Improved Heatmap-based Landmark Detection

TL;DR

This paper introduces a landmark detection network for sutures in endoscopic images, utilizing cycleGAN for domain adaptation, achieving moderate sensitivity and precision on simulated and real datasets from mitral valve repair procedures.

Contribution

It presents a novel landmark detection network combined with cycleGAN-based domain transfer to improve suture detection in endoscopic images.

Findings

Mean sensitivity of 75.64% on simulated data

Mean sensitivity of 50.23% on real data

CycleGAN improves dataset diversity and detection performance

Abstract

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.