Edge-Based Self-Supervision for Semi-Supervised Few-Shot Microscopy Image Cell Segmentation

TL;DR

This paper introduces an edge-based self-supervised semi-supervised learning method for microscopy cell segmentation, reducing the need for extensive labeled data while maintaining high performance.

Contribution

It combines edge-based self-supervision with semi-supervised learning to effectively train segmentation models using minimal labeled data.

Findings

Achieves comparable performance with only 10% labeled data

Effective in 1- to 10-shot microscopy segmentation

Code and models are publicly available

Abstract

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