Video-based Computer-aided Laparoscopic Bleeding Management: a Space-time Memory Neural Network with Positional Encoding and Adversarial Domain Adaptation

Navid Rabbani, Callyane Seve, Nicolas Bourdel, Adrien Bartoli
Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, PMLR 172:961-974, 2022.

Abstract

One of the main challenges in laparoscopic procedures is handling intraoperative bleeding. We propose video-based Computer-aided Laparoscopic Bleeding Management (CALBM) for early detection and management of intraoperative bleeding. Our system performs the online video-based segmentation of bleeding sources and displays them to the surgeon. It hinges on an improved space-time memory network, which we train from real and semi-synthetic data, using adversarial domain adaptation. Our system improves the IoU and F-Score from 69.97% to 73.40% and 50.23% to 58.09% in comparison to the baseline space-time memory network. It is far better than the prior CALBM systems based on still images, which we reimplemented with DeepLabV3+, reaching an IoU and F-Score of 65.86% and 43.19%. The improvement is also supported by user evaluation.

Cite this Paper

BibTeX
@InProceedings{pmlr-v172-rabbani22a, title = {Video-based Computer-aided Laparoscopic Bleeding Management: a Space-time Memory Neural Network with Positional Encoding and Adversarial Domain Adaptation}, author = {Rabbani, Navid and Seve, Callyane and Bourdel, Nicolas and Bartoli, Adrien}, booktitle = {Proceedings of The 5th International Conference on Medical Imaging with Deep Learning}, pages = {961--974}, year = {2022}, editor = {Konukoglu, Ender and Menze, Bjoern and Venkataraman, Archana and Baumgartner, Christian and Dou, Qi and Albarqouni, Shadi}, volume = {172}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v172/rabbani22a/rabbani22a.pdf}, url = {https://proceedings.mlr.press/v172/rabbani22a.html}, abstract = {One of the main challenges in laparoscopic procedures is handling intraoperative bleeding. We propose video-based Computer-aided Laparoscopic Bleeding Management (CALBM) for early detection and management of intraoperative bleeding. Our system performs the online video-based segmentation of bleeding sources and displays them to the surgeon. It hinges on an improved space-time memory network, which we train from real and semi-synthetic data, using adversarial domain adaptation. Our system improves the IoU and F-Score from 69.97% to 73.40% and 50.23% to 58.09% in comparison to the baseline space-time memory network. It is far better than the prior CALBM systems based on still images, which we reimplemented with DeepLabV3+, reaching an IoU and F-Score of 65.86% and 43.19%. The improvement is also supported by user evaluation.} }
Endnote
%0 Conference Paper %T Video-based Computer-aided Laparoscopic Bleeding Management: a Space-time Memory Neural Network with Positional Encoding and Adversarial Domain Adaptation %A Navid Rabbani %A Callyane Seve %A Nicolas Bourdel %A Adrien Bartoli %B Proceedings of The 5th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2022 %E Ender Konukoglu %E Bjoern Menze %E Archana Venkataraman %E Christian Baumgartner %E Qi Dou %E Shadi Albarqouni %F pmlr-v172-rabbani22a %I PMLR %P 961--974 %U https://proceedings.mlr.press/v172/rabbani22a.html %V 172 %X One of the main challenges in laparoscopic procedures is handling intraoperative bleeding. We propose video-based Computer-aided Laparoscopic Bleeding Management (CALBM) for early detection and management of intraoperative bleeding. Our system performs the online video-based segmentation of bleeding sources and displays them to the surgeon. It hinges on an improved space-time memory network, which we train from real and semi-synthetic data, using adversarial domain adaptation. Our system improves the IoU and F-Score from 69.97% to 73.40% and 50.23% to 58.09% in comparison to the baseline space-time memory network. It is far better than the prior CALBM systems based on still images, which we reimplemented with DeepLabV3+, reaching an IoU and F-Score of 65.86% and 43.19%. The improvement is also supported by user evaluation.
APA
Rabbani, N., Seve, C., Bourdel, N. & Bartoli, A.. (2022). Video-based Computer-aided Laparoscopic Bleeding Management: a Space-time Memory Neural Network with Positional Encoding and Adversarial Domain Adaptation. Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 172:961-974 Available from https://proceedings.mlr.press/v172/rabbani22a.html.

Related Material