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

Cancer cells co-opt nociceptive nerves to thrive in nutrient-poor environments and upon nutrient-starvation therapies.

Cell metabolism·2026

Same author

Andrographolide Suppresses Head and Neck Squamous Cell Carcinoma Progression via EGR1-ACSL4 Axis-Mediated Ferroptosis.

The American journal of Chinese medicine·2026

Same author

Motor intervention therapy for children with developmental coordination disorder: from behavioral improvement to neuroplasticity mechanisms.

Frontiers in human neuroscience·2026

Same author

Sensory neuron-derived CCL5 orchestrates an immunosuppressive niche via regulatory T cells to fuel head and neck tumor progression.

Journal for immunotherapy of cancer·2026

Same author

Targeting CGRP signaling alleviates cancer-associated pain in oral squamous cell carcinoma.

BMC oral health·2026

Same author

Retraction notice to "Polydatin protects against calcium oxalate crystal-induced renal injury through the cytoplasmic/mitochondrial reactive oxygen species-NLRP3 inflammasome pathway" [Biomedicine & Pharmacotherapy 167 (2023) 115621].

Biomedicine & pharmacotherapy = Biomedecine & pharmacotherapie·2026

Search research articles

Related Experiment Video

Updated: Oct 27, 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

Automatic mandible segmentation from CT image using 3D fully convolutional neural network based on DenseASPP and

Jiangchang Xu¹, Jiannan Liu², Dingzhong Zhang¹

¹Institute of Biomedical Manufacturing and Life Quality Engineering, State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Room 805, Dongchuan Road 800, Minhang District, Shanghai, 200240, China.

International Journal of Computer Assisted Radiology and Surgery

|July 21, 2021

Summary

This study introduces an advanced 3D deep learning model for automatic mandible segmentation in CT scans. The method significantly improves accuracy and efficiency, aiding cranio-maxillofacial surgery.

Keywords:

Attention gates DenseASPP Fully convolutional neural network Mandible segmentation

More Related Videos

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: Oct 27, 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: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Area of Science:

Medical Imaging
Computer-Aided Surgery
Deep Learning

Background:

Accurate mandible segmentation is crucial in cranio-maxillofacial surgery.
Manual and semi-automatic methods are time-consuming and inconsistent.
Existing automatic methods struggle with accuracy and speed.

Purpose of the Study:

To develop an automatic mandibular segmentation method for CT images.
To address challenges like connected regions and blurred boundaries in existing methods.
To improve segmentation consistency and reduce processing time.

Main Methods:

Utilized a 3D fully convolutional neural network incorporating DenseASPP and attention gates (AG).
Employed DenseASPP for multi-scale feature extraction and AG to focus on relevant regions.
Implemented a combined loss function (Dice + focal loss) to handle class imbalance.

Main Results:

Achieved high segmentation accuracy: Dice score 97.588%, IoU 95.293%.
Demonstrated superior performance compared to other networks, with reduced misjudgment.
Reported an average surface distance of 0.065 mm, indicating close proximity to ground truth.

Conclusions:

The proposed network enables accurate and automatic mandible segmentation.
Segmentation time of 50.43 seconds per scan significantly enhances surgical efficiency.
Presents practical significance for cranio-maxillofacial surgical applications.