Unsupervised Domain Adaptation With Optimal Transport in Multi-Site Segmentation of Multiple Sclerosis Lesions From MRI Data.

Automatic segmentation of Multiple Sclerosis (MS) lesions from Magnetic Resonance Imaging (MRI) images is essential for clinical assessment and treatment planning of MS. Recent years have seen an increasing use of Convolutional Neural Networks (CNNs) for this task. Although these methods provide accurate segmentation, their applicability in clinical settings remains limited due to a reproducibility issue across different image domains. MS images can have highly variable characteristics across patients, MRI scanners and imaging protocols; retraining a supervised model with data from each new domain is not a feasible solution because it requires manual annotation from expert radiologists. In this work, we explore an unsupervised solution to the problem of domain shift. We present a framework, Seg-JDOT, which adapts a deep model so that samples from a source domain and samples from a target domain sharing similar representations will be similarly segmented. We evaluated the framework on a multi-site dataset, MICCAI 2016, and showed that the adaptation toward a target site can bring remarkable improvements in a model performance over standard training.

One-year changes in brain microstructure differentiate preclinical Huntington's disease stages.

OBJECTIVE: To determine whether brain imaging markers of tissue microstructure can detect the effect of disease progression across the preclinical stages of Huntington's disease. METHODS: Longitudinal microstructural changes in diffusion imaging metrics (mean diffusivity and fractional anisotropy) were investigated in participants with presymptomatic Huntington's disease (N = 35) stratified into three preclinical subgroups according to their estimated time until onset of symptoms, compared with age- and gender-matched healthy controls (N = 19) over a 1y period. RESULTS: Significant differences were found over the four groups in change of mean diffusivity in the posterior basal ganglia and the splenium of the corpus callosum. This overall effect was driven by significant differences between the group far-from-onset (FAR) of symptoms and the groups midway- (MID) and near-the-onset (NEAR) of symptoms. In particular, an initial decrease of mean diffusivity in the FAR group was followed by a subsequent increase in groups closer to onset of symptoms. The seemingly counter-intuitive decrease of mean diffusivity in the group furthest from onset of symptoms might be an early indicator of neuroinflammatory process preceding the neurodegenerative phase. In contrast, the only clinical measure that was able to capture a difference in 1y changes between the preclinical stages was the UHDRS confidence in motor score. CONCLUSIONS: With sensitivity to longitudinal changes in brain microstructure within and between preclinical stages, and potential differential response to distinct pathophysiological mechanisms, diffusion imaging is a promising state marker for monitoring treatment response and identifying the optimal therapeutic window of opportunity in preclinical Huntington's disease.

Image processing and Quality Control for the first 10,000 brain imaging datasets from UK Biobank.

UK Biobank is a large-scale prospective epidemiological study with all data accessible to researchers worldwide. It is currently in the process of bringing back 100,000 of the original participants for brain, heart and body MRI, carotid ultrasound and low-dose bone/fat x-ray. The brain imaging component covers 6 modalities (T1, T2 FLAIR, susceptibility weighted MRI, Resting fMRI, Task fMRI and Diffusion MRI). Raw and processed data from the first 10,000 imaged subjects has recently been released for general research access. To help convert this data into useful summary information we have developed an automated processing and QC (Quality Control) pipeline that is available for use by other researchers. In this paper we describe the pipeline in detail, following a brief overview of UK Biobank brain imaging and the acquisition protocol. We also describe several quantitative investigations carried out as part of the development of both the imaging protocol and the processing pipeline.