Cell Detection with Star-convex Polygons
This addresses segmentation errors in biological applications for microscopy image analysis, offering an incremental improvement over existing methods.
The paper tackled the problem of crowded cell detection in microscopy images by proposing star-convex polygons as a shape representation, which improved segmentation accuracy by reducing errors like falsely merging cells or suppressing instances, as demonstrated on synthetic and fluorescence microscopy datasets.
Automatic detection and segmentation of cells and nuclei in microscopy images is important for many biological applications. Recent successful learning-based approaches include per-pixel cell segmentation with subsequent pixel grouping, or localization of bounding boxes with subsequent shape refinement. In situations of crowded cells, these can be prone to segmentation errors, such as falsely merging bordering cells or suppressing valid cell instances due to the poor approximation with bounding boxes. To overcome these issues, we propose to localize cell nuclei via star-convex polygons, which are a much better shape representation as compared to bounding boxes and thus do not need shape refinement. To that end, we train a convolutional neural network that predicts for every pixel a polygon for the cell instance at that position. We demonstrate the merits of our approach on two synthetic datasets and one challenging dataset of diverse fluorescence microscopy images.