The HD Integrated Staging System enables classification of people with HD into four disease stages based on quantitative landmark assessments. Here we characterized volume change over time in the caudate nucleus, putamen, lateral ventricles, and whole-brain across participants starting in each of the different HD-ISS Stages at baseline and compared to healthy controls.
For HD-ISS Stage 2 and Stage 3 participants, whole-brain volume shows significant association with clinical change for all four clinical variables examined here. For caudate and putamen volume, the association depended on the clinical variable. Our results provide further evidence on the use of volume change as a surrogate endpoint.
We have developed a fully automated framework that uses deep learning for caudate segmentation (IXIQ. Ai) and generalised BSI (gBSI) for longitudinal measurements. Here, we validate the new method by comparing its volumetric scores with those of the standard manual pipeline (Man+BSI). Man+BSI produced larger caudate volumes than IXIQ.