Automatic localization and identification of mitochondria in cellular electron cryo-tomography using faster-RCNN

Ran Li,Rui Jiang,Ruogu Lin,Kaiwen Wang,Min Xu,Bo Zhou,Chang Liu,Xiangrui Zeng,Stephanie E Sigmund,Hairong Lv,Zachary Freyberg

doi:10.1186/s12859-019-2650-7

Abstract

BackgroundCryo-electron tomography (cryo-ET) enables the 3D visualization of cellular organization in near-native state which plays important roles in the field of structural cell biology. However, due to the low signal-to-noise ratio (SNR), large volume and high content complexity within cells, it remains difficult and time-consuming to localize and identify different components in cellular cryo-ET. To automatically localize and recognize in situ cellular structures of interest captured by cryo-ET, we proposed a simple yet effective automatic image analysis approach based on Faster-RCNN.ResultsOur experimental results were validated using in situ cyro-ET-imaged mitochondria data. Our experimental results show that our algorithm can accurately localize and identify important cellular structures on both the 2D tilt images and the reconstructed 2D slices of cryo-ET. When ran on the mitochondria cryo-ET dataset, our algorithm achieved Average Precision >0.95. Moreover, our study demonstrated that our customized pre-processing steps can further improve the robustness of our model performance.ConclusionsIn this paper, we proposed an automatic Cryo-ET image analysis algorithm for localization and identification of different structure of interest in cells, which is the first Faster-RCNN based method for localizing an cellular organelle in Cryo-ET images and demonstrated the high accuracy and robustness of detection and classification tasks of intracellular mitochondria. Furthermore, our approach can be easily applied to detection tasks of other cellular structures as well.

Highlights

Cryo-electron tomography enables the 3D visualization of cellular organization in near-native state which plays important roles in the field of structural cell biology
Given the critical roles played by mitochondria within mammalian cells, and the distinctive morphology of these organelles, we chose to examine mitochondria imaged by in situ Cryo-electron tomography (cryo-ET) [5]
We proposed an automatic identification and localization method based on Faster-Region-based convolutional neural network (RCNN), which is the first Faster-RCNN based method for localizing an cellular organelle in Cryo-ET images

Summary

Introduction

Cryo-electron tomography (cryo-ET) enables the 3D visualization of cellular organization in near-native state which plays important roles in the field of structural cell biology. Localization of the subcellular structures of interest can facilitate subsequent study of specific macromolecular components within the selected structures [6] Such localization can be performed through image segmentation, which are usually performed manually or by designed heuristics. Luengo et al [14] proposed a supervised approach to classify each voxel with a trained classification model Both of these methods require manually designed features or rules, which might be time- and effort-consuming while having various limitations. Chen et al developed another supervised segmentation method, taking advantage of the excellent capability of feature extraction of convolutional neural network (CNN) [15] In this way, a separate CNN has to be trained for each type of structural features, and the precise contours need to be manually annotated in the training data, which may not be trivial

Objectives

Methods

Results

Conclusion