👩⚕️ Identification and Localization COVID-19 Abnormalities on Chest Radiographs
📋 News
- [2023.01.02] Paper is accepted to AICV 2023.
- [2022.09.06] Create baseline.
🦠 Main results
Evaluation of the COVID-19 lesion detector on the SIIM test set:
Detector | Accuracy (mAP@ IoU 0.5:0.95) | Performance | |||
---|---|---|---|---|---|
Discrete model | Lung localized | Inference speed (FPS) | GPU memory requirement (MB) | Model size (MB) | |
DETR | 0.542 | 0.587 | 25 | 2683 | 232 |
Yolov7 | 0.563 | 0.591 | 34 | 3520 | 290 |
EfficientDet | 0.499 | 0.574 | 19 | 1903 | 187 |
Weighted Box Fusion | 0.605 | 0.612 | 8 | 8106 | 709 |
💉 Installation
Please refer to INSTALL.md for installation instructions.
🧬 Model zoo
Trained models are available in the MODEL_ZOO.md.
💻 Dataset zoo
Please see DATASET_ZOO.md for detailed description of the training/evaluation datasets.
🔍 Getting Started
Follow the aforementioned instructions to install environments and download models and datasets.
GETTING_STARTED.md provides a brief intro of the usage of builtin command-line tools.
🔬 Citing
If you use this work in your research or wish to refer to the results, please use the following BibTeX entry.
@inproceedings{pham2023identification,
title={Identification and localization COVID-19 abnormalities on chest radiographs},
author={Pham, Van Tien and Nguyen, Thanh Phuong},
booktitle={The International Conference on Artificial Intelligence and Computer Vision},
pages={251--261},
year={2023},
organization={Springer}
}