From Feature Maps to Few-Shot Cell Segmentation

Serban Vadineanu, Daniël Maria Pelt, Oleh Dzyubachyk, Kees Joost Batenburg

Abstract: Deep learning is a potent tool for image segmentation, but it typically demands abundant annotated data for effective training. In scientific domains, such as cell imaging, obtaining annotations for every structure can be prohibitively expensive. Few-shot learning, adapting from one task to another using minimal examples, can alleviate the need for large training data sets. However, there is limited research addressing the particularities of using few-shot learning for cell imaging. Here, we propose a few-shot learning solution designed to be applicable to cell microscopy images. Our method trains feature extractor networks on classes with abundant labelled samples. These feature extractors are then used to generate high-resolution feature maps from the few labelled images of the new class. Finally, we train a perceptron to recombine the feature maps into predicting the new class. On two challenging cell segmentation data sets, we achieve, using five annotated images, Dice scores that are, on average, less than 20% lower than those of networks trained using several hundred annotated images.