Computational Evaluation of the Combination of Semi-Supervised and Active Learning for Histopathology Image Segmentation with Missing Annotations
(2023) ICCV CVAMD workshop — Location: Paris, France (2.October.2023)
Files
Jimenez_Computational_Evaluation_of_the_Combination_of_Semi-Supervised_and_Active_Learning_ICCVW_2023_paper.pdf
Preprint
Open Access - Adobe PDF
- 1.09 MB
Details
- Authors
Dierckx, Lucile 
- 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.
- Affiliations
Citations
Laura Gálvez Jiménez, Dierckx, L., Maxime Amodei, Hamed Razavi Khosroshahi, Natarajan Chidambaran, Anh-Thu Phan Ho, & Alberto Franzin. (2023). Computational Evaluation of the Combination of Semi-Supervised and Active Learning for Histopathology Image Segmentation with Missing Annotations. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2552-2563. https://hdl.handle.net/2078.5/256065 (Original work published 2023)