SF-TMN: SlowFast temporal modeling network for surgical phase recognition.

PURPOSE: Automatic surgical phase recognition is crucial for video-based assessment systems in surgical education. Utilizing temporal information is crucial for surgical phase recognition; hence, various recent approaches extract frame-level features to conduct full video temporal modeling. METHODS: For better temporal modeling, we propose SlowFast temporal modeling network (SF-TMN) for offline surgical phase recognition that can achieve not only frame-level full video temporal modeling but also segment-level full video temporal modeling. We employ a feature extraction network, pretrained on the target dataset, to extract features from video frames as the training data for SF-TMN. The Slow Path in SF-TMN utilizes all frame features for frame temporal modeling. The Fast Path in SF-TMN utilizes segment-level features summarized from frame features for segment temporal modeling. The proposed paradigm is flexible regarding the choice of temporal modeling networks. RESULTS: We explore MS-TCN and ASFormer as temporal modeling networks and experiment with multiple combination strategies for Slow and Fast Paths. We evaluate SF-TMN on Cholec80 and Cataract-101 surgical phase recognition tasks and demonstrate that SF-TMN can achieve state-of-the-art results on all considered metrics. SF-TMN with ASFormer backbone outperforms the state-of-the-art Swin BiGRU by approximately 1% in accuracy and 1.5% in recall on Cholec80. We also evaluate SF-TMN on action segmentation datasets including 50salads, GTEA, and Breakfast, and achieve state-of-the-art results. CONCLUSION: The improvement in the results shows that combining temporal information from both frame level and segment level by refining outputs with temporal refinement stages is beneficial for the temporal modeling of surgical phases.

Surgical workflow recognition with 3DCNN for Sleeve Gastrectomy.

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.

Predictors of Cardiac Perforation With Catheter Ablation of Atrial Fibrillation.

OBJECTIVES: This study identified factors associated with risk for cardiac perforation in the setting of atrial fibrillation (AF) ablation in contemporary clinical practice. BACKGROUND: Cardiac perforation is an uncommon but potentially fatal complication of AF ablation. An improved understanding of factors associated with cardiac perforation could facilitate improvements in procedural safety. METHODS: Logistic regression models were used to assess predictors of cardiac perforation among Medicare beneficiaries who underwent AF ablation from July 1, 2013 and December 31, 2017. Cardiac perforation was defined as a diagnosis of hemopericardium, cardiac tamponade, or pericardiocentesis, within 30 days of AF ablation. RESULTS: Of 102,398 patients who underwent AF ablation, 0.61% (n = 623) experienced cardiac perforation as a procedural complication. Rates of cardiac perforation decreased over time. In adjusted analyses of the overall population, female sex (odds ratio [OR]: 1.34; 95% confidence interval [CI]: 1.14 to 1.58; p = 0.0004), obesity (OR: 1.35; 95% CI: 1.09 to 1.68; p = 0.0050), and absence of intracardiac echocardiography (ICE) (OR: 4.85; 95% CI: 4.11 to 5.71; p < 0.0001) were associated with increased risk for cardiac perforation, whereas previous cardiac surgery (OR: 0.14; 95% CI: 0.07 to 0.26; p < 0.0001) was associated with a lower risk for perforation. Patient risk factors for cardiac perforation were identical in the subset of patients in whom ICE was used (n = 76,134). A risk score was generated with the following point assignments: female sex (1 point); obesity (1 point); nonuse of ICE (5 points); and previous cardiac surgery (-6 points). CONCLUSIONS: Cardiac perforation is a rare complication of AF ablation; incidence has decreased over time. One of the strongest predictors of cardiac perforation in the contemporary era is a modifiable factor, use of intraprocedural ICE.