Literature DB >> 29916062

3D surface voxel tracing corrector for accurate bone segmentation.

Haoyan Guo1, Sicong Song1, Jinke Wang1, Maozu Guo2, Yuanzhi Cheng3, Yadong Wang1, Shinichi Tamura4.   

Abstract

PURPOSE: For extremely close bones, their boundaries are weak and diffused due to strong interaction between adjacent surfaces. These factors prevent the accurate segmentation of bone structure. To alleviate these difficulties, we propose an automatic method for accurate bone segmentation. The method is based on a consideration of the 3D surface normal direction, which is used to detect the bone boundary in 3D CT images.
METHODS: Our segmentation method is divided into three main stages. Firstly, we consider a surface tracing corrector combined with Gaussian standard deviation [Formula: see text] to improve the estimation of normal direction. Secondly, we determine an optimal value of [Formula: see text] for each surface point during this normal direction correction. Thirdly, we construct the 1D signal and refining the rough boundary along the corrected normal direction. The value of [Formula: see text] is used in the first directional derivative of the Gaussian to refine the location of the edge point along accurate normal direction. Because the normal direction is corrected and the value of [Formula: see text] is optimized, our method is robust to noise images and narrow joint space caused by joint degeneration.
RESULTS: We applied our method to 15 wrists and 50 hip joints for evaluation. In the wrist segmentation, Dice overlap coefficient (DOC) of [Formula: see text]% was obtained by our method. In the hip segmentation, fivefold cross-validations were performed for two state-of-the-art methods. Forty hip joints were used for training in two state-of-the-art methods, 10 hip joints were used for testing and performing comparisons. The DOCs of [Formula: see text], [Formula: see text]%, and [Formula: see text]% were achieved by our method for the pelvis, the left femoral head and the right femoral head, respectively.
CONCLUSION: Our method was shown to improve segmentation accuracy for several specific challenging cases. The results demonstrate that our approach achieved a superior accuracy over two state-of-the-art methods.

Entities:  

Keywords:  Bone segmentation; CT images; Deformable model; Femur and pelvis; Image segmentation; Surface normal direction

Mesh:

Year:  2018        PMID: 29916062     DOI: 10.1007/s11548-018-1804-9

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


  19 in total

1.  An adaptive level set segmentation on a triangulated mesh.

Authors:  Meihe Xu; Paul M Thompson; Arthur W Toga
Journal:  IEEE Trans Med Imaging       Date:  2004-02       Impact factor: 10.048

2.  Decoupled active contour (DAC) for boundary detection.

Authors:  Akshaya Kumar Mishra; Paul W Fieguth; David A Clausi
Journal:  IEEE Trans Pattern Anal Mach Intell       Date:  2011-02       Impact factor: 6.226

3.  Automatic classification of pulmonary peri-fissural nodules in computed tomography using an ensemble of 2D views and a convolutional neural network out-of-the-box.

Authors:  Francesco Ciompi; Bartjan de Hoop; Sarah J van Riel; Kaman Chung; Ernst Th Scholten; Matthijs Oudkerk; Pim A de Jong; Mathias Prokop; Bram van Ginneken
Journal:  Med Image Anal       Date:  2015-09-08       Impact factor: 8.545

Review 4.  Thresholding technique for accurate analysis of density and geometry in QCT, pQCT and microCT images.

Authors:  T N Hangartner
Journal:  J Musculoskelet Neuronal Interact       Date:  2007 Jan-Mar       Impact factor: 2.041

5.  Adaptive thresholding by variational method.

Authors:  F Y Chan; F K Lam; H Zhu
Journal:  IEEE Trans Image Process       Date:  1998       Impact factor: 10.856

6.  A computational approach to edge detection.

Authors:  J Canny
Journal:  IEEE Trans Pattern Anal Mach Intell       Date:  1986-06       Impact factor: 6.226

7.  Fully automatic segmentation of the proximal femur using random forest regression voting.

Authors:  C Lindner; S Thiagarajah; J M Wilkinson; G A Wallis; T F Cootes
Journal:  IEEE Trans Med Imaging       Date:  2013-04-12       Impact factor: 10.048

8.  Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis.

Authors:  Heung-Il Suk; Seong-Whan Lee; Dinggang Shen
Journal:  Neuroimage       Date:  2014-07-18       Impact factor: 6.556

9.  Focused shape models for hip joint segmentation in 3D magnetic resonance images.

Authors:  Shekhar S Chandra; Ying Xia; Craig Engstrom; Stuart Crozier; Raphael Schwarz; Jurgen Fripp
Journal:  Med Image Anal       Date:  2014-02-18       Impact factor: 8.545

10.  Robust statistical shape models for MRI bone segmentation in presence of small field of view.

Authors:  Jérôme Schmid; Jinman Kim; Nadia Magnenat-Thalmann
Journal:  Med Image Anal       Date:  2010-09-24       Impact factor: 8.545

View more
  2 in total

1.  Semi-automatic micro-CT segmentation of the midfoot using calibrated thresholds.

Authors:  Melissa R Requist; Yantarat Sripanich; Andrew C Peterson; Tim Rolvien; Alexej Barg; Amy L Lenz
Journal:  Int J Comput Assist Radiol Surg       Date:  2021-02-19       Impact factor: 2.924

2.  Reliability of 3D image analysis and influence of contrast medium administration on measurement of Hounsfield unit values of the proximal femur.

Authors:  Hye-Won Lee; Hong Il Ha; Sun-Young Park; Hyun Kyung Lim
Journal:  PLoS One       Date:  2020-10-21       Impact factor: 3.240

  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.