Abstract
•Deep learning combined with reconstruction and shape analysis methods can be used to analyze individual instances of intracellular compartments in 3D FIB-SEM volumetric electron microscopy data;•A deep learning pipeline for automatic segmentation of the Golgi apparatus and fusiform vesicles in 3D volumetric electron microscopy data is presented and evaluated;•Automatic reconstruction methods for mitochondria and fusiform vesicles, as well as shape analysis methods for morphological analysis of noteworthy mitochondria are presented and evaluated;•Manual annotations of individual mitochondria, fusiform vesicles, mitochondria shapes and the Golgi apparatus are made public as an extension of the UroCell dataset.
Background and objectives: In recent years, electron microscopy is enabling the acquisition of volumetric data with resolving power to directly observe the ultrastructure of intracellular compartments. New insights and knowledge about cell processes that are offered by such data require a comprehensive analysis which is limited by the time-consuming manual segmentation and reconstruction methods.
Method: We present methods for automatic segmentation, reconstruction, and analysis of intracellular compartments from volumetric data obtained by the dual-beam electron microscopy. We specifically address segmentation of fusiform vesicles and the Golgi apparatus, reconstruction of mitochondria and fusiform vesicles, and morphological analysis of the reconstructed mitochondria. Results and conclusion: Evaluation on the public UroCell dataset demonstrated high accuracy of the proposed methods for segmentation of fusiform vesicles and the Golgi apparatus, as well as for reconstruction of mitochondria and analysis of their shapes, while reconstruction of fusiform vesicles proved to be more challenging. We published an extension of the UroCell dataset with all of the data used in this work, to further contribute to research on automatic analysis of the ultrastructure of intracellular compartments.