Microscopy cell counting with fully convolutional regression networks

This paper concerns automated cell counting in microscopy images. The approach we take is to adapt Convolutional Neural Networks (CNNs) to regress a cell spatial density map across the image. This is applicable to situations where traditional single-cell segmentation based methods do not work well due to cell clumping or overlap. We make the following contributions: (i) we develop and compare architectures for two Fully Convolutional Regression Networks (FCRNs) for this task; (ii) since the networks are fully convolutional, they can predict a density map for an input image of arbitrary size, and we exploit this to improve efficiency at training time by training end-to-end on image patches; and (iii) we show that FCRNs trained entirely on synthetic data are able to give excellent predictions on real microscopy images without fine-tuning, and that the performance can be further improved by fine-tuning on the real images. We set a new state-of-the-art performance for cell counting on the standard synthetic image benchmarks and, as a side benefit, show the potential of the FCRNs for providing cell detections for overlapping cells