Qualitative and Quantitative Evaluation of Blob-Based Time-of-Flight PET Image Reconstruction in Hybrid Brain PET/MR Imaging

Abstract

PurposeMany neurological diseases affect small structures in the brain and, as such, reliable visual evaluation and accurate quantification are required. Recent technological developments made the clinical use of hybrid positron emission tomography/magnetic resonance (PET/MR) systems possible, providing both functional and anatomical information in a single imaging session. Nevertheless, there is a trade-off between spatial resolution and image quality (contrast and noise), which is dictated mainly by the chosen acquisition and reconstruction protocols. Image reconstruction algorithms using spherical symmetric basis functions (blobs) for image representation have a number of additional parameters that impact both the qualitative and quantitative image characteristics. Hence, a detailed investigation of the blob-based reconstruction characteristics using different parameters is needed to achieve optimal reconstruction results.ProceduresThis work evaluated the impact of a range of blob parameters on image quality and quantitative accuracy of brain PET images acquired on the Ingenuity Time-of-Flight (TOF) PET/MR system. Two different phantoms were used to simulate brain imaging applications. Image contrast and noise characteristics were assessed using an image quality phantom. Quantitative performance in a clinical setting was investigated using the Hoffman 3D brain phantom at various count levels. Furthermore, the visual quality of four clinical studies was scored blindly by two experienced physicians to qualitatively evaluate the influence of different reconstruction protocols, hereby providing indications on parameters producing the best image quality.ResultsQuantitative evaluation using the image quality phantom showed that larger basis function radii result in lower contrast recovery (∼2 %) and lower variance levels (∼15 %). The brain phantom and clinical studies confirmed these observations since lower contrast was seen between anatomical structures. High and low count statistics gave comparable values. The qualitative evaluation of the clinical studies, based on the assessment performed by the physicians, showed a preference towards lower image variance levels with a slightly lower contrast, favoring higher radii and four iterations.ConclusionThis study systematically evaluated a number of basis function parameters and their quantitative and qualitative effect within PET image reconstruction in the context of brain imaging. A range of blob parameters can minimize error and provided optimal image quality, where the anatomical structures could be recognized but the exact delineation of these structures is simplified in scans with lower image variance levels and thus, higher radii should be preferred. With the optimization of blob parameters, the reconstructed images were found to be qualitatively improved (optimum parameters {d = 2.0375, alpha = 10.4101, radius = 3.9451}) as assessed by the physicians compared to the current clinical protocol. However, this qualitative improvement is task specific, depending on...

Optimization of reconstruction parameters in [18F]FDG PET brain images aiming scan time reduction

“…Moreover, the contrast was comparable between the 5-min reconstruction with post-reconstruction smoothing filter FWHM of 4 mm (2.37) and the clinical reconstruction parameters (2.40). Leemans et al (2015) obtained values of contrast ranging from 2.7 to 3.5, which were directly proportional to the number of iterations when reconstructed using OSEM with 1 to 12 iterations (32 subsets and 45 min acquisition time) 26 . In a multicenter study (22 PET centres), Habert et al(2016) obtained values of contrast of 3.0 ± 0.3 (range: 2.34 to 3.77; 3 × 5 min dynamic image) for different equipment and routine iterative reconstruction methods 27 .…”

“…Leemans et al (2015) obtained values of contrast ranging from 2.7 to 3.5, which were directly proportional to the number of iterations when reconstructed using OSEM with 1 to 12 iterations (32 subsets and 45 min acquisition time) 26 . In a multicenter study (22 PET centres), Habert et al(2016) obtained values of contrast of 3.0 ± 0.3 (range: 2.34 to 3.77; 3 × 5 min dynamic image) for different equipment and routine iterative reconstruction methods 27 . The lower contrast obtained in this study was likely due to the shorter image acquisition and differences in equipment and vendor-specific reconstruction algorithms.…”

Multimodal phantoms for clinical PET/MRI

“…Optional inserts are also available to simulate defects. The Hoffman phantom has been used to assess the performance of PET inserts in clinical MRI scanners [ 65 – 67 ], evaluate motion correction methods [ 68 , 69 ], the demonstrate of PET image reconstruction methods [ 70 ] and MRI-based attenuation correction [ 71 ] methods. This is the only commercially available phantom identified within this review that is also advertised for MRI use, although the polycarbonate plates are not visible in MRI.…”

Blob parameter selection for image representation

“…(17) and (18) by replacing R 1 and R 2 with 1∕σ and ffiffi ffi 2 p ∕σ, respectively; the former value is the distance from the origin of the six nearest neighbors and the latter is the location of the 12 second-nearest neighbors, as can be seen from Fig. 1(a).…”

“…We also discuss that, by making use of an extra degree of freedom that has not been considered in the above-mentioned literature, we can select from the options that are efficacious for the representation of nonzero-constant-valued functions those parameters that blur edges the least. The existence of such an extra degree of freedom is mentioned in a very recent application-oriented article [17]; our paper provides a detailed and mathematically rigorous analysis of the underlying theory.…”