Logo: to the web site of Uppsala University

The UK Biobank is a large-scale study collecting whole-body MR imaging and non-imaging health data. Robust and accurate inter-subject image registration of these whole-body MR images would enable their body-wide spatial standardization, and region-/voxel-wise correlation analysis of non-imaging data with image-derived parameters (e.g., tissue volume or fat content).

We propose a sex-stratified inter-subject whole-body MR image registration approach that uses subcutaneous adipose tissue- and muscle-masks from the state-of-the-art VIBESegmentator method to augment intensity-based graph-cut registration. The proposed method (that we refer to as mask-supported) was evaluated on a subset of 4000 subjects by comparing it to an intensity-only method as well as two previously published registration methods, uniGradICON and MIRTK. The evaluation consisted of a comparison of Jacobian Determinant (JD) folding frequency, Dice scores, and voxel-wise label error frequency calculated from the 71 VIBESegmentator masks. The 40 masks from MRSegmentator and 50 masks from TotalSegmentator were also used for independent Dice score evaluations. Additionally, voxel-wise correlation between age and each of fat content and tissue volume was studied to exemplify the usefulness for medical research.

The proposed method showed 7percentage points (pp) / 11pp lower frequency of JD folding for males / females when compared to the intensity-based method. The mask-supported method exhibited a mean Dice score of 0.773 / 0.744 across the cohort when evaluated on all VIBESegmentator masks, excluding the two used in the registration, for males / females, respectively. In comparison to the intensity-only registration, the mean values were 6 pp higher for both sexes, and the label error frequency was decreased in most tissue regions. These differences were 9pp / 8pp against uniGradICON and 12pp / 13pp against MIRTK. The mask-supported method achieved a mean Dice score of 0.736 / 0.676 when evaluated with MRSegmentator and 0.683/ 0.617 when evaluated with TotalSegmentator, showing an increase that ranged between 0.7pp and 12pp from the other three methods. Using the proposed method, the age-correlation maps were less noisy and showed higher anatomical alignment.

In conclusion, the image registration method using two tissue masks improves whole-body registration of UK Biobank images.