Deep Learning Models for PET Scatter Estimations

Projection data acquired from a positron emission tomography (PET) scanner consist of true, scattered and random events. Scattered events can cause severe artifacts and quantitation errors in reconstructed PET images unless corrected for properly. A scatter correction algorithm is required to predict scattered events from the measurement. Scatter correction requires estimation of both single scatter and multiple scatter profiles. Usually, single scatter profiles are calculated by modelbased simulation and multiple scatter profiles are estimated by a kernel-based convolution method. However, design of the convolution kernels for multiple scatter estimation is sophisticated and requires fine parameter tuning. In this work, we adopt deep learning techniques for scatter estimation. We propose two convolutional neural networks. The first network estimates multiple scatter profiles from single scatter profiles, replacing the kernel-based convolution method. The second network is designed to predict the total scatter profiles (including single and multiple scatters) directly from the input of emission and attenuation sinograms. Initial results from both networks show a promise with the potential for more accurate and faster scatter correction for PET.

[1]  Bin Yan,et al.  Image Prediction for Limited-angle Tomography via Deep Learning with Convolutional Neural Network , 2016, ArXiv.

[2]  S. Ross,et al.  Out-of-field scatter estimation in 3D whole body PET , 2009, 2009 IEEE Nuclear Science Symposium Conference Record (NSS/MIC).

[3]  Enhong Chen,et al.  Image Denoising and Inpainting with Deep Neural Networks , 2012, NIPS.

[4]  Leslie Ying,et al.  Accelerating magnetic resonance imaging via deep learning , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[5]  Hongming Shan,et al.  Enhancing Transferability of Features from Pretrained Deep Neural Networks for Lung Nodule Classification , 2017 .

[6]  Klaus Mueller,et al.  Low-Dose CT Streak Artifacts Removal using Deep Residual Neural Network , 2017 .

[7]  Kris Thielemans,et al.  A comparative study of multiple scatter estimations in 3D PET , 2010, IEEE Nuclear Science Symposuim & Medical Imaging Conference.

[8]  J. Ollinger.  Model-based scatter correction for fully 3D PET. , 1996, Physics in medicine and biology.

[9]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[10]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[11]  Yannan Jin,et al.  Reducing Metal Streak Artifacts in CT Images via Deep Learning : Pilot Results , 2017 .

[12]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[13]  C. Tsoumpas,et al.  Scatter simulation including double scatter , 2005, IEEE Nuclear Science Symposium Conference Record, 2005.

[14]  Lei Zhang,et al.  Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising , 2016, IEEE Transactions on Image Processing.

[15]  D. Newport,et al.  A Single Scatter Simulation Technique for Scatter Correction in 3D PET , 1996 .

[16]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..