16 Jul 21. Featured Paper
Improved identification of abdominal aortic aneurysm using the Kernelized Expectation Maximization algorithm.
Link to paper on Philosophical Transactions of the Royal Society A: Mathematical, Physical & Engineering Sciences
Authors
Daniel Deidda, Mercy I. Akerele, Robert G. Aykroyd, Marc R. Dweck, Kelley Ferreira, Rachael O. Forsythe, Warda Heetun, David E. Newby, Maaz Syed & Charalampos Tsoumpas
Abstract
Abdominal aortic aneurysm (AAA) monitoring & risk of rupture is currently assumed to be correlated with the aneurysm diameter.
Aneurysm growth, however, has been demonstrated to be unpredictable.
Using PET to measure uptake of [18F]-NaF in calcified lesions of the abdominal aorta has been shown to be useful for identifying AAA & to predict its growth.
The PET low spatial resolution, however, can affect the accuracy of the diagnosis.
Advanced edge-preserving reconstruction algorithms can overcome this issue.
The kernel method has been demonstrated to provide noise suppression while retaining emission & edge information.
Nevertheless, these findings were obtained using simulations, phantoms & a limited amount of patient data.
In this study, the authors aim to investigate the usefulness of the anatomically guided kernelized expectation maximization (KEM) & the hybrid KEM (HKEM) methods & to judge the statistical significance of the related improvements.
Sixty-one datasets of patients with AAA & 11 from control patients were reconstructed with ordered subsets expectation maximization (OSEM), HKEM & KEM & the analysis was carried out using the target-to-blood-pool ratio, & a series of statistical tests.
The results show that all algorithms have similar diagnostic power, but HKEM & KEM can significantly recover uptake of lesions & improve the accuracy of the diagnosis by up to 22% compared to OSEM.
The same improvements are likely to be obtained in clinical applications based on the quantification of small lesions, like for example cancer.
Keywords
Social media tags & titles
Featured paper: Improved identification of abdominal aortic aneurysm using the Kernelized Expectation Maximization algorithm.
@EdinUniCVS @MarcDweck