Evaluation of semi-supervised learning using sparse labeling to segment cell nuclei

The analysis of microscopic images from cell cultures plays an important role in the development of drugs. The segmentation of such images is a basic step to extract the viable information on which further evaluation steps are build. Classical image processing pipelines often fail under heterogeneous conditions. In the recent years deep neuronal networks gained attention due to their great potentials in image segmentation. One main pitfall of deep learning is often seen in the amount of labeled data required for training such models. Especially for 3D images the process to generate such data is tedious and time consuming and thus seen as a possible reason for the lack of establishment of deep learning models for 3D data. Efforts have been made to minimize the time needed to create labeled training data or to reduce the amount of labels needed for training. In this paper we present a new semisupervised training method for image segmentation of microscopic cell recordings based on an iterative approach utilizing unlabeled data during training. This method helps to further reduce the amount of labels required to effectively train deep learning models for image segmentation. By labeling less than one percent of the training data, a performance of 90% compared to a full annotation with 342 nuclei can be achieved