Random forest regression for magnetic resonance image synthesis

&NA; By choosing different pulse sequences and their parameters, magnetic resonance imaging (MRI) can generate a large variety of tissue contrasts. This very flexibility, however, can yield inconsistencies with MRI acquisitions across datasets or scanning sessions that can in turn cause inconsistent automated image analysis. Although image synthesis of MR images has been shown to be helpful in addressing this problem, an inability to synthesize both T2‐weighted brain images that include the skull and FLuid Attenuated Inversion Recovery (FLAIR) images has been reported. The method described herein, called REPLICA, addresses these limitations. REPLICA is a supervised random forest image synthesis approach that learns a nonlinear regression to predict intensities of alternate tissue contrasts given specific input tissue contrasts. Experimental results include direct image comparisons between synthetic and real images, results from image analysis tasks on both synthetic and real images, and comparison against other state‐of‐the‐art image synthesis methods. REPLICA is computationally fast, and is shown to be comparable to other methods on tasks they are able to perform. Additionally REPLICA has the capability to synthesize both T2‐weighted images of the full head and FLAIR images, and perform intensity standardization between different imaging datasets. HighlightsWe describe an MRI image synthesis algorithm capable of synthesizing full‐head T2w images and FLAIR images.Our algorithm, REPLICA, is a supervised method and learns the nonlinear intensity mappings for synthesis using innovative features and a multi‐resolution design.We show significant improvement in synthetic image quality over state‐of‐the‐art image synthesis algorithms.We also demonstrate that image analysis tasks like segmentation perform similarly for real and REPLICA‐generated synthetic images.REPLICA is computationally very fast and can be easily used as a preprocessing tool before further image analysis. Graphical abstract Figure. No caption available.

[1]  Snehashis Roy,et al.  Magnetic resonance image synthesis through patch regression , 2013, 2013 IEEE 10th International Symposium on Biomedical Imaging.

[2]  Aaron Carass,et al.  Simple paradigm for extra-cerebral tissue removal: Algorithm and analysis , 2011, NeuroImage.

[3]  Sébastien Ourselin,et al.  Template-Based Multimodal Joint Generative Model of Brain Data , 2015, IPMI.

[4]  Colin Studholme,et al.  A supervised patch-based image reconstruction technique: Application to brain MRI super-resolution , 2013, 2013 IEEE 10th International Symposium on Biomedical Imaging.

[5]  Ben Glocker,et al.  Is Synthesizing MRI Contrast Useful for Inter-modality Analysis? , 2013, MICCAI.

[6]  Peter A. Calabresi,et al.  A topology-preserving approach to the segmentation of brain images with multiple sclerosis lesions , 2010, NeuroImage.

[7]  Snehashis Roy,et al.  Magnetic Resonance Image Example-Based Contrast Synthesis , 2013, IEEE Transactions on Medical Imaging.

[8]  Alex Rovira,et al.  Segmentation of multiple sclerosis lesions in brain MRI: A review of automated approaches , 2012, Inf. Sci..

[9]  Ben Glocker,et al.  Modality Propagation: Coherent Synthesis of Subject-Specific Scans with Data-Driven Regularization , 2013, MICCAI.

[10]  Ninon Burgos,et al.  Attenuation Correction Synthesis for Hybrid PET-MR Scanners: Application to Brain Studies , 2014, IEEE Transactions on Medical Imaging.

[11]  M I Miller,et al.  Mathematical textbook of deformable neuroanatomies. , 1993, Proceedings of the National Academy of Sciences of the United States of America.

[12]  Jayaram K. Udupa,et al.  New variants of a method of MRI scale standardization , 2000, IEEE Transactions on Medical Imaging.

[13]  Snehashis Roy,et al.  Consistent segmentation using a Rician classifier , 2012, Medical Image Anal..

[14]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[15]  Anders M. Dale,et al.  Cortical Surface-Based Analysis I. Segmentation and Surface Reconstruction , 1999, NeuroImage.

[16]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[17]  A. Bovik,et al.  A universal image quality index , 2002, IEEE Signal Processing Letters.

[18]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[19]  Snehashis Roy,et al.  Atlas Based Intensity Transformation of Brain MR Images , 2013, MBIA.

[20]  Snehashis Roy,et al.  Synthesizing MR contrast and resolution through a patch matching technique , 2010, Medical Imaging.

[21]  Shaohua Kevin Zhou,et al.  Cross-Domain Synthesis of Medical Images Using Efficient Location-Sensitive Deep Network , 2015, MICCAI.

[22]  Snehashis Roy,et al.  MR contrast synthesis for lesion segmentation , 2010, 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[23]  Mehdi Moradi,et al.  Scandent Tree: A Random Forest Learning Method for Incomplete Multimodal Datasets , 2015, MICCAI.

[24]  Aaron Carass,et al.  Longitudinal changes in cortical thickness associated with normal aging , 2010, NeuroImage.

[25]  David Salesin,et al.  Image Analogies , 2001, SIGGRAPH.

[26]  Jennifer L. Cuzzocreo,et al.  Reconstruction of the human cerebral cortex robust to white matter lesions: Method and validation , 2014, Human brain mapping.

[27]  Marleen de Bruijne,et al.  Why Does Synthesized Data Improve Multi-sequence Classification? , 2015, MICCAI.

[28]  D. Altman,et al.  STATISTICAL METHODS FOR ASSESSING AGREEMENT BETWEEN TWO METHODS OF CLINICAL MEASUREMENT , 1986, The Lancet.

[29]  Sébastien Ourselin,et al.  Fast free-form deformation using graphics processing units , 2010, Comput. Methods Programs Biomed..

[30]  Ben Glocker,et al.  Encoding atlases by randomized classification forests for efficient multi-atlas label propagation , 2014, Medical Image Anal..

[31]  Snehashis Roy,et al.  A Compressed Sensing Approach for MR Tissue Contrast Synthesis , 2011, IPMI.

[32]  John H. Gilmore,et al.  Automatic Segmentation of Neonatal Brain MRI , 2004, MICCAI.

[33]  L G Nyúl,et al.  On standardizing the MR image intensity scale , 1999, Magnetic resonance in medicine.

[34]  François Rousseau,et al.  Brain Hallucination , 2008, ECCV.

[35]  André J. W. van der Kouwe,et al.  Example-Based Restoration of High-Resolution Magnetic Resonance Image Acquisitions , 2013, MICCAI.

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

[37]  D. Louis Collins,et al.  Unbiased average age-appropriate atlases for pediatric studies , 2011, NeuroImage.

[38]  Snehashis Roy,et al.  Pulse sequence based multi-acquisition MR intensity normalization , 2013, Medical Imaging.

[39]  Intermodality Priors.  A Non-local Approach for Image Super-Resolution using , 2010 .

[40]  Amod Jog,et al.  Random forest FLAIR reconstruction from T1, T2, and PD-weighted MRI , 2014, 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI).

[41]  Sébastien Ourselin,et al.  Reconstructing a 3D structure from serial histological sections , 2001, Image Vis. Comput..

[42]  Jerry L Prince,et al.  PET Attenuation Correction Using Synthetic CT from Ultrashort Echo-Time MR Imaging , 2014, The Journal of Nuclear Medicine.

[43]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[44]  M. Rahmati,et al.  Super-resolution MRI images using Compressive Sensing , 2012, 20th Iranian Conference on Electrical Engineering (ICEE2012).

[45]  Jerry L Prince,et al.  Current methods in medical image segmentation. , 2000, Annual review of biomedical engineering.

[46]  Amod Jog,et al.  Tree-Encoded Conditional Random Fields for Image Synthesis , 2015, IPMI.

[47]  Snehashis Roy,et al.  MR image synthesis by contrast learning on neighborhood ensembles , 2015, Medical Image Anal..

[48]  Amod Jog,et al.  Improving magnetic resonance resolution with supervised learning , 2014, 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI).

[49]  S. Stuckey,et al.  Hyperintensity in the subarachnoid space on FLAIR MRI. , 2007, AJR. American journal of roentgenology.

[50]  Xiao Han,et al.  CRUISE: Cortical reconstruction using implicit surface evolution , 2004, NeuroImage.

[51]  Daniel Rueckert,et al.  Multi-atlas segmentation with augmented features for cardiac MR images , 2015, Medical Image Anal..

[52]  Min Chen,et al.  Multi-parametric neuroimaging reproducibility: A 3-T resource study , 2011, NeuroImage.

[53]  Taku Komura,et al.  Topology matching for fully automatic similarity estimation of 3D shapes , 2001, SIGGRAPH.

[54]  Olivier Clatz,et al.  Spatial decision forests for MS lesion segmentation in multi-channel magnetic resonance images , 2011, NeuroImage.

[55]  C. Almli,et al.  Unbiased nonlinear average age-appropriate brain templates from birth to adulthood , 2009, NeuroImage.

[56]  Dong Hye Ye,et al.  Context-sensitive Classication Forests for Segmentation of Brain Tumor Tissues , 2012 .