Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Nov 2, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

CleftNet: Augmented Deep Learning for Synaptic Cleft Detection From Brain Electron Microscopy.

Yi Liu, Shuiwang Ji

IEEE Transactions on Medical Imaging

|June 15, 2021

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Augmenting Molecular Graphs with Geometries via Machine Learning Interatomic Potentials.

ArXiv·2025

Same author

A Benchmark for Quantum Chemistry Relaxations via Machine Learning Interatomic Potentials.

ArXiv·2025

Same author

Correction: DiffBP: generative diffusion of 3D molecules for target protein binding.

Chemical science·2025

Same author

Learning to Discover Regulatory Elements for Gene Expression Prediction.

ArXiv·2025

Same author

Fragment and Geometry Aware Tokenization of Molecules for Structure-Based Drug Design Using Language Models.

ArXiv·2024

Same author

Author Correction: BigNeuron: a resource to benchmark and predict performance of algorithms for automated tracing of neurons in light microscopy datasets.

Nature methods·2024

Same journal

Physiology-guided Self-supervised Learning for Simultaneous Dual-Tracer PET Separation.

IEEE transactions on medical imaging·2026

Same journal

Informed-Exploration Reinforcement Learning for Automated Virtual Coronary Intervention Planning.

IEEE transactions on medical imaging·2026

Same journal

4D Reconstruction of Fetal Left Ventricle from Echocardiography via 2.5D Radial Segmentation and Graph-Fourier Reconstruction.

IEEE transactions on medical imaging·2026

Same journal

Generalised Medical Phrase Grounding.

IEEE transactions on medical imaging·2026

Same journal

EndoLRMGS: Combining Large Reconstruction Modelling and Gaussian Splatting for Complete Endoscopic Scene Reconstruction.

IEEE transactions on medical imaging·2026

Same journal

A Neural-Analytical Fusion Scatter Correction Method for Multi-Source CT Using Equivalent High-Order Scatter.

IEEE transactions on medical imaging·2026

See all related articles

CleftNet, a novel deep learning model, significantly improves synaptic cleft detection in electron microscopy images. This new approach enhances feature and label representations for more accurate biological synapse analysis.

Area of Science:

Neuroscience
Computational Biology
Image Analysis

Background:

Synaptic cleft detection is vital for understanding synapse biological function.
Volume electron microscopy (EM) provides high-resolution images for synaptic cleft identification.
Automated methods using machine learning are increasingly used for synaptic cleft prediction.

Purpose of the Study:

To propose CleftNet, an augmented deep learning model for enhanced synaptic cleft detection in brain EM images.
To introduce novel feature and label augmentation components to improve cleft representations.
To evaluate the model's effectiveness on both internal and external datasets.

Main Methods:

Developed a feature augmentor to fuse global information and learn morphological patterns, creating augmented cleft features.

More Related Videos

Evaluation of Synapse Density in Hippocampal Rodent Brain Slices

Evaluation of Synapse Density in Hippocampal Rodent Brain Slices

Published on: October 6, 2017

DetectSyn: A Rapid, Unbiased Fluorescent Method to Detect Changes in Synapse Density

DetectSyn: A Rapid, Unbiased Fluorescent Method to Detect Changes in Synapse Density

Published on: July 22, 2022

Related Experiment Videos

Last Updated: Nov 2, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Evaluation of Synapse Density in Hippocampal Rodent Brain Slices

Evaluation of Synapse Density in Hippocampal Rodent Brain Slices

Published on: October 6, 2017

DetectSyn: A Rapid, Unbiased Fluorescent Method to Detect Changes in Synapse Density

DetectSyn: A Rapid, Unbiased Fluorescent Method to Detect Changes in Synapse Density

Published on: July 22, 2022

Introduced a label augmentor to convert voxel labels into vectors containing segmentation and boundary information.

Built CleftNet, a U-Net-like network incorporating these augmentation components.

Main Results:

CleftNet achieved the #1 rank on the CREMI open challenge external task.
Both quantitative and qualitative internal task results demonstrated significant outperformance over baseline methods.
The augmentation components improved cleft representations by incorporating shape information.

Conclusions:

CleftNet offers a significant advancement in automated synaptic cleft detection using deep learning.
The proposed feature and label augmentation strategies enhance model performance and representation learning.
This method holds promise for advancing neuroscience research through improved synapse analysis.