EM-stellar: benchmarking deep learning for electron microscopy image segmentation

Motivation: The inherent low contrast of electron microscopy (EM) datasets presents a significant challenge for rapid segmentation of cellular ultrastructures from EM data. This challenge is particularly prominent when working with high-resolution big-datasets that are now acquired using electron tomography and serial block-face imaging techniques. Deep learning (DL) methods offer an exciting opportunity to automate the segmentation process by learning from manual annotations of a small sample of EM data. While many DL methods are being rapidly adopted to segment EM data no benchmark analysis has been conducted on these methods to date. Results: We present EM-stellar, a platform that is hosted on Google Colab that can be used to benchmark the performance of a range of state-of-the-art DL methods on user-provided datasets. Using EM-stellar we show that the performance of any DL method is dependent on the properties of the images being segmented. It also follows that no single DL method performs consistently across all performance evaluation metrics.

Automated summary

This research introduces a platform called EM-stellar for benchmarking the performance of various state-of-the-art DL methods on user-provided datasets. The study finds that the performance of any DL method depends on the properties of the images being segmented, and no single DL method consistently performs across all performance evaluation metrics.