End-to-end Neuron Instance Segmentation based on Weakly Supervised Efficient UNet and Morphological Post-processing

Recent studies have demonstrated the superiority of deep learning in medical image analysis, especially in cell instance segmentation, a fundamental step for many biological studies. However, the good performance of the neural networks requires training on large unbiased dataset and annotations, which is labor-intensive and expertise-demanding. In this paper, we present an end-to-end weakly-supervised framework to automatically detect and segment NeuN stained neuronal cells on histological images using only point annotations. We integrate the state-of-the-art network, EfficientNet, into our U-Net-like architecture. Validation results show the superiority of our model compared to other recent methods. In addition, we investigated multiple post-processing schemes and proposed an original strategy to convert the probability map into segmented instances using ultimate erosion and dynamic reconstruction. This approach is easy to configure and outperforms other classical post-processing techniques.