Literature DB >> 28785960

Spine labeling in MRI via regularized distribution matching.

Seyed-Parsa Hojjat1, Ismail Ayed2, Gregory J Garvin3, Kumaradevan Punithakumar4.   

Abstract

PURPOSE: This 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.
METHODS: Based 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.
RESULTS: We 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.
CONCLUSION: Our 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.

Entities:  

Keywords:  Distribution matching; Geometric constraints; Magnetic resonance imaging (MRI); Regularization; Spine labelling

Mesh:

Year:  2017        PMID: 28785960     DOI: 10.1007/s11548-017-1651-0

Source DB:  PubMed          Journal:  Int J Comput Assist Radiol Surg        ISSN: 1861-6410            Impact factor:   2.924


  19 in total

1.  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.

Authors:  D F Fardon; P C Milette
Journal:  Spine (Phila Pa 1976)       Date:  2001-03-01       Impact factor: 3.468

2.  Labeling of lumbar discs using both pixel- and object-level features with a two-level probabilistic model.

Authors:  Raja' S Alomari; Jason J Corso; Vipin Chaudhary
Journal:  IEEE Trans Med Imaging       Date:  2010-04-08       Impact factor: 10.048

3.  Distribution Matching with the Bhattacharyya Similarity: A Bound Optimization Framework.

Authors:  Ismail Ben Ayed; Kumaradevan Punithakumar
Journal:  IEEE Trans Pattern Anal Mach Intell       Date:  2015-09       Impact factor: 6.226

4.  Automated model-based vertebra detection, identification, and segmentation in CT images.

Authors:  Tobias Klinder; Jörn Ostermann; Matthias Ehm; Astrid Franz; Reinhard Kneser; Cristian Lorenz
Journal:  Med Image Anal       Date:  2009-02-20       Impact factor: 8.545

5.  Multi-modal vertebrae recognition using Transformed Deep Convolution Network.

Authors:  Yunliang Cai; Mark Landis; David T Laidley; Anat Kornecki; Andrea Lum; Shuo Li
Journal:  Comput Med Imaging Graph       Date:  2016-04-08       Impact factor: 4.790

6.  Regression Segmentation for M³ Spinal Images.

Authors:  Zhijie Wang; Xiantong Zhen; KengYeow Tay; Said Osman; Walter Romano; Shuo Li
Journal:  IEEE Trans Med Imaging       Date:  2014-10-29       Impact factor: 10.048

7.  Spine detection in CT and MR using iterated marginal space learning.

Authors:  B Michael Kelm; Michael Wels; S Kevin Zhou; Sascha Seifert; Michael Suehling; Yefeng Zheng; Dorin Comaniciu
Journal:  Med Image Anal       Date:  2012-12-01       Impact factor: 8.545

8.  Spine image fusion via graph cuts.

Authors:  Brandon Miles; Ismail Ben Ayed; Max W K Law; Greg Garvin; Aaron Fenster; Shuo Li
Journal:  IEEE Trans Biomed Eng       Date:  2013-01-29       Impact factor: 4.538

9.  Robust MR spine detection using hierarchical learning and local articulated model.

Authors:  Yiqiang Zhan; Dewan Maneesh; Martin Harder; Xiang Sean Zhou
Journal:  Med Image Comput Comput Assist Interv       Date:  2012

10.  Convex-relaxed kernel mapping for image segmentation.

Authors:  Mohamed Ben Salah; Ismail Ben Ayed
Journal:  IEEE Trans Image Process       Date:  2014-03       Impact factor: 10.856

View more
  1 in total

1.  Fully automatic cross-modality localization and labeling of vertebral bodies and intervertebral discs in 3D spinal images.

Authors:  Maria Wimmer; David Major; Alexey A Novikov; Katja Bühler
Journal:  Int J Comput Assist Radiol Surg       Date:  2018-07-19       Impact factor: 2.924

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.