Spine labeling in MRI via regularized distribution matching

PurposeThis study investigates an efficient (nearly real-time) two-stage spine labeling algorithm that removes the need for an external training while being applicable to different types of MRI data and acquisition protocols.MethodsBased solely on the image being labeled (i.e., we do not use training data), the first stage aims at detecting potential vertebra candidates following the optimization of a functional containing two terms: (i) a distribution-matching term that encodes contextual information about the vertebrae via a density model learned from a very simple user input, which amounts to a point (mouse click) on a predefined vertebra; and (ii) a regularization constraint, which penalizes isolated candidates in the solution. The second stage removes false positives and identifies all vertebrae and discs by optimizing a geometric constraint, which embeds generic anatomical information on the interconnections between neighboring structures. Based on generic knowledge, our geometric constraint does not require external training.ResultsWe performed quantitative evaluations of the algorithm over a data set of 90 mid-sagittal MRI images of the lumbar spine acquired from 45 different subjects. To assess the flexibility of the algorithm, we used both T1- and T2-weighted images for each subject. A total of 990 structures were automatically detected/labeled and compared to ground-truth annotations by an expert. On the T2-weighted data, we obtained an accuracy of 91.6% for the vertebrae and 89.2% for the discs. On the T1-weighted data, we obtained an accuracy of 90.7% for the vertebrae and 88.1% for the discs.ConclusionOur algorithm removes the need for external training while being applicable to different types of MRI data and acquisition protocols. Based on the current testing data, a subject-specific model density and generic anatomical information, our method can achieve competitive performances when applied to T1- and T2-weighted MRI images.

[1]  Hao Chen,et al.  Automatic Localization and Identification of Vertebrae in Spine CT via a Joint Learning Model with Deep Neural Networks , 2015, MICCAI.

[2]  Ismail Ben Ayed,et al.  Pseudo-bound Optimization for Binary Energies , 2014, ECCV.

[3]  Shuo Li,et al.  Computational Methods and Clinical Applications for Spine Imaging , 2018, Lecture Notes in Computer Science.

[4]  Mila Nikolova,et al.  Algorithms for Finding Global Minimizers of Image Segmentation and Denoising Models , 2006, SIAM J. Appl. Math..

[5]  Maria Wimmer,et al.  Local entropy-optimized texture models for semi-automatic spine labeling in various MRI protocols , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[6]  ANTONIN CHAMBOLLE,et al.  An Algorithm for Total Variation Minimization and Applications , 2004, Journal of Mathematical Imaging and Vision.

[7]  Xue-Cheng Tai,et al.  A study on continuous max-flow and min-cut approaches , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Shang-Hong Lai,et al.  Learning-Based Vertebra Detection and Iterative Normalized-Cut Segmentation for Spinal MRI , 2009, IEEE Transactions on Medical Imaging.

[9]  Timothy F. Cootes,et al.  Automatic Location of Vertebrae on DXA Images Using Random Forest Regression , 2012, MICCAI.

[10]  Shuo Li,et al.  Distribution Matching with the Bhattacharyya Similarity: A Bound Optimization Framework , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Daguang Xu,et al.  Automatic Vertebra Labeling in Large-Scale 3D CT using Deep Image-to-Image Network with Message Passing and Sparsity Regularization , 2017, IPMI.

[12]  Julien Cohen-Adad,et al.  Automatic Labeling of Vertebral Levels Using a Robust Template-Based Approach , 2014, Int. J. Biomed. Imaging.

[13]  S. Li,et al.  Regression Segmentation for $M^{3}$ Spinal Images , 2015, IEEE Transactions on Medical Imaging.

[14]  Yiqiang Zhan,et al.  Robust MR Spine Detection Using Hierarchical Learning and Local Articulated Model , 2012, MICCAI.

[15]  Sebastian P. M. Dries,et al.  Spine Detection and Labeling Using a Parts-Based Graphical Model , 2007, IPMI.

[16]  Dimitri P. Bertsekas,et al.  Nonlinear Programming , 1997 .

[17]  Jun Ma,et al.  Hierarchical segmentation and identification of thoracic vertebra using learning-based edge detection and coarse-to-fine deformable model , 2010, Comput. Vis. Image Underst..

[18]  D. Fardon,et al.  Nomenclature and classification of lumbar disc pathology. Recommendations of the Combined task Forces of the North American Spine Society, American Society of Spine Radiology, and American Society of Neuroradiology. , 2001, Spine.

[19]  Ayse Betül Oktay,et al.  Localization of the Lumbar Discs Using Machine Learning and Exact Probabilistic Inference , 2011, MICCAI.

[20]  Cristian Lorenz,et al.  Automated model-based vertebra detection, identification, and segmentation in CT images , 2009, Medical Image Anal..

[21]  Jason J. Corso,et al.  Labeling of Lumbar Discs Using Both Pixel- and Object-Level Features With a Two-Level Probabilistic Model , 2011, IEEE Transactions on Medical Imaging.

[22]  Ben Glocker,et al.  Automatic Localization and Identification of Vertebrae in Arbitrary Field-of-View CT Scans , 2012, MICCAI.

[23]  Julien Cohen-Adad,et al.  Automatic Segmentation of the Spinal Cord and Spinal Canal Coupled With Vertebral Labeling , 2015, IEEE Transactions on Medical Imaging.

[24]  Takeshi Naemura,et al.  Superdifferential cuts for binary energies , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Jing Yuan,et al.  A Convex Max-Flow Approach to Distribution-Based Figure-Ground Separation , 2012, SIAM J. Imaging Sci..

[26]  Ben Glocker,et al.  Vertebrae Localization in Pathological Spine CT via Dense Classification from Sparse Annotations , 2013, MICCAI.

[27]  Dorin Comaniciu,et al.  Spine detection in CT and MR using iterated marginal space learning , 2013, Medical Image Anal..

[28]  Guoyan Zheng,et al.  Computational Methods and Clinical Applications for Spine Imaging , 2016, Lecture Notes in Computer Science.

[29]  Aaron Fenster,et al.  Spine Image Fusion Via Graph Cuts , 2013, IEEE Transactions on Biomedical Engineering.

[30]  Jing Yuan,et al.  Convex-Relaxed Kernel Mapping for Image Segmentation , 2014, IEEE Transactions on Image Processing.

[31]  Shuo Li,et al.  Multi-modal vertebrae recognition using Transformed Deep Convolution Network , 2016, Comput. Medical Imaging Graph..