Improved Heatmap-based Landmark Detection
This work addresses a domain-specific challenge in surgical training by improving landmark detection for suture localization in endoscopic images, though it is incremental as it builds on existing methods like cycleGAN and heatmap-based detection.
This paper tackles the problem of detecting suture points in endoscopic images for mitral valve repair, using a landmark detection network and cycleGAN for domain adaptation, achieving a mean sensitivity of 75.64% and precision of 73.62% on simulated data, and 50.23% sensitivity and 62.76% precision on real intraoperative data.
Mitral valve repair is a very difficult operation, often requiring experienced surgeons. The doctor will insert a prosthetic ring to aid in the restoration of heart function. The location of the prosthesis' sutures is critical. Obtaining and studying them during the procedure is a valuable learning experience for new surgeons. This paper proposes a landmark detection network for detecting sutures in endoscopic pictures, which solves the problem of a variable number of suture points in the images. Because there are two datasets, one from the simulated domain and the other from real intraoperative data, this work uses cycleGAN to interconvert the images from the two domains to obtain a larger dataset and a better score on real intraoperative data. This paper performed the tests using a simulated dataset of 2708 photos and a real dataset of 2376 images. The mean sensitivity on the simulated dataset is about 75.64% and the precision is about 73.62%. The mean sensitivity on the real dataset is about 50.23% and the precision is about 62.76%. The data is from the AdaptOR MICCAI Challenge 2021, which can be found at https://zenodo.org/record/4646979\#.YO1zLUxCQ2x.