Application of Deep Learning Algorithms for Automated MRI Knee Joint Image Segmentation

Manual segmentation of knee joint structures in 3D Magnetic Resonance Imaging (MRI) scans is a labor-intensive process, often requiring several hours per scan for detailed segmentations. This paper presents a deep learning approach utilizing a modified 3D U-Net architecture for automated segmentatio...

Full description

Saved in:
Bibliographic Details
Published in2025 15th International Conference on Measurement pp. 6 - 9
Main Authors Pajanova, Iveta, Krafcik, Andrej
Format Conference Proceeding
LanguageEnglish
Published Institute of Measurement Science, SAS 02.06.2025
Subjects
Artificial Neural Network
Automated MRI Image Segmentation
Convolutional Neural Network
Convolutional neural networks
Deep learning
Image segmentation
Inference algorithms
Knee Joint
Magnetic resonance imaging
Manuals
Monitoring
Osteoarthritis
Reliability
Three-dimensional displays
Online AccessGet full text
DOI10.23919/MEASUREMENT66999.2025.11078684

Cover

More Information
Summary:Manual segmentation of knee joint structures in 3D Magnetic Resonance Imaging (MRI) scans is a labor-intensive process, often requiring several hours per scan for detailed segmentations. This paper presents a deep learning approach utilizing a modified 3D U-Net architecture for automated segmentation of knee MRI images from the Osteoarthritis Initiative (OAI) dataset. Trained on 507 subjects, the model achieves minimum Dice similarity coefficients of 98.5% for femoral and tibial bone, 85.0% for femoral cartilage, and 70.8% for tibial cartilage. The average inference time per one subject was under 30 seconds, demonstrating a reduction in processing time compared to manual annotation. These results suggest that CNN-based segmentation offers a reliable and efficient alternative to manual segmentation, enhancing diagnostic workflows in osteoarthritis monitoring.
DOI:10.23919/MEASUREMENT66999.2025.11078684