Cell segmentation in phase contrast microscopy images lays a crucial foundation for numerous subsequent computer-aided cell image analysis, but it encounters many unsolved challenges due to image qualities and artifacts caused by phase contrast optics. Addressing the unsolved challenges, the authors propose an interactive cell segmentation scheme over phase retardation features. After partitioning the images into phase homogeneous atoms, human annotations are propagated to unlabeled atoms over an affinity graph that is learned based on discrimination analysis. Then, an active query strategy is proposed for which the most informative unlabeled atom is selected for annotation, which is also propagated to the other unlabeled atoms. Cell segmentation converges to quality results after several rounds of interactions involving both the user's intentions and characteristics of image features. Experimental results demonstrate that cells with different optical properties are well segmented via the proposed approach.
Keywords: active learning; interactive cell segmentation; label propagation; phase contrast microscopy image.