Bruhn, A. (2022). From Chairs To Brains: Customizing Optical Flow For Surgical Activity Localization. In Proceedings - International Symposium on Biomedical Imaging. Kolkata, IND: IEEE Computer Society.
MLA:
Philipp, Markus, et al. "From Chairs To Brains: Customizing Optical Flow For Surgical Activity Localization." Proceedings of the 19th IEEE International Symposium on Biomedical Imaging, ISBI 2022, Kolkata, IND IEEE Computer Society, 2022.
BibTeX: Download