Domain-agnostic segmentation of thalamic nuclei from joint structural and diffusion MRI.

The human thalamus is a highly connected subcortical grey-matter structure within the brain. It comprises dozens of nuclei with different function and connectivity, which are affected differently by disease. For this reason, there is growing interest in studying the thalamic nuclei in vivo with MRI. Tools are available to segment the thalamus from 1 mm T1 scans, but the contrast of the lateral and internal boundaries is too faint to produce reliable segmentations. Some tools have attempted to incorporate information from diffusion MRI in the segmentation to refine these boundaries, but do not generalise well across diffusion MRI acquisitions. Here we present the first CNN that can segment thalamic nuclei from T1 and diffusion data of any resolution without retraining or fine tuning. Our method builds on a public histological atlas of the thalamic nuclei and silver standard segmentations on high-quality diffusion data obtained with a recent Bayesian adaptive segmentation tool. We combine these with an approximate degradation model for fast domain randomisation during training. Our CNN produces a segmentation at 0.7 mm isotropic resolution, irrespective of the resolution of the input. Moreover, it uses a parsimonious model of the diffusion signal at each voxel (fractional anisotropy and principal eigenvector) that is compatible with virtually any set of directions and b-values, including huge amounts of legacy data. We show results of our proposed method on three heterogeneous datasets acquired on dozens of different scanners. An implementation of the method is publicly available at https://freesurfer.net/fswiki/ThalamicNucleiDTI.

Validation of markerless strain-field optical tracking approach for soft tissue mechanical assessment.

Strain measurement during tissue deformation is crucial to elucidate relationships between mechanical loading and functional changes in biological tissues. When combined with specified loading conditions, assessment of strain fields can be used to craft models that accurately represent the mechanical behavior of soft tissue. Inhomogeneities in strain fields may be indicative of normal or pathological inhomogeneities in mechanical properties. In this study, we present the validation of a modified Demons registration algorithm for non-contact, marker-less strain measurement of tissue undergoing uniaxial loading. We validate the algorithm on a synthetic dataset composed of artificial deformation fields applied to a speckle image, as well as images of aortic sections of varying perceptual quality. Initial results indicate that Demons outperforms recent Optical Flow and Digital Image Correlation methods in terms of accuracy and robustness to low image quality, with similar runtimes. Demons achieves at least 8% lower maximal deviation from ground truth on 50% biaxial and shear strain applied to aortic images. To illustrate utility, we quantified strain fields of multiple human aortic specimens undergoing uniaxial tensile testing, noting the formation of strain concentrations in areas of rupture. The modified Demons algorithm captured a large range of strains (up to 50%) and provided spatially resolved strain fields that could be useful in the assessment of soft tissue pathologies.