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

Case report: first-line lorlatinib in metastatic lung adenocarcinoma with a novel WIPF1-ALK and EML4-ALK dual fusion.

Translational lung cancer research·2026

Same author

Traditional Chinese Medicine Nursing Intervention in Chronic Obstructive Pulmonary Disease With Gastrointestinal Dysfunction: Bibliometric and Knowledge Graph Analysis, 2015-2025.

Complementary medicine research·2026

Same author

Systematic review and meta-analysis of the efficacy of repetitive transcranial magnetic stimulation on post-stroke limb spasticity.

Journal of neurology·2026

Same author

Perceived stress and severity of male etomidate use disorder in China: a moderated mediation model of anxiety symptoms severity and emotion regulation difficulties.

Frontiers in psychology·2026

Same author

Machine learning models based on magnetic resonance imaging for predicting Lymphovascular Invasion in Invasive Breast Cancer.

PloS one·2026

Same author

Simultaneous multi-biomarker detection: streptavidin-biotin mediated high-quality quantum dot immunosensor with signal amplification.

Analytica chimica acta·2026

Search research articles

Related Experiment Video

Updated: Sep 13, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Advanced multi-label brain hemorrhage segmentation using an attention-based residual U-Net model.

Xinxin Lin^1,2, Enmiao Zou³, Wenci Chen⁴

¹Department of General Practice, The Second Affiliated Hospital, Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, 325027, China.

BMC Medical Informatics and Decision Making

|August 1, 2025

Summary

An advanced Attention-Based Residual U-Net (ResUNet) model accurately segments brain hemorrhages in CT scans. This AI tool offers improved precision and generalizability for clinical analysis, outperforming existing methods.

Keywords:

Attention-based residual U-Net Brain hemorrhage CT Deep learning Medical imaging Segmentation

More Related Videos

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Related Experiment Videos

Last Updated: Sep 13, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Area of Science:

Medical Imaging
Artificial Intelligence
Neurology

Background:

Manual segmentation of brain hemorrhages is time-consuming and prone to errors.
Current automated methods lack the required precision and generalizability for diverse hemorrhage types.

Purpose of the Study:

To develop and evaluate an advanced Attention-Based Residual U-Net (ResUNet) model.
To achieve accurate segmentation of six common brain hemorrhage types from CT images.
To enhance precision and generalizability in automated brain hemorrhage analysis.

Main Methods:

A retrospective dataset of 1,347 CT scans with six hemorrhage types was utilized.
Data underwent standardization and intensity normalization.
A ResUNet model with attention and residual mechanisms was trained and tested using 10-fold cross-validation.

Main Results:

The ResUNet model demonstrated high performance with Dice Similarity Coefficient (DSC) scores ranging from 89% to 95% on training data.
Testing yielded strong generalization with DSC scores between 88% and 93% across all hemorrhage types.
High Intersection over Union (IoU) values and low directed Hausdorff distances (dHD) confirmed precise segmentation.

Conclusions:

The ResUNet model significantly improved multi-label segmentation accuracy compared to standard U-Net variants.
This model presents a valuable tool for rapid and reliable clinical brain hemorrhage analysis.
Future work may explore semi-supervised and 3D segmentation for further clinical utility.