Frame-by-frame annotation of bounding boxes by clinical experts is often required to train fully supervised object detection models on medical video data. We propose a method for improving object detection in medical videos through weak supervision from video-level labels. More concretely, we aggregate individual detection predictions into video-level predictions and extend a teacher-student training strategy to provide additional supervision via a video-level loss. We also introduce improvements to the underlying teacher-student framework, including methods to improve the quality of pseudo-labels based on weak supervision and adaptive schemes to optimize knowledge transfer between the student and teacher networks. We apply this approach to the clinically important task of detecting lung consolidations (seen in respiratory infections such as COVID-19 pneumonia) in medical ultrasound videos. Experiments reveal that our framework improves detection accuracy and robustness compared to baseline semi-supervised models, and improves efficiency in data and annotation usage.
@article{arxiv.2308.04463,
title = {Weakly Semi-Supervised Detection in Lung Ultrasound Videos},
author = {Jiahong Ouyang and Li Chen and Gary Y. Li and Naveen Balaraju and Shubham Patil and Courosh Mehanian and Sourabh Kulhare and Rachel Millin and Kenton W. Gregory and Cynthia R. Gregory and Meihua Zhu and David O. Kessler and Laurie Malia and Almaz Dessie and Joni Rabiner and Di Coneybeare and Bo Shopsin and Andrew Hersh and Cristian Madar and Jeffrey Shupp and Laura S. Johnson and Jacob Avila and Kristin Dwyer and Peter Weimersheimer and Balasundar Raju and Jochen Kruecker and Alvin Chen},
journal= {arXiv preprint arXiv:2308.04463},
year = {2023}
}