no code implementations • 26 Nov 2022 • Vladimir Poliakov, Kenan Niu, Emmanuel Vander Poorten, Dzmitry Tsetserukou
This work presents an RL-based agent for outpatient hysteroscopy training.
no code implementations • 7 Sep 2020 • Luis C. García-Peraza-Herrera, Wenqi Li, Caspar Gruijthuijsen, Alain Devreker, George Attilakos, Jan Deprest, Emmanuel Vander Poorten, Danail Stoyanov, Tom Vercauteren, Sébastien Ourselin
The latter, a combination of deep learning with optical flow tracking, yields an average balanced accuracy of 78. 2% across all the validated datasets.
1 code implementation • 8 Jul 2020 • Sophia Bano, Francisco Vasconcelos, Luke M. Shepherd, Emmanuel Vander Poorten, Tom Vercauteren, Sebastien Ourselin, Anna L. David, Jan Deprest, Danail Stoyanov
We propose a solution utilising the U-Net architecture for performing placental vessel segmentation in fetoscopic videos.
1 code implementation • 15 Jul 2019 • Sophia Bano, Francisco Vasconcelos, Marcel Tella Amo, George Dwyer, Caspar Gruijthuijsen, Jan Deprest, Sebastien Ourselin, Emmanuel Vander Poorten, Tom Vercauteren, Danail Stoyanov
Mosaicking can align multiple overlapping images to generate an image with increased FoV, however, existing techniques apply poorly to fetoscopy due to the low visual quality, texture paucity, and hence fail in longer sequences due to the drift accumulated over time.
no code implementations • 17 Sep 2017 • Thomas Probst, Kevis-Kokitsi Maninis, Ajad Chhatkuli, Mouloud Ourak, Emmanuel Vander Poorten, Luc van Gool
In recent works, such interventions are conducted under a stereo-microscope, and with a robot-controlled surgical tool.
no code implementations • 25 Jun 2017 • Luis C. Garcia-Peraza-Herrera, Wenqi Li, Lucas Fidon, Caspar Gruijthuijsen, Alain Devreker, George Attilakos, Jan Deprest, Emmanuel Vander Poorten, Danail Stoyanov, Tom Vercauteren, Sebastien Ourselin
We propose the use of parametric rectified linear units for semantic labeling in these small architectures to increase the regularization ability of the design and maintain the segmentation accuracy without overfitting the training sets.