Hybrid Learning System for Large-Scale Medical Image Analysis
Abstract
Adequate annotated data cannot always be satisfied in medical imaging applications. To address such a challenge, we would explore ways to reduce the quality and quantity of annotations requirements of the deep learning model by developing a hybrid learning system. We combined self-supervised learning, semi-supervised learning and weak-supervised learning to improve annotation utilization. Our primary research work on 2D medical image detection under poor annotation conditions has found that better regularization and adversarial loss can improve the robustness and performance with poor annotation conditions.
Cite
Text
Cheng and Wu. "Hybrid Learning System for Large-Scale Medical Image Analysis." International Joint Conference on Artificial Intelligence, 2022. doi:10.24963/IJCAI.2022/824Markdown
[Cheng and Wu. "Hybrid Learning System for Large-Scale Medical Image Analysis." International Joint Conference on Artificial Intelligence, 2022.](https://mlanthology.org/ijcai/2022/cheng2022ijcai-hybrid/) doi:10.24963/IJCAI.2022/824BibTeX
@inproceedings{cheng2022ijcai-hybrid,
title = {{Hybrid Learning System for Large-Scale Medical Image Analysis}},
author = {Cheng, Zehua and Wu, Lianlong},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2022},
pages = {5843-5844},
doi = {10.24963/IJCAI.2022/824},
url = {https://mlanthology.org/ijcai/2022/cheng2022ijcai-hybrid/}
}