Search

Segmentation of brain structures on magnetic resonance imaging (MRI) is a highly relevant neuroimaging topic, as it is a prerequisite for different analyses such as volumetry or shape analysis. Automated segmentation facilitates the study of brain structures in larger cohorts when compared with manual segmentation, which is time-consuming. However, the development of most automated methods relies on large and manually annotated datasets, which limits the generalizability of these methods. Recently, new techniques using synthetic images have emerged, reducing the need for manual annotation. Here we provide a dataset composed of label maps built from publicly available ultra-high resolution ex vivo MRI from 10 whole hemispheres, which can be used to develop segmentation methods using synthetic data. The label maps are obtained with a combination of manual labels for the hypothalamic regions and automated segmentations for the rest of the brain, and mirrored to simulate entire brains. We also provide the pre-processed ex vivo scans, as this dataset can support future projects to include other structures after these are manually segmented., (© 2024. The Author(s).)

Advances in artificial intelligence have cultivated a strong interest in developing and validating the clinical utilities of computer-aided diagnostic models. Machine learning for diagnostic neuroimaging has often been applied to detect psychological and neurological disorders, typically on small-scale datasets or data collected in a research setting. With the collection and collation of an ever-growing number of public datasets that researchers can freely access, much work has been done in adapting machine learning models to classify these neuroimages by diseases such as Alzheimer's, ADHD, autism, bipolar disorder, and so on. These studies often come with the promise of being implemented clinically, but despite intense interest in this topic in the laboratory, limited progress has been made in clinical implementation. In this review, we analyze challenges specific to the clinical implementation of diagnostic AI models for neuroimaging data, looking at the differences between laboratory and clinical settings, the inherent limitations of diagnostic AI, and the different incentives and skill sets between research institutions, technology companies, and hospitals. These complexities need to be recognized in the translation of diagnostic AI for neuroimaging from the laboratory to the clinic., (© 2023. The Author(s).)

Volumetric registration of brain MRI is routinely used in human neuroimaging, e.g., to align different MRI modalities, to measure change in longitudinal analysis, to map an individual to a template, or in registration-based segmentation. Classical registration techniques based on numerical optimization have been very successful in this domain, and are implemented in widespread software suites like ANTs, Elastix, NiftyReg, or DARTEL. Over the last 7-8 years, learning-based techniques have emerged, which have a number of advantages like high computational efficiency, potential for higher accuracy, easy integration of supervision, and the ability to be part of a meta-architectures. However, their adoption in neuroimaging pipelines has so far been almost inexistent. Reasons include: lack of robustness to changes in MRI modality and resolution; lack of robust affine registration modules; lack of (guaranteed) symmetry; and, at a more practical level, the requirement of deep learning expertise that may be lacking at neuroimaging research sites. Here, we present EasyReg, an open-source, learning-based registration tool that can be easily used from the command line without any deep learning expertise or specific hardware. EasyReg combines the features of classical registration tools, the capabilities of modern deep learning methods, and the robustness to changes in MRI modality and resolution provided by our recent work in domain randomization. As a result, EasyReg is: fast; symmetric; diffeomorphic (and thus invertible); agnostic to MRI modality and resolution; compatible with affine and nonlinear registration; and does not require any preprocessing or parameter tuning. We present results on challenging registration tasks, showing that EasyReg is as accurate as classical methods when registering 1 mm isotropic scans within MRI modality, but much more accurate across modalities and resolutions. EasyReg is publicly available as part of FreeSurfer; see https://surfer.nmr.mgh.harvard.edu/fswiki/EasyReg ., (© 2023. The Author(s).)

Depression is a common non-motor feature of Parkinson's disease (PD) which confers significant morbidity and is challenging to treat. The thalamus is a key component in the basal ganglia-thalamocortical network critical to the pathogenesis of PD and depression but the precise thalamic subnuclei involved in PD depression have not been identified. We performed structural and diffusion-weighted imaging (DWI) on 76 participants with PD to evaluate the relationship between PD depression and grey and white matter thalamic subnuclear changes. We used a thalamic segmentation method to divide the thalamus into its 50 constituent subnuclei (25 each hemisphere). Fixel-based analysis was used to calculate mean fibre cross-section (FC) for white matter tracts connected to each subnucleus. We assessed volume and FC at baseline and 14-20 months follow-up. A generalised linear mixed model was used to evaluate the relationship between depression, subnuclei volume and mean FC for each thalamic subnucleus. We found that depression scores in PD were associated with lower right pulvinar anterior (PuA) subnucleus volume. Antidepressant use was associated with higher right PuA volume suggesting a possible protective effect of treatment. After follow-up, depression scores were associated with reduced white matter tract macrostructure across almost all tracts connected to thalamic subnuclei. In conclusion, our work implicates the right PuA as a relevant neural structure in PD depression and future work should evaluate its potential as a therapeutic target for PD depression., (© 2022. The Author(s).)

Ex vivo imaging enables analysis of the human brain at a level of detail that is not possible in vivo with MRI. In particular, histology can be used to study brain tissue at the microscopic level, using a wide array of different stains that highlight different microanatomical features. Complementing MRI with histology has important applications in ex vivo atlas building and in modeling the link between microstructure and macroscopic MR signal. However, histology requires sectioning tissue, hence distorting its 3D structure, particularly in larger human samples. Here, we present an open-source computational pipeline to produce 3D consistent histology reconstructions of the human brain. The pipeline relies on a volumetric MRI scan that serves as undistorted reference, and on an intermediate imaging modality (blockface photography) that bridges the gap between MRI and histology. We present results on 3D histology reconstruction of whole human hemispheres from two donors.

Most individuals identified as ultra-high-risk (UHR) for psychosis do not develop frank psychosis. They continue to exhibit subthreshold symptoms, or go on to fully remit. Prior work has shown that the volume of CA1, a subfield of the hippocampus, is selectively reduced in the early stages of schizophrenia. Here we aimed to determine whether patterns of volume change of CA1 are different in UHR individuals who do or do not achieve symptomatic remission. Structural MRI scans were acquired at baseline and at 1-2 follow-up time points (at 12-month intervals) from 147 UHR and healthy control subjects. An automated method (based on an ex vivo atlas of ultra-high-resolution hippocampal tissue) was used to delineate the hippocampal subfields. Over time, a greater decline in bilateral CA1 subfield volumes was found in the subgroup of UHR subjects whose subthreshold symptoms persisted (n=40) and also those who developed clinical psychosis (n=12), compared with UHR subjects who remitted (n=41) and healthy controls (n=54). No baseline differences in volumes of the overall hippocampus or its subfields were found among the groups. Moreover, the rate of volume decline of CA1, but not of other hippocampal subfields, in the non-remitters was associated with increasing symptom severity over time. Thus, these findings indicate that there is deterioration of CA1 volume in persistently symptomatic UHR individuals in proportion to symptomatic progression.