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

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

FOXK2 regulates PFKFB3 in promoting glycolysis and tumorigenesis in multiple myeloma.

Leukemia research·2023

Same author

A lightweight dual-path cascaded network for vessel segmentation in fundus image.

Mathematical biosciences and engineering : MBE·2023

Same author

Histone lysine demethylase 3B regulates autophagy via transcriptional regulation of <i>GABARAPL1</i> in acute myeloid leukemia cells.

International journal of oncology·2023

Same author

Drug-drug interaction of ciprofol injectable emulsion with mefenamic acid capsules in healthy subjects.

British journal of clinical pharmacology·2023

Same author

Developing a New Phylogeny-Driven Random Forest Model for Functional Metagenomics.

IEEE transactions on nanobioscience·2023

Same author

Structural Change and Radical Generation of a Cadmium-Based Metal-Organic Framework Induced by an Electric Field.

Inorganic chemistry·2023

Search research articles

Related Experiment Video

Updated: Jul 31, 2025

Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies

Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies

Published on: March 12, 2022

MIC-Net: multi-scale integrated context network for automatic retinal vessel segmentation in fundus image.

Jinke Wang^1,2, Lubiao Zhou², Zhongzheng Yuan¹

¹Department of Software Engineering, Harbin University of Science and Technology, Rongcheng 264300, China.

Mathematical Biosciences and Engineering : MBE

|May 10, 2023

Summary

This summary is machine-generated.

This study introduces MIC-Net, a novel deep learning model for precise retinal vessel segmentation. The network achieves high accuracy, offering a promising tool for early ophthalmic disease diagnosis.

Keywords:

deep learning fundus image multi-scale retinal vessel segmentation

More Related Videos

Measuring Retinal Vessel Diameter from Mouse Fluorescent Angiography Images

Measuring Retinal Vessel Diameter from Mouse Fluorescent Angiography Images

Published on: May 19, 2023

Using Retinal Imaging to Study Dementia

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

Related Experiment Videos

Last Updated: Jul 31, 2025

Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies

Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies

Published on: March 12, 2022

Measuring Retinal Vessel Diameter from Mouse Fluorescent Angiography Images

Measuring Retinal Vessel Diameter from Mouse Fluorescent Angiography Images

Published on: May 19, 2023

Using Retinal Imaging to Study Dementia

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

Area of Science:

Medical Imaging
Computer Vision
Ophthalmology

Background:

Accurate retinal vessel segmentation is crucial for diagnosing various eye diseases.
Challenges include low contrast, optic disc variability, and complex vessel morphology.

Purpose of the Study:

To develop a high-precision retinal blood vessel segmentation method.
To introduce the multi-scale integrated context network (MIC-Net).

Main Methods:

Designed a hybrid stride sampling (HSS) block to minimize information loss during downsampling.
Employed dense hybrid dilated convolution (DHDC) for richer contextual perception.
Integrated squeeze-and-excitation with residual connections (SERC) for adaptive channel attention.
Utilized multi-layer feature fusion in skip connections for comprehensive feature integration.

Main Results:

Evaluated on DRIVE, STARE, and CHASE datasets.
Achieved high performance with Area Under the ROC curve (ROC) of 98.62%/98.60%/98.73% and accuracy (Acc) of 97.02%/97.76%/97.38%.
Demonstrated comparable segmentation performance to state-of-the-art methods.

Conclusions:

The proposed MIC-Net effectively reduces segmentation errors, particularly for small blood vessels.
MIC-Net shows significant promise as an auxiliary diagnostic tool for ophthalmic diseases.