Segmenting Articular Cartilage Automatically Using a Voxel Classification Approach

IT Univ. of Copenhagen
IEEE Transactions on Medical Imaging (Impact Factor: 3.39). 02/2007; 26(1):106 - 115. DOI: 10.1109/TMI.2006.886808
Source: DBLP

ABSTRACT 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

Download full-text


Available from: Jenny Folkesson, Mar 14, 2013
1 Follower
26 Reads
  • Source
    • "Since performing such segmentations manually is very time consuming and prone to inter-and intra-observer variabilities, a large variety of algorithms has been developed to perform automated segmentation . Many methods for automated image segmentation are based on supervised learning (Anbeek et al., 2005; Folkesson et al., 2007; Geremia et al., 2011; Van der Lijn et al., 2008; Liu et al., 2006; Van Opbroek et al., 2013b), where a segmentation model is trained on a manually annotated set of training images. To train a successful model, these supervised-learning techniques require a training set that is both sufficiently large to capture a large variation of appearances and representative of the target data. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Many automatic segmentation methods are based on supervised machine learning. Such methods have proven to perform well, on the condition that they are trained on a sufficiently large manually labeled training set that is representative of the images to segment. However, due to differences between scanners, scanning parameters, and patients such a training set may be difficult to obtain. We present a transfer-learning approach to segmentation by multi-feature voxelwise classification. The presented method can be trained using a heterogeneous set of training images that may be obtained with different scanners than the target image. In our approach each training image is given a weight based on the distribution of its voxels in the feature space. These image weights are chosen as to minimize the difference between the weighted probability density function (PDF) of the voxels of the training images and the PDF of the voxels of the target image. The voxels and weights of the training images are then used to train a weighted classifier. We tested our method on three segmentation tasks: brain-tissue segmentation, skull stripping, and white-matter-lesion segmentation. For all three applications, the proposed weighted classifier significantly outperformed an unweighted classifier on all training images, reducing classification errors by up to 42%. For brain-tissue segmentation and skull stripping our method even significantly outperformed the traditional approach of training on representative training images from the same study as the target image. Copyright © 2015 Elsevier B.V. All rights reserved.
    Medical image analysis 07/2015; 24(1):245-254. DOI:10.1016/ · 3.65 Impact Factor
  • Source
    • "We have reviewed relevant works in segmentation software for knee bones and cartilages in automated and interactive approaches. [25] first obtained a bone-cartilage interface (BCI) using bone statistical shape model and then extracted the cartilage from the BCI based on modified tissue classification method introduced by [26]. Although the authors claimed that their segmentation software was fully automated, the bone statistical shape model atlas was created by manual segmentation. "
    [Show abstract] [Hide abstract]
    ABSTRACT: In medical image segmentation, manual segmentation is considered both labor- and time-intensive while automated segmentation often fails to segment anatomically intricate structure accordingly. Interactive segmentation can tackle shortcomings reported by previous segmentation approaches through user intervention. To better reflect user intention, development of suitable editing functions is critical. In this paper, we propose an interactive knee cartilage extraction software that covers three important features: intuitiveness, speed, and convenience. The segmentation is performed using multi-label random walks algorithm. Our segmentation software is simple to use, intuitive to normal and osteoarthritic image segmentation and efficient using only two third of manual segmentation's time. Future works will extend this software to three dimensional segmentation and quantitative analysis.
    Bio-medical materials and engineering 09/2014; 24(6):3145-57. DOI:10.3233/BME-141137 · 1.09 Impact Factor
  • Source
    • "Compared to [1], we use a probabilistic version of kNN classification to integrate the classification results into a Bayesian framework. We choose a reduced set of 15 features compared to [1]: intensities on three scales, first-order derivatives in three directions on three scales and second-order derivatives in axial direction on three scales. The three different scales are obtained by convolving with Gaussian kernels of σ = 0.3 mm, 0.6 mm and 1.0 mm. "
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a multi-atlas-based method to automatically segment the femoral and tibial cartilage from T1 weighted magnetic resonance (MR) knee images. The segmentation result is a joint decision of the spatial priors from a multi-atlas registration and the local likelihoods within a Bayesian framework. The cartilage likelihoods are obtained from a probabilistic k nearest neighbor classification. Validation results on 18 knee MR images against the manual expert segmentations from a dataset acquired for osteoarthritis research show good performance for the segmentation of femoral and tibial cartilage (mean Dice similarity coefficient of 75.2% and 81.7% respectively).
    Proceedings / IEEE International Symposium on Biomedical Imaging: from nano to macro. IEEE International Symposium on Biomedical Imaging 12/2012; 2012:1028-1031. DOI:10.1109/ISBI.2012.6235733
Show more