No abstract

Aims The GermAn Laser Lead Extraction GallerY (GALLERY) is a retrospective, national multicentre registry, investigating the safety and efficacy of laser lead extraction procedures in Germany. Methods and results Twenty-four German centres that are performing laser lead extraction have participated in the registry. All patients, treated with a laser lead extraction procedure between January 2013 and March 2017, were consecutively enrolled. Safety and efficacy of laser lead extraction were investigated. A total number of 2524 consecutive patients with 6117 leads were included into the registry. About 5499 leads with a median lead dwell time of 96 (62–141) months were treated. The mean number of treated leads per patient was 2.18 ± 1.02. The clinical procedural success rate was 97.86% and the complete lead removal was observed in 94.85%. Additional extraction tools were used in 6.65% of cases. The rate of procedural failure was 2.14% with lead age  ≥10 years being its only predictor. The overall complication rate was 4.32%, including 2.06% major and 2.26% minor complications. Procedure-related mortality was 0.55%. Female sex and the presence of abandoned leads were predictors for procedure-related complications. The all-cause in-hospital mortality was 3.56% with systemic infection being the strongest predictor, followed by age ≥75 years and chronic kidney disease. Conclusion In the GALLERY, a high success- and low procedure-related complication rates have been demonstrated. In multivariate analysis, female sex and the presence of abandoned leads were predictors for procedure-related complications, while the presence of systemic infection, age ≥75 years, and chronic kidney disease were independent predictors for all-cause mortality.

Purpose: Mitral valve repair is a complex minimally invasive surgery of the heart valve. In this context, suture detection from endoscopic images is a highly relevant task that provides quantitative information to analyse suturing patterns, assess prosthetic configurations and produce augmented reality visualisations. Facial or anatomical landmark detection tasks typically contain a fixed number of landmarks, and use regression or fixed heatmap-based approaches to localize the landmarks. However in endoscopy, there are a varying number of sutures in every image, and the sutures may occur at any location in the annulus, as they are not semantically unique. Method: In this work, we formulate the suture detection task as a multi-instance deep heatmap regression problem, to identify entry and exit points of sutures. We extend our previous work, and introduce the novel use of a 2D Gaussian layer followed by a differentiable 2D spatial Soft-Argmax layer to function as a local non-maximum suppression. Results: We present extensive experiments with multiple heatmap distribution functions and two variants of the proposed model. In the intra-operative domain, Variant 1 showed a mean $$F_1$$ F 1 of $$+ 0.0422$$ + 0.0422 over the baseline. Similarly, in the simulator domain, Variant 1 showed a mean $$F_1$$ F 1 of $$+ 0.0865$$ + 0.0865 over the baseline. Conclusion: The proposed model shows an improvement over the baseline in the intra-operative and the simulator domains. The data is made publicly available within the scope of the MICCAI AdaptOR2021 Challenge https://adaptor2021.github.io/, and the code at https://github.com/Cardio-AI/suture-detection-pytorch/.