Preconditioned P-ULA for Joint Deconvolution-Segmentation of Ultrasound Images -- Extended Version
This work addresses a challenging problem in medical imaging for ultrasound analysis, but it is incremental as it builds on existing methods with improvements in speed.
The authors tackled the joint deconvolution and segmentation of ultrasound images by proposing an accelerated Markov chain Monte Carlo scheme, achieving high-quality results and up to six times faster performance compared to an existing method.
Joint deconvolution and segmentation of ultrasound images is a challenging problem in medical imaging. By adopting a hierarchical Bayesian model, we propose an accelerated Markov chain Monte Carlo scheme where the tissue reflectivity function is sampled thanks to a recently introduced proximal unadjusted Langevin algorithm. This new approach is combined with a forward-backward step and a preconditioning strategy to accelerate the convergence, and with a method based on the majorization-minimization principle to solve the inner nonconvex minimization problems. As demonstrated in numerical experiments conducted on both simulated and in vivo ultrasound images, the proposed method provides high-quality restoration and segmentation results and is up to six times faster than an existing Hamiltonian Monte Carlo method.