Long-range medical image registration through generalized mutual information (GMI): toward a fully automatic volumetric alignment
This work addresses the problem of limited registration range in medical image processing for clinicians and researchers, offering a more robust and fully automatic volumetric alignment solution.
The paper proposes a generalized parametric mutual information (GMI) as a cost function for affine medical image registration to overcome the limitations of traditional mutual information in handling large transformations. The GMI functions demonstrated significantly prolonged registration ranges, achieving success rates of 99.99% for translations within [-150mm, 150mm], 97.58% for rotations within [-180°, 180°], 99.99% for scales within [0.5, 2], and 99.99% for skew within [-1, 1] in simulated gradient descent, and 99.75% success in Monte Carlo simulations with 2,000 randomized translation trials.
Image registration is a key operation in medical image processing, allowing a plethora of applications. Mutual information (MI) is consolidated as a robust similarity metric often used for medical image registration. Although MI provides a robust medical image registration, it usually fails when the needed image transform is too big due to MI local maxima traps. In this paper, we propose and evaluate a generalized parametric MI as an affine registration cost function. We assessed the generalized MI (GMI) functions for separable affine transforms and exhaustively evaluated the GMI mathematical image seeking the maximum registration range through a gradient descent simulation. We also employed Monte Carlo simulation essays for testing translation registering of randomized T1 versus T2 images. GMI functions showed to have smooth isosurfaces driving the algorithm to the global maxima. Results show significantly prolonged registration ranges, avoiding the traps of local maxima. We evaluated a range of [-150mm,150mm] for translations, [-180°,180°] for rotations, [0.5,2] for scales, and [-1,1] for skew with a success rate of 99.99%, 97.58%, 99.99%, and 99.99% respectively for the transforms in the simulated gradient descent. We also obtained 99.75% success in Monte Carlo simulation from 2,000 randomized translations trials with 1,113 subjects T1 and T2 MRI images. The findings point towards the reliability of GMI for long-range registration with enhanced speed performance