Abstract
Occlusion-free video generation is challenging due to surgeons’ obstructions in the camera field of view. Prior work has addressed this issue by installing multiple cameras on a surgical light, hoping some cameras will observe the surgical field with less occlusion. However, this special camera setup poses a new imaging challenge since camera configurations can change every time surgeons move the light, and manual image alignment is required. This paper proposes an algorithm to automate this alignment task. The proposed method detects frames where the lighting system moves, realigns them, and selects the camera with the least occlusion. This algorithm results in a stabilized video with less occlusion. Quantitative results show that our method outperforms conventional approaches. A user study involving medical doctors also confirmed the superiority of our method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
project page: https://github.com/isogawalab/SingleViewSurgicalVideo.
References
Byrd, R.J., Ujjin, V.M., Kongchan, S.S., Reed, H.D.: Surgical lighting system with integrated digital video camera. US6633328B1 (2003)
Date, I., Morita, A., Kenichiro, K.: NS NOW Updated No.9 Thorough Knowledge and Application of Device and Information Technology (IT) for Neurosurgical Opperation. Medical View Co., Ltd. (2017)
Guilluy, W., Beghdadi, A., Oudre, L.: A performance evaluation framework for video stabilization methods. In: 2018 7th European Workshop on Visual Information Processing (EUVIP), pp. 1–6 (2018)
Hachiuma, R., Shimizu, T., Saito, H., Kajita, H., Takatsume, Y.: Deep selection: a fully supervised camera selection network for surgery recordings. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12263, pp. 419–428. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59716-0_40
Hanada, E.: [special talk] video recording, storing, distributing and editing system for surgical operation. In: ITE Technical Report, pp. 77–80. The Institute of Image Information and Television Engineers (2017). in Japanese
Kajita, H.: Surgical video recording and application of deep learning for open surgery. J. Japan Soc. Comput. Aided Surg. 23(2), 59–64 (2021). in Japanese
Kumar, A.S., Pal, H.: Digital video recording of cardiac surgical procedures. Ann. Thorac. Surg. 77(3), 1063–1065 (2004)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60, 91–110 (2004)
Nair, A.G., et al.: Surgeon point-of-view recording: using a high-definition head-mounted video camera in the operating room. Indian J. Ophthalmol. 63(10), 771–774 (2015)
Obayashi, M., Mori, S., Saito, H., Kajita, H., Takatsume, Y.: Multi-view surgical camera calibration with none-feature-rich video frames: toward 3D surgery playback. Appl. Sci. 13(4), 2447 (2023)
Saito, Y., Hachiuma, R., Saito, H., Kajita, H., Takatsume, Y., Hayashida, T.: Camera selection for occlusion-less surgery recording via training with an egocentric camera. IEEE Access 9, 138307–138322 (2021)
Shimizu, T., Oishi, K., Hachiuma, R., Kajita, H., Takatsume, Y., Saito, H.: Surgery recording without occlusions by multi-view surgical videos. In: VISIGRAPP (5: VISAPP), pp. 837–844 (2020)
Yoshida, K., et al.: Spatiotemporal video highlight by neural network considering gaze and hands of surgeon in egocentric surgical videos. J. Med. Robot. Res. 7, 2141001 (2022)
Acknowledgements
This work was partially supported by JSPS KAKENHI Grant Number 22H03617.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kato, Y., Isogawa, M., Mori, S., Saito, H., Kajita, H., Takatsume, Y. (2023). High-Quality Virtual Single-Viewpoint Surgical Video: Geometric Autocalibration of Multiple Cameras in Surgical Lights. In: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. MICCAI 2023. Lecture Notes in Computer Science, vol 14228. Springer, Cham. https://doi.org/10.1007/978-3-031-43996-4_26
Download citation
DOI: https://doi.org/10.1007/978-3-031-43996-4_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43995-7
Online ISBN: 978-3-031-43996-4
eBook Packages: Computer ScienceComputer Science (R0)
