Related Experiment Video
Updated: May 5, 2026
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
BDU-Net: An Edge-Segmentation-Oriented U-Shaped Network for Pediatric Knee Joint Segmentation
Huazheng Zhu1, Yaping Liu1, Zhuo Cheng2
1School of Computer Science and Engineering, Chongqing University of Science and Technology, Chongqing, 401331, China.
Insights
A new BDU-Net model precisely segments pediatric knee cartilage in MRI scans, improving early detection of bone development issues. This advanced segmentation enhances cartilage monitoring and risk identification for children
Area of Science:
- Medical imaging analysis
- Pediatric orthopedics
- Artificial intelligence in healthcare
Background:
- Accurate segmentation of pediatric knee cartilage in MRI is crucial for assessing bone development and identifying risks.
- Challenges include variations in cartilage size/shape, low contrast, and fuzzy boundaries in pediatric knee MRI.
- High-precision automatic segmentation models are needed for effective cartilage monitoring and early intervention.
Purpose of the Study:
- To develop a novel, high-precision automatic segmentation model for pediatric knee cartilage MRI.
- To address the challenges of segmentation accuracy, edge preservation, and noise suppression in pediatric knee cartilage images.
- To improve the quantitative assessment of cartilage development and enable early detection of potential issues.
Main Methods:
- Proposed BDU-Net, a UNet++-based segmentation model incorporating an edge-preserving enhancement module (EPEM) using ordinary differential equations (ODE) and the Runge-Kutta second-order (RK2) method.
- Integrated a multi-scale feature extraction module (MSFEM) in the bridge section for enhanced global and local feature modeling.
- Employed dynamic feature-weighted fusion to improve edge perception.
Main Results:
- BDU-Net demonstrated superior performance over state-of-the-art methods on three pediatric knee cartilage datasets (PC, MCC, LCGP).
- Achieved high Intersection over Union (IoU) scores: 0.7519 (PC), 0.8283 (MCC), and 0.8485 (LCGP), outperforming comparative methods.
- Showcased significant improvements in segmentation accuracy, edge preservation, and noise suppression, validated by qualitative analysis and expert scoring.
Conclusions:
- The proposed BDU-Net model effectively addresses the challenges of segmenting pediatric knee cartilage in MRI.
- BDU-Net offers clear performance advantages and significant application potential for monitoring cartilage development and enabling early intervention in children.
- The model's ability to enhance edge perception and model complex features contributes to its high accuracy and reliability.
Abstract:
The growth plate and articular cartilage are essential for children's bone development. Precise segmentation of cartilage in MRI images enables the extraction of quantitative indicators for health assessment and risk identification. Therefore, developing high-precision automatic segmentation models is of great importance for monitoring cartilage development and enabling early intervention. However, in pediatric knee joint MRI images, there are significant variations in the size and shape of the cartilage, the cartilage's gray value is close to that of the surrounding tissue or synovial fluid, and the boundaries are often fuzzy. To address these challenges, this paper proposes a new UNet++-based segmentation model, BDU-Net. In this model, an edge-preserving enhancement module (EPEM) is designed based on ordinary differential equations (ODE), with the Runge-Kutta second-order (RK2) method introduced to model and strengthen complex textures and contour regions. The edge perception ability is further improved through dynamic feature-weighted fusion. In addition, a multi-scale feature extraction module(MSFEM) is integrated into the bridge section to enhance the joint modeling of global context and local details, thereby improving the model's ability to focus on and represent key regions. Experiments on three pediatric knee cartilage datasets (PC, MCC, LCGP) demonstrate that BDU-Net outperforms existing state-of-the-art methods in segmentation accuracy, edge preservation, and noise suppression. The proposed method achieves IoU values of 0.7519, 0.8283, and 0.8485 on the three datasets, while the best results from the compared methods are 0.7456, 0.8184, and 0.8352. It also achieves strong results in qualitative analysis and expert scoring, showing clear performance advantages and application potential.
