Automatic segmentation of cartilage in high-field magnetic resonance images of the knee joint with an improved voxel-classification-driven region-growing algorithm using vicinity-correlated subsampling

Anatomical structures that can deteriorate over time, such as cartilage, can be successfully delineated with voxel-classification approaches in magnetic resonance (MR) images. However, segmentation via voxel-classification is a computationally demanding process for high-field MR images with high spatial resolutions. In this study, the whole femoral, tibial, and patellar cartilage compartments in the knee joint were automatically segmented in high-field MR images obtained from Osteoarthritis Initiative using a voxel-classification-driven region-growing algorithm with sample-expand method. Computational complexity of the classification was alleviated via subsampling of the background voxels in the training MR images and selecting a small subset of significant features by taking into consideration systems with limited memory and processing power. Although subsampling of the voxels may lead to a loss of generality of the training models and a decrease in segmentation accuracies, effective subsampling strategies can overcome these problems. Therefore, different subsampling techniques, which involve uniform, Gaussian, vicinity-correlated (VC) sparse, and VC dense subsampling, were used to generate four training models. The segmentation system was experimented using 10 training and 23 testing MR images, and the effects of different training models on segmentation accuracies were investigated. Experimental results showed that the highest mean Dice similarity coefficient (DSC) values for all compartments were obtained when the training models of VC sparse subsampling technique were used. Mean DSC values optimized with this technique were 82.6%, 83.1%, and 72.6% for femoral, tibial, and patellar cartilage compartments, respectively, when mean sensitivities were 79.9%, 84.0%, and 71.5%, and mean specificities were 99.8%, 99.9%, and 99.9%.

[1]  Sunil Arya,et al.  An optimal algorithm for approximate nearest neighbor searching fixed dimensions , 1998, JACM.

[2]  José G. Tamez-Peña,et al.  Unsupervised Segmentation and Quantification of Anatomical Knee Features: Data From the Osteoarthritis Initiative , 2012, IEEE Transactions on Biomedical Engineering.

[3]  Demetri Terzopoulos,et al.  Deformable models in medical image analysis: a survey , 1996, Medical Image Anal..

[4]  Meritxell Bach Cuadra,et al.  A review of atlas-based segmentation for magnetic resonance brain images , 2011, Comput. Methods Programs Biomed..

[5]  Bernhard Preim,et al.  Visualization in Medicine: Theory, Algorithms, and Applications , 2007 .

[6]  Milan Sonka,et al.  3-D active appearance models: segmentation of cardiac MR and ultrasound images , 2002, IEEE Transactions on Medical Imaging.

[7]  Aamir Saeed Malik,et al.  Multinuclear MR and multilevel data processing: an insight into morphologic assessment of in vivo knee articular cartilage. , 2015, Academic radiology.

[8]  Stuart Crozier,et al.  Automatic Segmentation and Quantitative Analysis of the Articular Cartilages From Magnetic Resonance Images of the Knee , 2010, IEEE Transactions on Medical Imaging.

[9]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[10]  Kim L. Boyer,et al.  Semantic Context Forests for Learning-Based Knee Cartilage Segmentation in 3D MR Images , 2013, MCV.

[11]  J. Sethian,et al.  Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations , 1988 .

[12]  Russell H. Taylor,et al.  A Perspective on Medical Robotics , 2006, Proceedings of the IEEE.

[13]  June-Goo Lee,et al.  Fully automated segmentation of cartilage from the MR images of knee using a multi-atlas and local structural analysis method. , 2014, Medical physics.

[14]  Pierre Hellier,et al.  Segmentation of brain 3D MR images using level sets and dense registration , 2001, Medical Image Anal..

[15]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  David Zhang,et al.  A survey of graph theoretical approaches to image segmentation , 2013, Pattern Recognit..

[17]  Christopher J. Taylor,et al.  Anatomically Corresponded Regional Analysis of Cartilage in Asymptomatic and Osteoarthritic Knees by Statistical Shape Modelling of the Bone , 2010, IEEE Transactions on Medical Imaging.

[18]  Aamir Saeed Malik,et al.  Automatic segmentation of articular cartilage from combined assessment of sodium and proton MR knee images , 2013 .

[19]  Hans-Peter Meinzer,et al.  Active Shape Models for a Fully Automated 3D Segmentation of the Liver - An Evaluation on Clinical Data , 2006, MICCAI.

[20]  Pina Marziliano,et al.  Automatic knee cartilage segmentation from multi-contrast MR images using support vector machine classification with spatial dependencies. , 2013, Magnetic resonance imaging.

[21]  C E Hutchinson,et al.  Measurement and visualisation of focal cartilage thickness change by MRI in a study of knee osteoarthritis using a novel image analysis tool. , 2010, The British journal of radiology.

[22]  Marc Niethammer,et al.  Automatic atlas-based three-label cartilage segmentation from MR knee images , 2014, 2012 IEEE Workshop on Mathematical Methods in Biomedical Image Analysis.

[23]  Xiaodong Wu,et al.  LOGISMOS—Layered Optimal Graph Image Segmentation of Multiple Objects and Surfaces: Cartilage Segmentation in the Knee Joint , 2010, IEEE Transactions on Medical Imaging.

[24]  Marco Loog,et al.  Efficient Segmentation by Sparse Pixel Classification , 2008, IEEE Transactions on Medical Imaging.

[25]  Mads Nielsen,et al.  Automatic segmentation of high- and low-field knee MRIs using knee image quantification with data from the osteoarthritis initiative , 2015, Journal of medical imaging.

[26]  Ole Fogh Olsen,et al.  Combining Binary Classifiers for Automatic Cartilage Segmentation in Knee MRI , 2005, CVBIA.

[27]  T. Mosher,et al.  Articular cartilage in the knee: current MR imaging techniques and applications in clinical practice and research. , 2011, Radiographics : a review publication of the Radiological Society of North America, Inc.

[28]  F. Eckstein,et al.  Magnetic resonance imaging (MRI) of articular cartilage in knee osteoarthritis (OA): morphological assessment. , 2006, Osteoarthritis and cartilage.

[29]  Hans-Peter Meinzer,et al.  Statistical shape models for 3D medical image segmentation: A review , 2009, Medical Image Anal..

[30]  Sang Hyun Park,et al.  Optimization of local shape and appearance probabilities for segmentation of knee cartilage in 3-D MR images , 2011, Comput. Vis. Image Underst..

[31]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[32]  Wolfgang Birkfellner,et al.  Applied Medical Image Processing: A Basic Course , 2010 .

[33]  Ole Fogh Olsen,et al.  Segmenting Articular Cartilage Automatically Using a Voxel Classification Approach , 2007, IEEE Transactions on Medical Imaging.