Random forest FLAIR reconstruction from T1, T2, and PD-weighted MRI

Fluid Attenuated Inversion Recovery (FLAIR) is a commonly acquired pulse sequence for multiple sclerosis (MS) patients. MS white matter lesions appear hyperintense in FLAIR images and have excellent contrast with the surrounding tissue. Hence, FLAIR images are commonly used in automated lesion segmentation algorithms to easily and quickly delineate the lesions. This expedites the lesion load computation and correlation with disease progression. Unfortunately for numerous reasons the acquired FLAIR images can be of a poor quality and suffer from various artifacts. In the most extreme cases the data is absent, which poses a problem when consistently processing a large data set. We propose to fill in this gap by reconstructing a FLAIR image given the corresponding T1-weighted, T2-weighted, and PD-weighted images of the same subject using random forest regression. We show that the images we produce are similar to true high quality FLAIR images and also provide a good surrogate for tissue segmentation.

[1]  R. Rudick,et al.  Gray matter atrophy in multiple sclerosis: A longitudinal study , 2008, Annals of neurology.

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

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

[4]  C Becker,et al.  Quantitative assessment of MRI lesion load in multiple sclerosis. A comparison of conventional spin-echo with fast fluid-attenuated inversion recovery. , 1996, Brain : a journal of neurology.

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

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

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

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

[9]  Christian Barillot,et al.  Optimized supervised segmentation of MS lesions from multispectral MRIs , 2009 .

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

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

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

[13]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

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

[15]  Bobby R. Hunt,et al.  Super‐resolution of images: Algorithms, principles, performance , 1995, Int. J. Imaging Syst. Technol..

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

[17]  Christian Barillot,et al.  Adaptive weighted fusion of multiple MR sequences for brain lesion segmentation , 2010, 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[18]  Snehashis Roy,et al.  Intensity inhomogeneity correction of magnetic resonance images using patches , 2011, Medical Imaging.

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