Key result
C-ECT achieves ~95% accuracy for online surgical phase recognition, outperforming state-of-the-art methods.
Why the study?
Automatic online recognition of surgical phases can help surgical teams make better decisions to improve surgical outcomes, but current AI approaches can be improved.
Does the Cross-Enhancement Causal Transformer (C-ECT) improve the accuracy of online surgical phase recognition compared to current state-of-the-art AI approaches?
Does the Cross-Enhancement Causal Transformer (C-ECT) improve the accuracy of online surgical phase recognition compared to current state-of-the-art AI approaches?
The proposed C-ECT architecture significantly improves the accuracy of online surgical phase recognition compared to existing state-of-the-art AI methods.
C-ECT advances technical accuracy in surgical phase recognition; leaves open prospective validation for clinical workflow integration or outcomes.
Automatic online recognition of surgical phases can provide insight that can help surgical teams make better decisions that may lead to better surgical outcomes. Current state-of-the-art AI approaches for surgical phase recognition utilize both spatial and temporal information to learn context awareness in surgical videos. We propose the use of EfficientNetV2 for spatial feature extraction and we design Cross-Enhancement Causal Transformer (C-ECT) by modifying previous transformer-based architectures for temporal modeling to achieve online surgical phase recognition. Additionally, we propose Cross-Attention Feature Fusion (CAFF) to better integrate the global and local information in our C-ECT. We show that our approach can achieve 94.9% accuracy on the Cholec80 dataset which improves upon the current state-of-the-art method by approximately 3% in accuracy and precision, 2% in the recall, and 4% in terms of the Jaccard score.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2023) studied Surgical phase recognition. Cross-Enhancement Causal Transformer (C-ECT) vs. Current state-of-the-art AI approaches was evaluated on Accuracy on the Cholec80 dataset. The Cross-Enhancement Causal Transformer (C-ECT) achieved 94.9% accuracy for online surgical phase recognition on the Cholec80 dataset, improving upon state-of-the-art methods by approximately 3%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: