Dynamic PET Image Reconstruction Incorporating Multiscale Superpixel Clusters

Abstract

Dynamic positron emission tomography (PET) image reconstruction is challenging due to the low-count statistics of individual frames. This study proposes a novel reconstruction framework aiming to enhance the quantitative accuracy of individual dynamic frames via the introduction of priors based on multiscale superpixel clusters. The clusters are derived from pre-reconstruction composite images using superpixel clustering followed by fuzzy c-means (FCM) clustering. A multiscale aggregation is exploited during the superpixel clustering to generate multiscale superpixel clusters. Then, maximum a posteriori (MAP) PET reconstruction with different-scale clusters is separately applied to individual frame and fused to generate the final result. Using realistic simulated dynamic brain PET data, the quantitative performance of the proposed method is investigated and compared with the maximum-likelihood expectationmaximization (MLEM), Bowsher method, and kernelized expectation-maximization (the kernel method). The proposed method achieves substantial improvements in both visual and quantitative accuracy (in terms of the signal-to-noise ratio and contrast versus noise performances). The method is also tested with a 60 min 18 F-FDG rat study performed with an Inveon small animal PET scanner. The proposed method is shown to outperform the other methods via improvements in visual and quantitative accuracy (in terms of noise versus the mean intensity of the region of interest). INDEX TERMS Image reconstruction, maximum a posteriori, positron emission tomography, superpixel clustering.

Matrix and tensor completion using tensor ring decomposition with sparse representation

“…Superpixels can be found in many applications of computer vision and machine learning tasks. As an efficient superpixel method, SLIC (Simple Linear Iterative Clustering) algorithm was introduced in [12] and due to its superior performance [14], [15] was extensively used in many applications such as image segmentation [7], [8], [9], [10], object detection [11], anomaly detection [16], [17] and image reconstruction [18], [19], [20]. To efficiently generate superpixels, the SLIC algorithm employs a k-means clustering approach.…”