Analysis of the performance of U-Net neural networks for the segmentation of living cells

TL;DR

This paper evaluates and optimizes U-Net neural networks for segmenting live cells in microscopy images, enhancing a pipeline for real-time single-cell tracking and analysis.

Contribution

It presents an optimized U-Net architecture and an improved pipeline for fast, accurate segmentation and tracking of single cells in microscopy images.

Findings

Achieved quasi-real-time image analysis processing 6.20GB in 4 minutes.

Optimized U-Net hyperparameters for improved segmentation accuracy.

Enhanced pipeline for localizing traps and tracking cells over time.

Abstract

The automated analysis of microscopy images is a challenge in the context of single-cell tracking and quantification. This work has as goals the study of the performance of deep learning for segmenting microscopy images and the improvement of the previously available pipeline for tracking single cells. Deep learning techniques, mainly convolutional neural networks, have been applied to cell segmentation problems and have shown high accuracy and fast performance. To perform the image segmentation, an analysis of hyperparameters was done in order to implement a convolutional neural network with U-Net architecture. Furthermore, different models were built in order to optimize the size of the network and the number of learnable parameters. The trained network is then used in the pipeline that localizes the traps in a microfluidic device, performs the image segmentation on trap images, and evaluates the fluorescence intensity and the area of single cells over time. The tracking of the cells during an experiment is performed by image processing algorithms, such as centroid estimation and watershed. Finally, with all improvements in the neural network to segment single cells and in the pipeline, quasi-real-time image analysis was enabled, where 6.20GB of data was processed in 4 minutes.