Surgical workflow recognition with 3DCNN for Sleeve Gastrectomy
International Journal of Computer Assisted Radiology and Surgery · 2021-11 · 16 (11) · 2029-2036
DOI: 10.1007/s11548-021-02473-3 ↗Kurz gefasst
Video/Audio in der Zeitschrift International Journal of Computer Assisted Radiology and Surgery, online erschienen am 20.08.2021. Verfasst von Bokai Zhang und 4 weiteren Autor:innen. Beteiligte Einrichtung: C-SATS, Inc. Johnson & Johnson, 1100 Olive Way, Suite 1100, Seattle, WA, 98101, USA. bzhang29@its.jnj.com. Hauptthemen laut MEDLINE: Neural Networks, Computer, Surgery, Computer-Assisted. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Purpose
Surgical workflow recognition is a crucial and challenging problem when building a computer-assisted surgery system. Current techniques focus on utilizing a convolutional neural network and a recurrent neural network (CNN–RNN) to solve the surgical workflow recognition problem. In this paper, we attempt to use a deep 3DCNN to solve this problem.
Methods
In order to tackle the surgical workflow recognition problem and the imbalanced data problem, we implement a 3DCNN workflow referred to as I3D-FL-PKF. We utilize focal loss (FL) to train a 3DCNN architecture known as Inflated 3D ConvNet (I3D) for surgical workflow recognition. We use prior knowledge filtering (PKF) to filter the recognition results.
Results
We evaluate our proposed workflow on a large sleeve gastrectomy surgical video dataset. We show that focal loss can help to address the imbalanced data problem. We show that our PKF can be used to generate smoothed prediction results and improve the overall accuracy. We show that the proposed workflow achieves 84.16% frame-level accuracy and reaches a weighted Jaccard score of 0.7327 which outperforms traditional CNN–RNN design.
Conclusion
The proposed workflow can obtain consistent and smooth predictions not only within the surgical phases but also for phase transitions. By utilizing focal loss and prior knowledge filtering, our implementation of deep 3DCNN has great potential to solve surgical workflow recognition problems for clinical practice.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- C-SATS, Inc. Johnson & Johnson, 1100 Olive Way, Suite 1100, Seattle, WA, 98101, USA. bzhang29@its.jnj.com.
- C-SATS, Inc. Johnson & Johnson, 1100 Olive Way, Suite 1100, Seattle, WA, 98101, USA.
Zitieren
APA
Zhang, B., Ghanem, A., Simes, A., Choi, H., & Yoo, A. (2021). Surgical workflow recognition with 3DCNN for Sleeve Gastrectomy. International Journal of Computer Assisted Radiology and Surgery, 16(11), 2029-2036. https://doi.org/10.1007/s11548-021-02473-3
Vancouver
Zhang B, Ghanem A, Simes A, Choi H, Yoo A. Surgical workflow recognition with 3DCNN for Sleeve Gastrectomy. International Journal of Computer Assisted Radiology and Surgery. 2021;16(11):2029-2036. doi:10.1007/s11548-021-02473-3
BibTeX
@article{Zhang2021,
author = {Zhang, Bokai and Ghanem, Amer and Simes, Alexander and Choi, Henry and Yoo, Andrew},
title = {Surgical workflow recognition with 3DCNN for Sleeve Gastrectomy},
journal = {International Journal of Computer Assisted Radiology and Surgery},
year = {2021},
volume = {16},
number = {11},
pages = {2029--2036},
doi = {10.1007/s11548-021-02473-3}
}
EUVIMED