Data

Tools

Indexes

Applications

Experiments

Awesome

An open API service indexing awesome lists of open source software.

https://github.com/subeeshvasu/Awesome-Neuron-Segmentation-in-EM-Images

A curated list of resources for 3D segmentation of neurites in EM images
https://github.com/subeeshvasu/Awesome-Neuron-Segmentation-in-EM-Images

List: Awesome-Neuron-Segmentation-in-EM-Images

Last synced: 5 days ago
JSON representation

A curated list of resources for 3D segmentation of neurites in EM images

Awesome Lists containing this project

README 

        
A curated list of resources for 3D segmentation of neurites (connectomics) in EM images



# Papers



+ 2017-BioInf - DeepEM3D: approaching human-level performance on 3D anisotropic EM image segmentation. [[Paper]](https://academic.oup.com/bioinformatics/article/33/16/2555/3096435)[[Code]](https://github.com/divelab/deepem3d)



+ 2017-Arxiv - Superhuman Accuracy on the SNEMI3D Connectomics Challenge. [[Paper]](https://arxiv.org/abs/1706.00120)[[Code]](https://github.com/torms3/Superhuman)



+ 2017-NIPS - An Error Detection and Correction Framework for Connectomics. [[Paper]](http://papers.nips.cc/paper/7258-an-error-detection-and-correction-framework-for-connectomics.pdf)



+ 2017-ICCVW - Solving large Multicut problems for connectomics via domain decomposition. [[Paper]](https://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w1/Pape_Solving_Large_Multicut_ICCV_2017_paper.pdf)



+ 2017-NatureMethods - Multicut brings automated neurite segmentation closer to human performance. [[Paper]](https://www.nature.com/articles/nmeth.4151)



+ 2018-BMVC - Efficient Correction for EM Connectomics with Skeletal Representation. [[Paper]](http://bmvc2018.org/contents/papers/0064.pdf)



+ 2018-NatureMethods - High-Precision Automated Reconstruction of Neurons with Flood-filling Networks. [[Paper]](https://www.nature.com/articles/s41592-018-0049-4)[[Arxiv]](https://arxiv.org/pdf/1611.00421.pdf)[[Code]](https://github.com/google/ffn)



+ 2018-FNC - Analyzing Image Segmentation for Connectomics. [[Paper]](https://www.frontiersin.org/articles/10.3389/fncir.2018.00102/full)



+ 2019-CVPR - Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics. [[Paper]](https://openaccess.thecvf.com/content_CVPR_2019/papers/Meirovitch_Cross-Classification_Clustering_An_Efficient_Multi-Object_Tracking_Technique_for_3-D_Instance_CVPR_2019_paper.pdf)



+ 2019-CVPR - Biologically-Constrained Graphs for Global Connectomics Reconstruction. [[Paper]](https://openaccess.thecvf.com/content_CVPR_2019/papers/Matejek_Biologically-Constrained_Graphs_for_Global_Connectomics_Reconstruction_CVPR_2019_paper.pdf)



+ 2019-CVPR - End-to-End Learned Random Walker for Seeded Image Segmentation. [[Paper]](https://openaccess.thecvf.com/content_CVPR_2019/papers/Cerrone_End-To-End_Learned_Random_Walker_for_Seeded_Image_Segmentation_CVPR_2019_paper.pdf)



+ 2019-ISBI - Learning Metric Graphs for Neuron Segmentation In Electron Microscopy Images. [[Paper]](https://arxiv.org/abs/1902.00100)



+ 2019-ISBI - Reconstructing neuronal anatomy from whole-brain images. [[Paper]](https://arxiv.org/abs/1903.07027)



+ 2019-CON - Convolutional nets for reconstructing neural circuits from brain images acquired by serial section electron microscopy. [[Paper]](https://www.sciencedirect.com/science/article/pii/S0959438818301788?casa_token=qD2Qt7KLqL8AAAAA:MBY0RBvJZPG690q7lrd657Luyd8n5dPwVYsRoyeK7R4unkiVeBKW2mqWvhHdFr70nGXn5iuaqpw)



+ 2019-CON - Big data in nanoscale connectomics, and the greed for training labels. [[Paper]](https://www.sciencedirect.com/science/article/pii/S0959438818301016?casa_token=a7Xm1iBxeysAAAAA:u8tbkV15MoWHcQY67gbdCVnWBtts4MmA7F97r56Q4gVBoFucm0O4-24q6P-UCiSWwBj1eEnix3U)



+ 2019-TPAMI - Large Scale Image Segmentation with Structured Loss Based Deep Learning for Connectome Reconstruction. [[Paper]](https://ieeexplore.ieee.org/document/8364622)[[Arxiv]](https://arxiv.org/abs/1709.02974)[[Code]](https://github.com/funkey/mala)



+ 2019-MM - Automated reconstruction of a serial-section EM Drosophila brain with flood-filling networks and local realignment. [[Paper]](https://www.biorxiv.org/content/10.1101/605634v1)



+ 2019-SR - UNI-EM: An Environment for Deep Neural Network-Based Automated Segmentation of Neuronal Electron Microscopic Images. [[Paper]](https://www.nature.com/articles/s41598-019-55431-0)



+ 2019 - Entropy policy for supervoxel agglomeration of neurite segmentation. [[Paper]](http://www.me.cs.scitec.kobe-u.ac.jp/publications/papers/2019/O3-4.pdf)



+ 2019 - A Generalized Framework for Agglomerative Clustering of Signed Graphs applied to Instance Segmentation. [[Paper]](https://arxiv.org/pdf/1906.11713.pdf)



+ 2019 - Reconstructing neurons from serial section electron microscopy images. [[Thesis]](https://dspace.mit.edu/handle/1721.1/133076)



+ 2020 - Robust neural circuit reconstruction from serial electron microscopy with convolutional recurrent networks. [[Paper]](https://arxiv.org/pdf/1811.11356.pdf)



+ 2020 - Optimizing the Computational Efficiency of 3D Segmentation Models for Connectomics. [[Paper]](https://easychair.org/publications/preprint/dftD)



+ 2020 - Machine Learning for Instance Segmentation. [[Thesis]](https://archiv.ub.uni-heidelberg.de/volltextserver/28353/1/steffen_wolf_thesis_compressed.pdf)



+ 2020 - Generative and discriminative model-based approaches to microscopic image restoration and segmentation. [[Paper]](https://academic.oup.com/jmicro/article/69/2/79/5811684)



+ 2020 - Accelerated EM Connectome Reconstruction using 3D Visualization and Segmentation Graphs. [[Paper]](https://www.biorxiv.org/content/biorxiv/early/2020/01/17/2020.01.17.909572.full.pdf)



+ 2020 - Machine Learning for Connectomics. [[Thesis]](https://mediatum.ub.tum.de/doc/1449120/document.pdf)



+ 2020-TPAMI - The Mutex Watershed and its Objective: Efficient, Parameter-Free Graph Partitioning. [[Paper]](https://ieeexplore.ieee.org/document/9036993)[[Code]](https://github.com/hci-unihd/mutex-watershed)



+ 2021-TMI - Learning Dense Voxel Embeddings for 3D Neuron Reconstruction. [[Paper]](https://ieeexplore.ieee.org/abstract/document/9489304)[[Code]](https://github.com/seung-lab/devoem)



+ 2021 - Scalable Instance Segmentation for Microscopy. [[Thesis]](https://archiv.ub.uni-heidelberg.de/volltextserver/30147/1/phd-thesis-cpape.pdf)



+ 2022-TMI - Semi-Supervised Neuron Segmentation via Reinforced Consistency Learning. [[Paper]](https://ieeexplore.ieee.org/abstract/document/9777694)[[Code]](https://github.com/weih527/SSNS-Net)



+ 2023-NatureMethods - Local Shape Descriptors for Neuron Segmentation. [[Paper]](https://www.nature.com/articles/s41592-022-01711-z)[[Code]](https://localshapedescriptors.github.io)



# Benchmark Datasets



+ 2013-ISBI - SNEMI3D: [[Dataset & Challenge details]](https://snemi3d.grand-challenge.org/)



+ 2015-PNAS - FIB-25: Synaptic circuits and their variations within different columns in the visual system of Drosophila. [[Paper]](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4640747/) [[Dataset & details]](https://www.janelia.org/project-team/flyem/tools-and-data-release)



+ 2015-Neuron - SegEM: SegEM: Efficient Image Analysis for High-Resolution Connectomics. [[Paper]](https://www.sciencedirect.com/science/article/pii/S0896627315007606)[[Dataset & Challenge details]](http://segem.brain.mpg.de/)



+ 2016-MICCAI - CREMI: [[Dataset & Challenge details]](https://cremi.org/)



+ 2018-Arxiv - star-challenge: Robust neural circuit reconstruction from serial electron microscopy with convolutional recurrent networks. [[Paper]](https://arxiv.org/abs/1811.11356v1)[[Dataset & Challenge details]](https://star-challenge.github.io/)



# Metrics



+ 2013-ISBI - Adapted Rand error: SNEMI3D [[Definition]](http://brainiac2.mit.edu/SNEMI3D/evaluation)[[Matlab-Code]](http://brainiac2.mit.edu/SNEMI3D/evaluation)[[Python-code]](https://github.com/cremi/cremi_python/blob/master/cremi/evaluation/rand.py)



+ 2015-PNAS - Inter-error distance (IED): SegEM: Efficient Image Analysis for High-Resolution Connectomics. [[Definition]](https://www.sciencedirect.com/science/article/pii/S0896627315007606)[[Matlab-Code]](https://github.com/mhlabCodingTeam/SegEM/blob/master/cortex/segmentation/evaluateSeg.m)



+ 2015-Methods - Tolerant Edit Distance (TED): TED: A Tolerant Edit Distance for Segmentation Evaluation. [[Paper]](https://arxiv.org/abs/1503.02291)[[Code]](https://github.com/funkey/ted)



+ 2016-MICCAI - Variation of Information (VOI): CREMI: [[Links]](https://cremi.org/) [[Python-code]](https://github.com/cremi/cremi_python/blob/master/cremi/evaluation/voi.py)



+ 2018-NatureMethods - Expected Run Length (ERL): High-Precision Automated Reconstruction of Neurons with Flood-filling Networks. [[Definition]](https://static-content.springer.com/esm/art%3A10.1038%2Fs41592-018-0049-4/MediaObjects/41592_2018_49_MOESM1_ESM.pdf)



+ 2018-FN - Neural Reconstruction Integrity (NRI): A Metric for Assessing the Connectivity Accuracy of Reconstructed Neural Networks. [[Paper]](https://www.frontiersin.org/articles/10.3389/fninf.2018.00074/full)



+ 2019-NeurIPS - Betti number error: Topology-Preserving Deep Image Segmentation. [[Paper]](https://proceedings.neurips.cc/paper/2019/file/2d95666e2649fcfc6e3af75e09f5adb9-Paper.pdf)



+ 2023-NatureMethods - Min-Cut Metric (MCM): Local Shape Descriptors for Neuron Segmentation. [[Paper]](https://www.nature.com/articles/s41592-022-01711-z)[[Code]](https://localshapedescriptors.github.io)



# Other Resources



+ PyTorch Connectomics - [[Code]](https://github.com/zudi-lin/pytorch_connectomics)



+ pytorch-3dunet - [[Code]](https://github.com/wolny/pytorch-3dunet)



+ Awesome-vEM-Datasets - [[Dataset details]](https://github.com/JackieZhai/awesome-vem-datasets)