A guided-ensembling approach for cell counting in fluorescence microscopy images

Abstract

Although deep learning and computer vision based approaches have demonstrated success in the field of cell counting and detection in microscopic images, they continue to have certain limitations. More specifically, they experience an overall increase in false positives when dealing with cell populations that show high density and heterogeneity. Existing approaches require the reselection of parameters for each new dataset to improve the accuracy of cell counting. Therefore, it is necessary to revise the fundamental models for each new microscopic image. This study introduces a novel neural network-based method that eliminates the need for retraining by combining the pretrained Cellpose and Stardist models. The accuracy of our proposed approach was evaluated on a variety of microscopic images. Despite variations in cell densities, our proposed approach demonstrated a notably improved cell counting performance in comparison to solely utilizing the Cellpose and Stardist models.