Khadangi Afshin, Boudier Thomas, Rajagopal Vijay
Department of Biomedical Engineering, University of Melbourne, Victoria, 3000, Australia.
Institute of Molecular Biology, Academia Sinica, Taipei, Taiwan.
Bioinformatics. 2021 Apr 9;37(1):97-106. doi: 10.1093/bioinformatics/btaa1094.
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.
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.
EM-stellar (code and data) is written in Python and is freely available under MIT license on GitHub (https://github.com/cellsmb/em-stellar).
Supplementary data are available at Bioinformatics online.
电子显微镜（EM）数据集固有的低对比度给从EM数据中快速分割细胞超微结构带来了重大挑战。当处理现在使用电子断层扫描和连续块面成像技术获取的高分辨率大数据集时，这一挑战尤为突出。深度学习（DL）方法提供了一个令人兴奋的机会，通过从一小部分EM数据的手动注释中学习来实现分割过程的自动化。虽然许多DL方法正在迅速被采用来分割EM数据，但迄今为止尚未对这些方法进行基准分析。
我们展示了EM-stellar，这是一个托管在谷歌Colab上的平台，可用于在用户提供的数据集上对一系列先进的DL方法的性能进行基准测试。使用EM-stellar，我们表明任何DL方法的性能都取决于被分割图像的属性。由此还可以得出，没有一种单一的DL方法在所有性能评估指标上都能始终如一地表现良好。
EM-stellar（代码和数据）用Python编写，根据麻省理工学院许可在GitHub（https://github.com/cellsmb/em-stellar）上免费提供。
补充数据可在《生物信息学》在线获取。
