Back to Search
Start Over
Deep learning‐based fully automatic segmentation of wrist cartilage in MR images
- Source :
- NMR in Biomedicine, NMR in Biomedicine, Wiley, 2020, 33 (8), ⟨10.1002/nbm.4320⟩, NMR Biomed, NMR in Biomedicine, 2020, 33 (8), ⟨10.1002/nbm.4320⟩
- Publication Year :
- 2020
- Publisher :
- Wiley, 2020.
-
Abstract
- The study objective was to investigate the performance of a dedicated convolutional neural network (CNN) optimized for wrist cartilage segmentation from 2D MR images. CNN utilized a planar architecture and patch-based (PB) training approach that ensured optimal performance in the presence of a limited amount of training data. The CNN was trained and validated in twenty multi-slice MRI datasets acquired with two different coils in eleven subjects (healthy volunteers and patients). The validation included a comparison with the alternative state-of-the-art CNN methods for the segmentation of joints from MR images and the ground-truth manual segmentation. When trained on the limited training data, the CNN outperformed significantly image-based and patch-based U-Net networks. Our PB-CNN also demonstrated a good agreement with manual segmentation (Sørensen–Dice similarity coefficient (DSC) = 0.81) in the representative (central coronal) slices with large amount of cartilage tissue. Reduced performance of the network for slices with a very limited amount of cartilage tissue suggests the need for fully 3D convolutional networks to provide uniform performance across the joint. The study also assessed inter- and intra-observer variability of the manual wrist cartilage segmentation (DSC=0.78–0.88 and 0.9, respectively). The proposed deep-learning-based segmentation of the wrist cartilage from MRI could facilitate research of novel imaging markers of wrist osteoarthritis to characterize its progression and response to therapy.
- Subjects :
- Adult
Male
Computer science
Wrist
Convolutional neural network
Article
030218 nuclear medicine & medical imaging
03 medical and health sciences
Deep Learning
0302 clinical medicine
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]
Osteoarthritis
Image Processing, Computer-Assisted
[INFO.INFO-IM]Computer Science [cs]/Medical Imaging
medicine
Humans
Radiology, Nuclear Medicine and imaging
Segmentation
ComputingMilieux_MISCELLANEOUS
Spectroscopy
Aged
business.industry
Cartilage
Deep learning
Reproducibility of Results
Pattern recognition
Middle Aged
medicine.disease
Magnetic Resonance Imaging
Wrist osteoarthritis
medicine.anatomical_structure
[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]
Coronal plane
Molecular Medicine
Female
Neural Networks, Computer
Artificial intelligence
Mr images
business
030217 neurology & neurosurgery
Subjects
Details
- ISSN :
- 10991492 and 09523480
- Volume :
- 33
- Database :
- OpenAIRE
- Journal :
- NMR in Biomedicine
- Accession number :
- edsair.doi.dedup.....ffbbd019cb67194c0e9dd6f916a41a91