Prediction of Standard-Dose PET Image by Low-Dose PET and MRI Images

Positron emission tomography (PET) is a nuclear medical imaging technology that produces 3D images of tissue metabolic activity in human body. PET has been used in various clinical applications, such as diagnosis of tumors and diffuse brain disorders. High quality PET image plays an essential role in diagnosing diseases/disorders and assessing the response to therapy. In practice, in order to obtain the high quality PET images, standard-dose radionuclide (tracer) needs to be used and injected into the living body. As a result, it will inevitably increase the risk of radiation. In this paper, we propose a regression forest (RF) based framework for predicting standard-dose PET images using low-dose PET and corresponding magnetic resonance imaging (MRI) images instead of injecting the standard-dose radionuclide into the body. The proposed approach has been evaluated on a dataset consisting of 7 subjects using leave-one-out cross-validation. Moreover, we compare the prediction performance between sparse representation (SR) based method and our proposed method. Both qualitative and quantitative results illustrate the practicability of our proposed method.

[1]  Shu Liao,et al.  Prostate Segmentation by Sparse Representation Based Classification , 2012, MICCAI.

[2]  Bernd Fischer,et al.  Biomedical Image Registration, 4th International Workshop, WBIR 2010, Lübeck, Germany, July 11-13, 2010. Proceedings , 2010, Workshop on Biomedical Image Registration.

[3]  Timothy F. Cootes,et al.  Fully Automatic Segmentation of the Proximal Femur Using Random Forest Regression Voting , 2013, IEEE Transactions on Medical Imaging.

[4]  Thomas S. Huang,et al.  Image Super-Resolution Via Sparse Representation , 2010, IEEE Transactions on Image Processing.

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

[6]  Daoqiang Zhang,et al.  Multimodal classification of Alzheimer's disease and mild cognitive impairment , 2011, NeuroImage.

[7]  T. Turkington,et al.  Clinical applications of PET in oncology. , 2004, Radiology.

[8]  Michael Brady,et al.  Motion Correction and Attenuation Correction for Respiratory Gated PET Images , 2011, IEEE Transactions on Medical Imaging.

[9]  Luc Van Gool,et al.  Random Forests for Real Time 3D Face Analysis , 2012, International Journal of Computer Vision.

[10]  Hervé Delingette,et al.  Medical Image Computing and Computer-Assisted Intervention – MICCAI 2012 , 2012, Lecture Notes in Computer Science.

[11]  Jan Modersitzki,et al.  FLIRT: A Flexible Image Registration Toolbox , 2003, WBIR.

[12]  Stephen M. Smith,et al.  Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm , 2001, IEEE Transactions on Medical Imaging.