LAUSR

&NA; Image registration is typically formulated as an optimization process, which aims to find the optimal transformation parameters of a given transformation model by minimizing a cost function. Local minima may exist in the optimization landscape, which could hamper the optimization process. To eliminate local minima, smoothing the cost function would be desirable. In this paper, we investigate the use of a randomized smoothing (RS) technique for stochastic gradient descent (SGD) optimization, to effectively smooth the cost function. In this approach, Gaussian noise is added to the transformation parameters prior to computing the cost function gradient in each iteration of the SGD optimizer. The approach is suitable for both rigid and nonrigid registrations. Experiments on synthetic images, cell images, public CT lung data, and public MR brain data demonstrate the effectiveness of the novel RS technique in terms of registration accuracy and robustness. HighlightsTo suppress local minima, we smooth the cost function of image registration with a randomized smoothing (RS) technique.A convolution‐based smoothing technique in which the original cost function is convolved by a Gaussian distribution with an efficient randomized optimization procedure.The RS technique is applied to translation, rigid, affine and B‐spline transformation models.Experiments on 2D artificial images, 2D cell images, 3D lung CT, and 3D brain MRI scans confirm the benefits of the method. Graphical abstract Figure. No caption available.