Automated classification of bone and air volumes for hybrid PET-MRI brain imaging

Sze Liang Stanley Chan; Yaniv Gal; Rosalind L. Jeffree; Michael Fay; Paul Thomas; Stuart Crozier; Zhengyi Yang

doi:10.1109/DICTA.2013.6691483

Automated classification of bone and air volumes for hybrid PET-MRI brain imaging

Sze Liang Stanley Chan, Yaniv Gal, Rosalind L. Jeffree, Michael Fay, Paul Thomas, Stuart Crozier, Zhengyi Yang

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

12 Citations (Scopus)

Abstract

In clinically applicable structural magnetic resonance images (MRI), bone and air have similarly low signal intensity, making the differentiation between them a very challenging task. MRI-based bone/air segmentation, however, is a critical step in some emerging applications, such as skull atlas building, MRI-based attenuation correction for Positron Emission Tomography (PET), and MRI-based radiotherapy planning. In view of the availability of hybrid PET-MRI machines, we propose a voxel-wise classification method for bone/air segmentation. The method is based on random forest theory and features extracted from structural MRI and attenuation uncorrected PET. The Dice Similarity Score (DSC) score between the segmentation result and the 'ground truth' obtained by thresholding Computed Tomography images was calculated for validation. Images from 10 subjects were used for validation, achieving a DSC of 0.83±0.08 and 0.98±0.01 for air and bone, respectively. The results suggest that structural MRI and uncorrected PET can be used to reliably differentiate between air and bone.

Original language	English
Title of host publication	2013 International Conference on Digital Image Computing
Subtitle of host publication	Techniques and Applications, DICTA 2013
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Number of pages	8
ISBN (Print)	9781479921263
DOIs	https://doi.org/10.1109/DICTA.2013.6691483
Publication status	Published - 2013
Externally published	Yes
Event	Digital Image Computing Techniques and Applications 2013 - Wrest Point Hotel, Hobart, Australia Duration: 26 Nov 2013 → 28 Nov 2013 Conference number: 15th http://staff.itee.uq.edu.au/lovell/aprs/dicta13/index.html https://ieeexplore.ieee.org/xpl/conhome/6689677/proceeding (Proceedings)

Conference

Conference	Digital Image Computing Techniques and Applications 2013
Abbreviated title	DICTA 2013
Country/Territory	Australia
City	Hobart
Period	26/11/13 → 28/11/13
Other	The International Conference on Digital Image Computing: Techniques and Applications (DICTA) is the main Australian Conference on computer vision, image processing, pattern recognition, and related areas. DICTA was established as a biennial conference in 1991 and became an annual event in 2007. It is the premier conference of the Australian Pattern Recognition Society (APRS). The conference will be held at Wrest Point Hotel, Hobart, Tasmania, Australia from 26 - 28 November 2013.
Internet address	http://staff.itee.uq.edu.au/lovell/aprs/dicta13/index.html https://ieeexplore.ieee.org/xpl/conhome/6689677/proceeding (Proceedings)

Keywords

Attenuation correction
Multi-modal imaging
PET-MRI
Random forest
Tissue classification

Access to Document

10.1109/DICTA.2013.6691483

Cite this

Chan, S. L. S., Gal, Y., Jeffree, R. L., Fay, M., Thomas, P., Crozier, S., & Yang, Z. (2013). Automated classification of bone and air volumes for hybrid PET-MRI brain imaging. In 2013 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2013 Article 6691483 IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/DICTA.2013.6691483

@inproceedings{15c076d295964f3f8dca336524c9c2f7,

title = "Automated classification of bone and air volumes for hybrid PET-MRI brain imaging",

abstract = "In clinically applicable structural magnetic resonance images (MRI), bone and air have similarly low signal intensity, making the differentiation between them a very challenging task. MRI-based bone/air segmentation, however, is a critical step in some emerging applications, such as skull atlas building, MRI-based attenuation correction for Positron Emission Tomography (PET), and MRI-based radiotherapy planning. In view of the availability of hybrid PET-MRI machines, we propose a voxel-wise classification method for bone/air segmentation. The method is based on random forest theory and features extracted from structural MRI and attenuation uncorrected PET. The Dice Similarity Score (DSC) score between the segmentation result and the 'ground truth' obtained by thresholding Computed Tomography images was calculated for validation. Images from 10 subjects were used for validation, achieving a DSC of 0.83±0.08 and 0.98±0.01 for air and bone, respectively. The results suggest that structural MRI and uncorrected PET can be used to reliably differentiate between air and bone.",

keywords = "Attenuation correction, Multi-modal imaging, PET-MRI, Random forest, Tissue classification",

author = "Chan, \{Sze Liang Stanley\} and Yaniv Gal and Jeffree, \{Rosalind L.\} and Michael Fay and Paul Thomas and Stuart Crozier and Zhengyi Yang",

year = "2013",

doi = "10.1109/DICTA.2013.6691483",

language = "English",

isbn = "9781479921263",

booktitle = "2013 International Conference on Digital Image Computing",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "Digital Image Computing Techniques and Applications 2013, DICTA 2013 ; Conference date: 26-11-2013 Through 28-11-2013",

url = "http://staff.itee.uq.edu.au/lovell/aprs/dicta13/index.html, https://ieeexplore.ieee.org/xpl/conhome/6689677/proceeding",

}

Chan, SLS, Gal, Y, Jeffree, RL, Fay, M, Thomas, P, Crozier, S & Yang, Z 2013, Automated classification of bone and air volumes for hybrid PET-MRI brain imaging. in 2013 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2013., 6691483, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, Digital Image Computing Techniques and Applications 2013, Hobart, Tasmania, Australia, 26/11/13. https://doi.org/10.1109/DICTA.2013.6691483

Automated classification of bone and air volumes for hybrid PET-MRI brain imaging. / Chan, Sze Liang Stanley; Gal, Yaniv; Jeffree, Rosalind L. et al.
2013 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2013. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers, 2013. 6691483.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Automated classification of bone and air volumes for hybrid PET-MRI brain imaging

AU - Chan, Sze Liang Stanley

AU - Gal, Yaniv

AU - Jeffree, Rosalind L.

AU - Fay, Michael

AU - Thomas, Paul

AU - Crozier, Stuart

AU - Yang, Zhengyi

N1 - Conference code: 15th

PY - 2013

Y1 - 2013

N2 - In clinically applicable structural magnetic resonance images (MRI), bone and air have similarly low signal intensity, making the differentiation between them a very challenging task. MRI-based bone/air segmentation, however, is a critical step in some emerging applications, such as skull atlas building, MRI-based attenuation correction for Positron Emission Tomography (PET), and MRI-based radiotherapy planning. In view of the availability of hybrid PET-MRI machines, we propose a voxel-wise classification method for bone/air segmentation. The method is based on random forest theory and features extracted from structural MRI and attenuation uncorrected PET. The Dice Similarity Score (DSC) score between the segmentation result and the 'ground truth' obtained by thresholding Computed Tomography images was calculated for validation. Images from 10 subjects were used for validation, achieving a DSC of 0.83±0.08 and 0.98±0.01 for air and bone, respectively. The results suggest that structural MRI and uncorrected PET can be used to reliably differentiate between air and bone.

AB - In clinically applicable structural magnetic resonance images (MRI), bone and air have similarly low signal intensity, making the differentiation between them a very challenging task. MRI-based bone/air segmentation, however, is a critical step in some emerging applications, such as skull atlas building, MRI-based attenuation correction for Positron Emission Tomography (PET), and MRI-based radiotherapy planning. In view of the availability of hybrid PET-MRI machines, we propose a voxel-wise classification method for bone/air segmentation. The method is based on random forest theory and features extracted from structural MRI and attenuation uncorrected PET. The Dice Similarity Score (DSC) score between the segmentation result and the 'ground truth' obtained by thresholding Computed Tomography images was calculated for validation. Images from 10 subjects were used for validation, achieving a DSC of 0.83±0.08 and 0.98±0.01 for air and bone, respectively. The results suggest that structural MRI and uncorrected PET can be used to reliably differentiate between air and bone.

KW - Attenuation correction

KW - Multi-modal imaging

KW - PET-MRI

KW - Random forest

KW - Tissue classification

UR - https://www.scopus.com/pages/publications/84893235302

U2 - 10.1109/DICTA.2013.6691483

DO - 10.1109/DICTA.2013.6691483

M3 - Conference Paper

AN - SCOPUS:84893235302

SN - 9781479921263

BT - 2013 International Conference on Digital Image Computing

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

T2 - Digital Image Computing Techniques and Applications 2013

Y2 - 26 November 2013 through 28 November 2013

ER -

Automated classification of bone and air volumes for hybrid PET-MRI brain imaging

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this