Automated Segmentation of Drosophila RNAi Fluorescence Cellular Images Using Deformable Models

Image-based high-throughput genome-wide RNA interference (RNAi) experiments are increasingly carried out to facilitate the understanding of gene functions in intricate biological processes. Robust automated segmentation of the large volumes of output images generated from image-based screening is much needed for data analyses. In this paper, we propose a new automated segmentation technique to fill the void. The technique consists of two steps: nuclei and cytoplasm segmentation. In the former step, nuclei are extracted, labeled, and used as starting points for the latter step. A new force obtained from rough segmentation is introduced into the classical level set curve evolution to improve the performance for odd shapes, such as spiky or ruffly cells. A scheme of preventing curve intersection is proposed to treat the difficulty of segmenting touching cells. Synthetic images are generated to test the capabilities of our approach. Then, we apply it to three types of Drosophila cells in RNAi fluorescence images. In all cases, accuracy of greater than 92% is obtained