Publications by authors named "Stefanie Krell"
Introduction: Complex oncological procedures pose various surgical challenges including dissection in distinct tissue planes and preservation of vulnerable anatomical structures throughout different surgical phases. In rectal surgery, violation of dissection planes increases the risk of local recurrence and autonomous nerve damage resulting in incontinence and sexual dysfunction. This work explores the feasibility of phase recognition and target structure segmentation in robot-assisted rectal resection (RARR) using machine learning.
View Article and Find Full Text PDFArticle Synopsis
- Lack of anatomy recognition in abdominal surgery poses a significant risk, and machine learning (ML) could potentially help identify important anatomical structures.
- A study created advanced segmentation models using a dataset of 13,195 laparoscopic images, comparing their performance to that of a group of 28 human participants on pancreas segmentation.
- Results showed that the ML models, particularly the DeepLabv3-based models, significantly outperformed most human participants and can operate in near-real-time, suggesting ML's valuable role in assisting with anatomy recognition in minimally invasive surgeries.