Knowing What to Label for Few Shot Microscopy Image Cell Segmentation

TL;DR

This paper introduces a novel method for selecting the most informative unlabelled microscopy images for annotation, improving the fine-tuning process of deep neural networks in cell segmentation tasks by leveraging consistency scores and self-supervised tasks.

Contribution

It proposes a new scoring function based on model prediction consistency and self-supervised tasks to optimize image selection for few-shot microscopy image segmentation.

Findings

Improved segmentation accuracy over random selection.

Outperforms entropy and Monte-Carlo dropout-based methods.

Effective across five different cell image types.

Abstract

In microscopy image cell segmentation, it is common to train a deep neural network on source data, containing different types of microscopy images, and then fine-tune it using a support set comprising a few randomly selected and annotated training target images. In this paper, we argue that the random selection of unlabelled training target images to be annotated and included in the support set may not enable an effective fine-tuning process, so we propose a new approach to optimise this image selection process. Our approach involves a new scoring function to find informative unlabelled target images. In particular, we propose to measure the consistency in the model predictions on target images against specific data augmentations. However, we observe that the model trained with source datasets does not reliably evaluate consistency on target images. To alleviate this problem, we propose novel self-supervised pretext tasks to compute the scores of unlabelled target images. Finally, the top few images with the least consistency scores are added to the support set for oracle (i.e., expert) annotation and later used to fine-tune the model to the target images. In our evaluations that involve the segmentation of five different types of cell images, we demonstrate promising results on several target test sets compared to the random selection approach as well as other selection approaches, such as Shannon's entropy and Monte-Carlo dropout.