Search research articles

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

Ultrasound Slice-to-Volume Registration via Artifact-Suppressed Ultra-Feature Learning.

IEEE journal of biomedical and health informatics·2026

Same author

Three-dimensional Liver Respiratory Motion Tracking in Ultrasound Images via Vascular Structural Projection Optimization and Multi-path Constrained Estimation.

Ultrasound in medicine & biology·2026

Same author

Robot-Assisted Osteotomy and Reconstruction with AR Guidance in Maxillofacial Reconstructive Surgery.

Cyborg and bionic systems (Washington, D.C.)·2026

Same author

Point-Supervised Coronary Semantic Segmentation in X-Ray Angiographic Images.

IEEE journal of biomedical and health informatics·2026

Same author

Multimodal hybrid mamba classification model for tumor pathological grade prediction using magnetic resonance images.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

Iterative joint learning integrating temporal and geometric information for vessel segmentation in X-ray coronary angiography.

Medical physics·2026

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: Oct 9, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Multi-task Dynamic Transformer Network for Concurrent Bone Segmentation and Large-Scale Landmark Localization with

Chunfeng Lian¹, Fan Wang¹, Hannah H Deng²

¹Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention

|December 22, 2021

Summary

This study introduces the dynamic transformer network (DTNet) for simultaneously segmenting craniomaxillofacial bones and localizing anatomical landmarks from CBCT scans. DTNet achieves superior performance in these critical tasks for surgical simulation.

Keywords:

Craniomaxillofacial (CMF)Landmark localization Multi-task learning Segmentation

More Related Videos

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

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

Related Experiment Videos

Last Updated: Oct 9, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

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

Area of Science:

Medical Imaging
Computer-Aided Surgery
Deep Learning

Background:

Accurate bone segmentation and landmark localization are crucial for craniomaxillofacial (CMF) surgical simulations.
Existing methods often address these tasks separately, limiting efficiency and potentially overlooking interdependencies.

Purpose of the Study:

To develop an efficient, end-to-end deep network for concurrent CMF bone segmentation and large-scale landmark localization.
To leverage the complementary nature of segmentation and localization tasks for improved accuracy in CMF deformity analysis.

Main Methods:

A novel multi-task dynamic transformer network (DTNet) was proposed, integrating bone segmentation and landmark localization.
DTNet employs a collaborative two-branch architecture for capturing fine-grained details and global context.
Regionalized dynamic learners (RDLs) and adaptive transformer modules (ATMs) were utilized for efficient, joint landmark regression and task-specific feature learning.

Main Results:

DTNet demonstrated superior quantitative performance compared to state-of-the-art methods on CMF deformity CBCT datasets.
The method achieved high accuracy in both CMF bone segmentation and large-scale 3D landmark digitization.
The one-pass, end-to-end approach proved efficient for processing large volumes of medical imaging data.

Conclusions:

The proposed DTNet effectively integrates CMF bone segmentation and landmark localization within a single framework.
DTNet offers a significant advancement for computer-aided surgical simulation, particularly for patients with CMF deformities.
The network's architecture provides an efficient and accurate solution for complex anatomical analysis in medical imaging.