Segmenting articular cartilage automatically using a voxel classification approach
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Segmenting articular cartilage automatically using a voxel classification approach. / Folkesson, Jenny; Dam, Erik B; Olsen, Ole F; Pettersen, Paola C; Christiansen, Claus.
In: IEEE Transactions on Medical Imaging, Vol. 26, No. 1, 01.2007, p. 106-15.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Segmenting articular cartilage automatically using a voxel classification approach
AU - Folkesson, Jenny
AU - Dam, Erik B
AU - Olsen, Ole F
AU - Pettersen, Paola C
AU - Christiansen, Claus
PY - 2007/1
Y1 - 2007/1
N2 - We present a fully automatic method for articular cartilage segmentation from magnetic resonance imaging (MRI) which we use as the foundation of a quantitative cartilage assessment. We evaluate our method by comparisons to manual segmentations by a radiologist and by examining the interscan reproducibility of the volume and area estimates. Training and evaluation of the method is performed on a data set consisting of 139 scans of knees with a status ranging from healthy to severely osteoarthritic. This is, to our knowledge, the only fully automatic cartilage segmentation method that has good agreement with manual segmentations, an interscan reproducibility as good as that of a human expert, and enables the separation between healthy and osteoarthritic populations. While high-field scanners offer high-quality imaging from which the articular cartilage have been evaluated extensively using manual and automated image analysis techniques, low-field scanners on the other hand produce lower quality images but to a fraction of the cost of their high-field counterpart. For low-field MRI, there is no well-established accuracy validation for quantitative cartilage estimates, but we show that differences between healthy and osteoarthritic populations are statistically significant using our cartilage volume and surface area estimates, which suggests that low-field MRI analysis can become a useful, affordable tool in clinical studies.
AB - We present a fully automatic method for articular cartilage segmentation from magnetic resonance imaging (MRI) which we use as the foundation of a quantitative cartilage assessment. We evaluate our method by comparisons to manual segmentations by a radiologist and by examining the interscan reproducibility of the volume and area estimates. Training and evaluation of the method is performed on a data set consisting of 139 scans of knees with a status ranging from healthy to severely osteoarthritic. This is, to our knowledge, the only fully automatic cartilage segmentation method that has good agreement with manual segmentations, an interscan reproducibility as good as that of a human expert, and enables the separation between healthy and osteoarthritic populations. While high-field scanners offer high-quality imaging from which the articular cartilage have been evaluated extensively using manual and automated image analysis techniques, low-field scanners on the other hand produce lower quality images but to a fraction of the cost of their high-field counterpart. For low-field MRI, there is no well-established accuracy validation for quantitative cartilage estimates, but we show that differences between healthy and osteoarthritic populations are statistically significant using our cartilage volume and surface area estimates, which suggests that low-field MRI analysis can become a useful, affordable tool in clinical studies.
KW - Adult
KW - Aged
KW - Algorithms
KW - Artificial Intelligence
KW - Cartilage, Articular
KW - Cluster Analysis
KW - Female
KW - Humans
KW - Image Enhancement
KW - Image Interpretation, Computer-Assisted
KW - Imaging, Three-Dimensional
KW - Information Storage and Retrieval
KW - Male
KW - Middle Aged
KW - Osteoarthritis
KW - Pattern Recognition, Automated
KW - Reproducibility of Results
KW - Sensitivity and Specificity
KW - Signal Processing, Computer-Assisted
KW - Evaluation Studies
KW - Journal Article
U2 - 10.1109/TMI.2006.886808
DO - 10.1109/TMI.2006.886808
M3 - Journal article
C2 - 17243589
VL - 26
SP - 106
EP - 115
JO - I E E E Transactions on Medical Imaging
JF - I E E E Transactions on Medical Imaging
SN - 0278-0062
IS - 1
ER -
ID: 187555202