High-confidence pseudo-labels for domain adaptation in COVID-19 detection (2403.13509v1)
Abstract: This paper outlines our submission for the 4th COV19D competition as part of the `Domain adaptation, Explainability, Fairness in AI for Medical Image Analysis' (DEF-AI-MIA) workshop at the Computer Vision and Pattern Recognition Conference (CVPR). The competition consists of two challenges. The first is to train a classifier to detect the presence of COVID-19 from over one thousand CT scans from the COV19-CT-DB database. The second challenge is to perform domain adaptation by taking the dataset from Challenge 1 and adding a small number of scans (some annotated and other not) for a different distribution. We preprocessed the CT scans to segment the lungs, and output volumes with the lungs individually and together. We then trained 3D ResNet and Swin Transformer models on these inputs. We annotated the unlabeled CT scans using an ensemble of these models and chose the high-confidence predictions as pseudo-labels for fine-tuning. This resulted in a best cross-validation mean F1 score of 93.39\% for Challenge 1 and a mean F1 score of 92.15 for Challenge 2.
- Deep transparent prediction through latent representation analysis. arXiv preprint arXiv:2009.07044, 2020a.
- Transparent adaptation in deep medical image diagnosis. In TAILOR, page 251–267, 2020b.
- Domain adaptation, explainability & fairness in ai for medical image analysis: Diagnosis of covid-19 based on 3-d chest ct-scans. arXiv preprint arXiv:2403.02192, 2024.
- Mia-cov19d: Covid-19 detection through 3-d chest ct image analysis. In Proceedings of the IEEE/CVF International Conference on Computer Vision, page 537–544, 2021.
- Ai-mia: Covid-19 detection and severity analysis through medical imaging. In European Conference on Computer Vision, page 677–690. Springer, 2022.
- Ai-enabled analysis of 3-d ct scans for diagnosis of covid-19 & its severity. In 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), page 1–5. IEEE, 2023a.
- Data-driven covid-19 detection through medical imaging. In 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), page 1–5. IEEE, 2023.
- A deep neural architecture for harmonizing 3-d input data analysis and decision making in medical imaging. Neurocomputing, 542:126244, 2023b.
- A large imaging database and novel deep neural architecture for covid-19 diagnosis. In 2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP), page 1–5. IEEE, 2022.
- Robert Turnbull. Using a 3D ResNet for Detecting the Presence and Severity of COVID-19 from CT Scans. In Leonid Karlinsky, Tomer Michaeli, and Ko Nishino, editors, Computer Vision – ECCV 2022 Workshops, number 7, pages 663–676, Cham, 2023a. Springer Nature. ISBN 978-3-031-25082-8. doi:10.1007/978-3-031-25082-8_45.
- Robert Turnbull. Lung segmentation enhances covid-19 detection. In 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), pages 1–5, 2023b. doi:10.1109/ICASSPW59220.2023.10193492.
- Study of thoracic ct in covid-19: The stoic project. Radiology, 301(1):E361–E370, 2021. doi:10.1148/radiol.2021210384. URL https://doi.org/10.1148/radiol.2021210384. PMID: 34184935.
- Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 770–778, 2016. doi:10.1109/CVPR.2016.90.
- A closer look at spatiotemporal convolutions for action recognition. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6450–6459, 2018. doi:10.1109/CVPR.2018.00675.
- Video swin transformer, 2021. URL https://arxiv.org/abs/2106.13230.
- The kinetics human action video dataset, 2017. URL https://arxiv.org/abs/1705.06950.
- Adam: A method for stochastic optimization, 2014. URL https://arxiv.org/abs/1412.6980.
- Dong-Hyun Lee et al. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In Workshop on challenges in representation learning, ICML, volume 3, page 896. Atlanta, 2013.