Edge-Based Self-Supervision for Semi-Supervised Few-Shot Microscopy Image Cell Segmentation
This work addresses the costly labeling process in microscopy image analysis, offering an incremental improvement for researchers in biomedical imaging.
The paper tackles the problem of reducing labeling requirements for microscopy image cell segmentation by combining self-supervised and semi-supervised learning, achieving similar performance with only 10% of labeled data compared to fully annotated databases in few-shot settings.
Deep neural networks currently deliver promising results for microscopy image cell segmentation, but they require large-scale labelled databases, which is a costly and time-consuming process. In this work, we relax the labelling requirement by combining self-supervised with semi-supervised learning. We propose the prediction of edge-based maps for self-supervising the training of the unlabelled images, which is combined with the supervised training of a small number of labelled images for learning the segmentation task. In our experiments, we evaluate on a few-shot microscopy image cell segmentation benchmark and show that only a small number of annotated images, e.g. 10% of the original training set, is enough for our approach to reach similar performance as with the fully annotated databases on 1- to 10-shots. Our code and trained models is made publicly available