Automated Classification of Bone and Air Volumes for Hybrid PET-MRI Brain Imaging

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.

[1]  Anant Madabhushi,et al.  Textural Kinetics: A Novel Dynamic Contrast-Enhanced (DCE)-MRI Feature for Breast Lesion Classification , 2011, Journal of Digital Imaging.

[2]  J. Daugman.  Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[3]  Stephan G. Nekolla,et al.  Photon attenuation correction in whole-body PET/MRI using tissue classification , 2010, 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[4]  Sébastien Ourselin,et al.  Block Matching: A General Framework to Improve Robustness of Rigid Registration of Medical Images , 2000, MICCAI.

[5]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[6]  E. Hoffman,et al.  Quantitation in positron emission computed tomography: 2. Effects of inaccurate attenuation correction. , 1979, Journal of computer assisted tomography.

[7]  Koenraad Van Leemput,et al.  Automated model-based tissue classification of MR images of the brain , 1999, IEEE Transactions on Medical Imaging.

[8]  H. Zaidi,et al.  Magnetic resonance imaging-guided attenuation and scatter corrections in three-dimensional brain positron emission tomography. , 2003, Medical physics.

[9]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .

[10]  C. Kuhl,et al.  MRI-Based Attenuation Correction for Hybrid PET/MRI Systems: A 4-Class Tissue Segmentation Technique Using a Combined Ultrashort-Echo-Time/Dixon MRI Sequence , 2012, The Journal of Nuclear Medicine.

[11]  Stuart Crozier,et al.  Mutual information-based binarisation of multiple images of an object: an application in medical imaging , 2013, IET Comput. Vis..

[12]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[13]  Jean-Francois Mangin,et al.  Segmented MR images for brain attenuation correction in PET , 1994, Medical Imaging.

[14]  Stuart Crozier,et al.  Tissue Classification for PET/MRI Attenuation Correction Using Conditional Random Field and Image Fusion , 2013 .

[15]  R A Kirsch,et al.  Computer determination of the constituent structure of biological images. , 1971, Computers and biomedical research, an international journal.

[16]  Qing Ji,et al.  A knowledge-guided active model method of skull segmentation on T1-weighted MR images , 2007, SPIE Medical Imaging.

[17]  B. Schölkopf,et al.  Towards quantitative PET/MRI: a review of MR-based attenuation correction techniques , 2009, European Journal of Nuclear Medicine and Molecular Imaging.

[18]  R. Günther,et al.  Automatic, three-segment, MR-based attenuation correction for whole-body PET/MR data , 2010, European Journal of Nuclear Medicine and Molecular Imaging.

[19]  Gudrun Wagenknecht,et al.  MRI for attenuation correction in PET: methods and challenges , 2012, Magnetic Resonance Materials in Physics, Biology and Medicine.

[20]  Nassir Navab,et al.  Tissue Classification as a Potential Approach for Attenuation Correction in Whole-Body PET/MRI: Evaluation with PET/CT Data , 2009, Journal of Nuclear Medicine.

[21]  S. Vandenberghe,et al.  MRI-Based Attenuation Correction for PET/MRI Using Ultrashort Echo Time Sequences , 2010, Journal of Nuclear Medicine.

[22]  Stuart Crozier,et al.  New Spatiotemporal Features for Improved Discrimination of Benign and Malignant Lesions in Dynamic Contrast-Enhanced-Magnetic Resonance Imaging of the Breast , 2011, Journal of computer assisted tomography.

[23]  A Boudraa,et al.  Fuzzy clustering-based segmented attenuation correction in whole-body PET imaging. , 2002, Physics in medicine and biology.

[24]  Belma Dogdas,et al.  Segmentation of skull and scalp in 3‐D human MRI using mathematical morphology , 2005, Human brain mapping.

[25]  John W. Clark,et al.  Investigating the use of nonattenuation corrected PET images for the attenuation correction of PET data. , 2013, Medical physics.

[26]  Habib Zaidi,et al.  Advances in Attenuation Correction Techniques in PET. , 2007, PET clinics.

[27]  V. Schulz,et al.  Challenges and current methods for attenuation correction in PET/MR , 2013, Magnetic Resonance Materials in Physics, Biology and Medicine.

[28]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[29]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[30]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  Ron Kikinis,et al.  Markov random field segmentation of brain MR images , 1997, IEEE Transactions on Medical Imaging.

[32]  Baowei Fei,et al.  Research and applications: Multiscale segmentation of the skull in MR images for MRI-based attenuation correction of combined MR/PET , 2013, J. Am. Medical Informatics Assoc..

[33]  B. Schölkopf,et al.  MR-Based PET attenuation correction for PET/MR imaging. , 2013, Seminars in nuclear medicine.

[34]  Hans Herzog,et al.  MRI Based Attenuation Correction for Brain PET Images , 2007 .