MitoEM Dataset: Large-Scale 3D Mitochondria Instance Segmentation from EM Images

  title={MitoEM Dataset: Large-Scale 3D Mitochondria Instance Segmentation from EM Images},
  author={D. Wei and Zudi Lin and Daniel Franco-Barranco and N. Wendt and Xingyu and Liu and Wenjie Yin and Xin Huang and Aarush Gupta and Won-Dong Jang and Xueying Wang and I. Arganda-Carreras and J. Lichtman and H. Pfister},
  journal={Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention},
  • D. Wei, Zudi Lin, +11 authors H. Pfister
  • Published 2020
  • Medicine, Computer Science
  • Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
Electron microscopy (EM) allows the identification of intracellular organelles such as mitochondria, providing insights for clinical and scientific studies. However, public mitochondria segmentation datasets only contain hundreds of instances with simple shapes. It is unclear if existing methods achieving human-level accuracy on these small datasets are robust in practice. To this end, we introduce the MitoEM dataset, a 3D mitochondria instance segmentation dataset with two (30μm)3 volumes from… Expand

Figures and Tables from this paper

AxonEM Dataset: 3D Axon Instance Segmentation of Brain Cortical Regions
The AxonEM dataset is introduced, which consists of two 30×30×30 μm EM image volumes from the human and mouse cortex, respectively, to provide dense 3D axon instance segmentation, enabling largescale evaluation of axon reconstruction methods. Expand
NucMM Dataset: 3D Neuronal Nuclei Instance Segmentation at Sub-Cubic Millimeter Scale
A novel hybrid-representation learning model is proposed that combines the merits of foreground mask, contour map, and signed distance transform to produce high-quality 3D masks and significantly outperforms state-of-the-art nuclei segmentation approaches. Expand
Automatic instance segmentation of mitochondria in electron microscopy data
We present a new method for rapid, automated, large-scale 3D mitochondria instance segmentation, developed in response to the ISBI 2021 MitoEM Challenge. In brief, we trained separate machineExpand
Hierarchical Encoder-Decoder With Soft Label-Decomposition for Mitochondria Segmentation in EM Images
A novel soft label-decomposition strategy to exploit shape knowledge in manual labels is introduced and additional subcategory-aware supervision is introduced by softly decomposing each manual label map into two complementary label maps according to mitochondria's ovality. Expand
Automatic whole cell organelle segmentation in volumetric electron microscopy
An analysis pipeline for comprehensively reconstructing and analyzing the cellular organelles in entire cells imaged by focused ion beam scanning electron microscopy (FIB-SEM) at a near-isotropic size of 4 or 8 nm per voxel is developed, and automatic reconstructions were used to directly quantify various previously inaccessible metrics about these structures, including their spatial interactions. Expand
Sparse Object-level Supervision for Instance Segmentation with Pixel Embeddings
A proposal-free segmentation approach based on non-spatial embeddings, which exploits the structure of the learned embedding space to extract individual instances in a differentiable way to address the dense annotation bottleneck. Expand
A Systematic Collection of Medical Image Datasets for Deep Learning
A collection of medical image datasets with their associated challenges for deep learning research to provide a universal reference to easily find the datasets for clinical image analysis and to guide researchers on the methodology to test and evaluate their methods’ performance and robustness on relevant datasets. Expand
CleftNet: Augmented Deep Learning for Synaptic Cleft Detection from Brain Electron Microscopy
  • Yi Liu, Shuiwang Ji
  • Medicine, Computer Science
  • IEEE transactions on medical imaging
  • 2021
A novel and augmented deep learning model, known as CleftNet, for improving synaptic cleft detection from brain EM images by augmenting features and labels to improve cleft representations and is built as a U-Net like network. Expand
Advanced Deep Networks for 3D Mitochondria Instance Segmentation
This paper designs a simple yet effective anisotropic convolution block and deploy a multi-scale training strategy, which together boost the segmentation performance and enhances the generalizability of the trained models on the test set by adding a denoising operation as pre-processing. Expand
Stable deep neural network architectures for mitochondria segmentation on electron microscopy volumes
An extensive study of the state-of-the-art deep learning architectures for the segmentation of mitochondria on EM volumes, and evaluates the impact in performance of different variations of 2D and 3D U-Net-like models for this task. Expand


Automatic Mitochondria Segmentation for EM Data Using a 3D Supervised Convolutional Network
  • Chi Xiao, Xi Chen, +4 authors Hua Han
  • Computer Science, Medicine
  • Front. Neuroanat.
  • 2018
An effective and automated pipeline based on deep learning to realize mitochondria segmentation in different EM images contributes to the development of neuroscience by providing neurologists with a rapid approach for obtaining rich mitochondria statistics and helping them elucidate the mechanism and function of mitochondria. Expand
Supervoxel-Based Segmentation of Mitochondria in EM Image Stacks With Learned Shape Features
This work proposes an automated graph partitioning scheme that is able to segment mitochondria at a performance level close to that of a human annotator, and outperforms a state-of-the-art 3-D segmentation technique. Expand
Mitochondria segmentation in electron microscopy volumes using deep convolutional neural network
A deep convolutional neural network approach for automatic segmentation of mitochondria in brain tissue, specifically the CA1 hippocampus region imaged by an focusedion beam scanning electron microscope is presented. Expand
DeepEM3D: approaching human‐level performance on 3D anisotropic EM image segmentation
This work proposes DeepEM3D, a deep learning method for segmenting 3D anisotropic brain electron microscopy images that combines a combination of novel boundary map generation methods with optimized model ensembles to address the inherent challenges of segmenting an isotropic images. Expand
Automatic Detection and Segmentation of Mitochondria from SEM Images using Deep Neural Network
  • Jing Liu, Weifu Li, Chi Xiao, B. Hong, Q. Xie, Hua Han
  • Computer Science, Medicine
  • 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
  • 2018
This paper proposes an effective deep neural network improved from Mask R-CNN to produce the detection and segmentation results of mitochondria from EM images, and demonstrates that the proposed method has comparable performance than state-of-the-art methods. Expand
Large Scale Image Segmentation with Structured Loss Based Deep Learning for Connectome Reconstruction
A method combining affinity prediction with region agglomeration, which improves significantly upon the state of the art of neuron segmentation from electron microscopy (EM) in accuracy and scalability, and suggests that a single method can be applied to both nearly isotropic block-face EM data and anisotropic serial sectioned EM data. Expand
Segmentation fusion for connectomics
This work identifies the fusion of segments and links that provide the most globally consistent segmentation of the stack and shows that this two-step approach of pre-enumeration and posterior fusion yields significant advantages and provides state-of-the-art reconstruction results. Expand
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
The proposed network extends the previous u-net architecture from Ronneberger et al. by replacing all 2D operations with their 3D counterparts and performs on-the-fly elastic deformations for efficient data augmentation during training. Expand
U-Net: Convolutional Networks for Biomedical Image Segmentation
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Expand
High-precision automated reconstruction of neurons with flood-filling networks
Flood-filling networks are a deep-learning-based pipeline for reconstruction of neurons from electron microscopy datasets that results in exceptionally low error rates, thereby reducing the need for extensive human proofreading. Expand