Computational Evaluation of the Combination of Semi-Supervised and Active Learning for Histopathology Image Segmentation with Missing Annotations

Laura Gálvez Jiménez, Lucile Dierckx, Maxime Amodei, Hamed Razavi Khosroshahi, Natarajan Chidambaram, Anh-Thu Phan Ho, Alberto Franzin

ICCVW 2023 pp. 2544-2555

doi:10.1109/ICCVW60793.2023.00269 /iccvw/2023/jimenez2023iccvw-computational/

Abstract

Real-world segmentation tasks in digital pathology require a great effort from human experts to accurately annotate a sufficiently high number of images. Hence, there is a huge interest in methods that can make use of non-annotated samples, to alleviate the burden on the annotators. In this work, we evaluate two classes of such methods, semi-supervised and active learning, and their combination on a version of the GlaS dataset for gland segmentation in colorectal cancer tissue with missing annotations. Our results show that semi-supervised learning benefits from the combination with active learning and outperforms fully supervised learning on a dataset with missing annotations. However, an active learning procedure alone with a simple selection strategy obtains results of comparable quality.

PDF ICCVW Semantic Scholar

Cite

Text

Jiménez et al. "Computational Evaluation of the Combination of Semi-Supervised and Active Learning for Histopathology Image Segmentation with Missing Annotations." IEEE/CVF International Conference on Computer Vision Workshops, 2023. doi:10.1109/ICCVW60793.2023.00269

Markdown

[Jiménez et al. "Computational Evaluation of the Combination of Semi-Supervised and Active Learning for Histopathology Image Segmentation with Missing Annotations." IEEE/CVF International Conference on Computer Vision Workshops, 2023.](https://mlanthology.org/iccvw/2023/jimenez2023iccvw-computational/) doi:10.1109/ICCVW60793.2023.00269

BibTeX

@inproceedings{jimenez2023iccvw-computational,
  title     = {{Computational Evaluation of the Combination of Semi-Supervised and Active Learning for Histopathology Image Segmentation with Missing Annotations}},
  author    = {Jiménez, Laura Gálvez and Dierckx, Lucile and Amodei, Maxime and Khosroshahi, Hamed Razavi and Chidambaram, Natarajan and Ho, Anh-Thu Phan and Franzin, Alberto},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2023},
  pages     = {2544-2555},
  doi       = {10.1109/ICCVW60793.2023.00269},
  url       = {https://mlanthology.org/iccvw/2023/jimenez2023iccvw-computational/}
}