Bias in iterative reconstruction of low-statistics PET data: benefits of a resolution model.
AffiliationSchool of Cancer and Enabling Sciences, Wolfson Molecular Imaging Centre, MAHSC, The University of Manchester, Manchester, UK.
MetadataShow full item record
AbstractIterative image reconstruction methods such as ordered-subset expectation maximization (OSEM) are widely used in PET. Reconstructions via OSEM are however reported to be biased for low-count data. We investigated this and considered the impact for dynamic PET. Patient listmode data were acquired in [(11)C]DASB and [(15)O]H(2)O scans on the HRRT brain PET scanner. These data were subsampled to create many independent, low-count replicates. The data were reconstructed and the images from low-count data were compared to the high-count originals (from the same reconstruction method). This comparison enabled low-statistics bias to be calculated for the given reconstruction, as a function of the noise-equivalent counts (NEC). Two iterative reconstruction methods were tested, one with and one without an image-based resolution model (RM). Significant bias was observed when reconstructing data of low statistical quality, for both subsampled human and simulated data. For human data, this bias was substantially reduced by including a RM. For [(11)C]DASB the low-statistics bias in the caudate head at 1.7 M NEC (approx. 30 s) was -5.5% and -13% with and without RM, respectively. We predicted biases in the binding potential of -4% and -10%. For quantification of cerebral blood flow for the whole-brain grey- or white-matter, using [(15)O]H(2)O and the PET autoradiographic method, a low-statistics bias of <2.5% and <4% was predicted for reconstruction with and without the RM. The use of a resolution model reduces low-statistics bias and can hence be beneficial for quantitative dynamic PET.
CitationBias in iterative reconstruction of low-statistics PET data: benefits of a resolution model. 2011, 56 (4):931-49 Phys Med Biol
JournalPhysics in Medicine and Biology
- Optimization of methods for quantification of rCBF using high-resolution [¹⁵O]H₂O PET images.
- Authors: Walker MD, Feldmann M, Matthews JC, Anton-Rodriguez JM, Wang S, Koepp MJ, Asselin MC
- Issue date: 2012 Apr 21
- Impact of image-space resolution modeling for studies with the high-resolution research tomograph.
- Authors: Sureau FC, Reader AJ, Comtat C, Leroy C, Ribeiro MJ, Buvat I, Trébossen R
- Issue date: 2008 Jun
- Studying the properties of the updating coefficients in the OSEM algorithm for iterative image reconstruction in PET.
- Authors: Gaitanis A, Kontaxakis G, Spyrou G, Panayiotakis G, Tzanakos G
- Issue date: 2010 Sep
- A method for accurate modelling of the crystal response function at a crystal sub-level applied to PET reconstruction.
- Authors: Stute S, Benoit D, Martineau A, Rehfeld NS, Buvat I
- Issue date: 2011 Feb 7
- Optimization of the injected activity in dynamic 3D PET: a generalized approach using patient-specific NECs as demonstrated by a series of 15O-H2O scans.
- Authors: Walker MD, Matthews JC, Asselin MC, Saleem A, Dickinson C, Charnley N, Julyan PJ, Price PM, Jones T
- Issue date: 2009 Sep