Semantic filtering through deep source separation on microscopy images
This addresses the challenge of automating image analysis in biological microscopy, offering a practical solution for researchers by reducing annotation effort while handling overlapping objects.
The paper tackles the problem of decomposing microscopy images into semantically meaningful objects and layers without requiring dense manual annotations, achieving state-of-the-art segmentation results by using synthetic images generated from cell crops.
By their very nature microscopy images of cells and tissues consist of a limited number of object types or components. In contrast to most natural scenes, the composition is known a priori. Decomposing biological images into semantically meaningful objects and layers is the aim of this paper. Building on recent approaches to image de-noising we present a framework that achieves state-of-the-art segmentation results requiring little or no manual annotations. Here, synthetic images generated by adding cell crops are sufficient to train the model. Extensive experiments on cellular images, a histology data set, and small animal videos demonstrate that our approach generalizes to a broad range of experimental settings. As the proposed methodology does not require densely labelled training images and is capable of resolving the partially overlapping objects it holds the promise of being of use in a number of different applications.