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: Jan 17, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

MDWC-Net: a multi-scale dynamic-weighting context network for precise spinal X-ray segmentation.

Zhongzheng Gu¹, Xuan Wang², Baojun Chen¹

¹Department of Spine and Spinal Cord Surgery, Henan Provincial People's Hospital, Zhengzhou, Henan, China.

Frontiers in Physiology

|September 15, 2025

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

Correlations between inflammatory biomarkers and clinicopathological features in surgically resected thymic epithelial tumors: implications for preoperative diagnosis.

PeerJ·2026

Same author

GhTUA2 promote roots elongation through regulating cell wall synthesis in cotton.

Plant science : an international journal of experimental plant biology·2026

Same author

A novel wearable interface based on IMUs for robotic endoscopy.

International journal of computer assisted radiology and surgery·2026

Same author

Li<sub><i>x</i></sub>Ag<sub>1-<i>x</i></sub>GaS<sub>2</sub>: A Tunable Crystal for Mid-IR Nonlinear Optics via Composition Control.

Inorganic chemistry·2026

Same author

Quaternized chitosan-g-polyaniline (QCSP)-based versatile immunomodulatory conductive supramolecular hydrogel with controlled Zn<sup>2+</sup> release for functional healing of infected burn wounds.

International journal of biological macromolecules·2026

Same author

AKT3-Driven Epithelial-Mesenchymal Plasticity Governs Ovarian Metastasis in Colorectal Cancer via Tumor Microenvironment Remodeling.

Cancer research·2026

Same journal

Physiological load and breath-holding in artistic swimming: a scoping review establishing historical baselines and evidence gaps in the context of the 2022-2025 rule changes.

Frontiers in physiology·2026

Same journal

Effects of blood flow restriction exercise interventions on patellofemoral pain syndrome: a systematic review and meta-analysis.

Frontiers in physiology·2026

Same journal

Effects of resistance-type and cycling-type high-intensity interval training on cardiorespiratory fitness, lower-body strength, and anaerobic fitness.

Frontiers in physiology·2026

Same journal

Model-based estimates of sex differences in peak power and fatigue index in track cyclists using directed acyclic graphs, inverse probability of treatment weighting, and Bayesian modeling.

Frontiers in physiology·2026

Same journal

Fine-tuning striated muscle performance: conserved sarcomere-level mechanisms across insect and vertebrate systems.

Frontiers in physiology·2026

Same journal

Effects of different dual-task trainings on gait and cortical activation during obstacle crossing in stroke patients: a randomized controlled trial.

Frontiers in physiology·2026

See all related articles

This study introduces MDWC-Net, a deep learning model for accurate spinal X-ray segmentation. MDWC-Net enhances spinal structure identification, improving clinical workflow efficiency.

Area of Science:

Medical Imaging
Artificial Intelligence
Computer Vision

Background:

Spinal X-ray segmentation is challenging due to complex anatomy, scale variations, and poor boundary contrast.
Traditional segmentation models struggle with accuracy and robustness in spinal imaging.
Accurate spinal structure identification is crucial for clinical diagnosis and treatment planning.

Purpose of the Study:

To propose MDWC-Net, a novel deep learning framework for improved spinal X-ray image segmentation.
To enhance the accuracy and efficiency of spinal structure identification in clinical settings.
To address limitations of traditional models in segmenting complex spinal anatomy.

Main Methods:

MDWC-Net utilizes an encoder-decoder architecture with specialized modules: Multi-Scale Contextual Attention (MSCAW), Dual Feature Fusion (DFCB), and Boundary Information Enhancement (BIEB).

Keywords:

bottleneck information enhancement block convolutional neural networks dual feature complementary block multi-scale convolutional adaptive weighting spinal image segmentation

Related Experiment Videos

Last Updated: Jan 17, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

The model was trained and validated on the Spine Dataset (280 X-ray images) with a 7:1:2 split.

Generalizability was assessed using the Chest X-ray and ISIC2016 datasets for lung and melanoma segmentation, respectively.

Main Results:

MDWC-Net achieved superior performance compared to mainstream models on the Spine Dataset.
Key metrics include Dice score (89.86% ± 0.356), Mean Intersection over Union (MIoU) (90.53% ± 0.315), Global Accuracy (GPA) (96.82% ± 0.289), and Sensitivity (96.77% ± 0.212).
Ablation studies confirmed the significant contribution of the MSCAW, DFCB, and BIEB modules.

Conclusions:

MDWC-Net provides accurate and efficient segmentation of spinal structures.
The framework demonstrates strong potential for integration into clinical workflows.
The model's high performance and generalizability suggest broad applicability to other medical image segmentation tasks.