Probabilistic atlas priors have been commonly used to derive adaptive and robust brain MRI segmentation algorithms. Widely-used neuroimage analysis pipelines rely heavily on these techniques, which are often computationally expensive. In contrast, there has been a recent surge of approaches that leverage deep learning to implement segmentation tools that are computationally efficient at test time. However, most of these strategies rely on learning from manually annotated images. These supervised deep learning methods are therefore sensitive to the intensity profiles in the training dataset. To develop a deep learning-based segmentation model for a new image dataset (e.g., of different contrast), one usually needs to create a new labeled training dataset, which can be prohibitively expensive, or rely on suboptimal adaptation or augmentation approaches. In this paper, we propose an alternative strategy that combines a conventional probabilistic atlas-based segmentation with deep learning, enabling one to train a segmentation model for new MRI scans without the need for any manually segmented images. Our experiments include thousands of brain MRI scans and demonstrate that the proposed method achieves good accuracy for a brain MRI segmentation task for different MRI contrasts, requiring only approximately 15 seconds at test time on a GPU.

We present a deep learning tractography segmentation method that allows fast and consistent white matter fiber tract identification across healthy and disease populations and across multiple diffusion MRI (dMRI) acquisitions. We create a large-scale training tractography dataset of 1 million labeled fiber samples (54 anatomical tracts are included). To discriminate between fibers from different tracts, we propose a novel 2D multi-channel feature descriptor (FiberMap) that encodes spatial coordinates of points along each fiber. We learn a CNN tract classification model based on FiberMap and obtain a high tract classification accuracy of 90.99%. The method is evaluated on a test dataset of 374 dMRI scans from three independently acquired populations across health conditions (healthy control, neuropsychiatric disorders, and brain tumor patients). We perform comparisons with two state-of-the-art white matter tract segmentation methods. Experimental results show that our method obtains a highly consistent segmentation result, where over 99% of the fiber tracts are successfully detected across all subjects under study, most importantly, including patients with space occupying brain tumors. The proposed method leverages deep learning techniques and provides a much faster and more efficient tool for large data analysis than methods using traditional machine learning techniques.

The performance and diagnostic utility of magnetic resonance imaging (MRI) in pregnancy is fundamentally constrained by fetal motion. Motion of the fetus, which is unpredictable and rapid on the scale of conventional imaging times, limits the set of viable acquisition techniques to single-shot imaging with severe compromises in signal-to-noise ratio and diagnostic contrast, and frequently results in unacceptable image quality. Surprisingly little is known about the characteristics of fetal motion during MRI and here we propose and demonstrate methods that exploit a growing repository of MRI observations of the gravid abdomen that are acquired at low spatial resolution but relatively high temporal resolution and over long durations (10-30 minutes). We estimate fetal pose per frame in MRI volumes of the pregnant abdomen via deep learning algorithms that detect key fetal landmarks. Evaluation of the proposed method shows that our framework achieves quantitatively an average error of 4.47 mm and 96.4% accuracy (with error less than 10 mm). Fetal pose estimation in MRI time series yields novel means of quantifying fetal movements in health and disease, and enables the learning of kinematic models that may enhance prospective mitigation of fetal motion artifacts during MRI acquisition.

We propose and demonstrate a joint model of anatomical shapes, image features and clinical indicators for statistical shape modeling and medical image analysis. The key idea is to employ a copula model to separate the joint dependency structure from the marginal distributions of variables of interest. This separation provides flexibility on the assumptions made during the modeling process. The proposed method can handle binary, discrete, ordinal and continuous variables. We demonstrate a simple and efficient way to include binary, discrete and ordinal variables into the modeling. We build Bayesian conditional models based on observed partial clinical indicators, features or shape based on Gaussian processes capturing the dependency structure. We apply the proposed method on a stroke dataset to jointly model the shape of the lateral ventricles, the spatial distribution of the white matter hyperintensity associated with periventricular white matter disease, and clinical indicators. The proposed method yields interpretable joint models for data exploration and patient-specific statistical shape models for medical image analysis.

We present a volumetric mesh-based algorithm for flattening the placenta to a canonical template to enable effective visualization of local anatomy and function. Monitoring placental function promises to support pregnancy assessment and to improve care outcomes. We aim to alleviate visualization and interpretation challenges presented by the shape of the placenta when it is attached to the curved uterine wall. To do so, we flatten the volumetric mesh that captures placental shape to resemble the well-studied shape. We formulate our method as a map from the shape to a flattened template that minimizes the symmetric Dirichlet energy to control distortion throughout the volume. Local injectivity is enforced via constrained line search during gradient descent. We evaluate the proposed method on 28 placenta shapes extracted from MRI images in a clinical study of placental function. We achieve sub-voxel accuracy in mapping the boundary of the placenta to the template while successfully controlling distortion throughout the volume. We illustrate how the resulting mapping of the placenta enhances visualization of placental anatomy and function. Our implementation is freely available at https://github.com/mabulnaga/placenta-flattening.

The Alzheimer’s Disease Prediction Of Longitudinal Evolution (TADPOLE) Challenge compares the performance of algorithms at predicting the future evolution of individuals at risk of Alzheimer’s disease. TADPOLE Challenge participants train their models and algorithms on historical data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) study. Participants are then required to make forecasts of three key outcomes for ADNI-3 rollover participants: clinical diagnosis, Alzheimer’s Disease Assessment Scale Cognitive Subdomain (ADAS-Cog 13), and total volume of the ventricles - which are then compared with future measurements. Strong points of the challenge are that the test data did not exist at the time of forecasting (it was acquired afterwards), and that it focuses on the challenging problem of cohort selection for clinical trials by identifying fast progressors. The submission phase of TADPOLE was open until 15 November 2017; since then data has been acquired until April 2019 from 219 subjects with 223 clinical visits and 150 Magnetic Resonance Imaging (MRI) scans, which was used for the evaluation of the participants’ predictions. Thirty-three teams participated with a total of 92 submissions. No single submission was best at predicting all three outcomes. For diagnosis prediction, the best forecast (team Frog), which was based on gradient boosting, obtained a multiclass area under the receiver-operating curve (MAUC) of 0.931, while for ventricle prediction the best forecast (team ), which was based on disease progression modelling and spline regression, obtained mean absolute error of 0.41% of total intracranial volume (ICV). For ADAS-Cog 13, no forecast was considerably better than the benchmark mixed effects model ( ), provided to participants before the submission deadline. Further analysis can help understand which input features and algorithms are most suitable for Alzheimer’s disease prediction and for aiding patient stratification in clinical trials. The submission system remains open via the website: https://tadpole.grand-challenge.org/.

We introduce Disease Knowledge Transfer (DKT), a novel technique for transferring biomarker information between related neurodegenerative diseases. DKT infers robust multimodal biomarker trajectories in rare neurodegenerative diseases even when only limited, unimodal data is available, by transferring information from larger multimodal datasets from common neurodegenerative diseases. DKT is a joint-disease generative model of biomarker progressions, which exploits biomarker relationships that are shared across diseases. Our proposed method allows, for the first time, the estimation of plausible biomarker trajectories in Posterior Cortical Atrophy (PCA), a rare neurodegenerative disease where only unimodal MRI data is available. For this we train DKT on a combined dataset containing subjects with two distinct diseases and sizes of data available: 1) a larger, multimodal typical AD (tAD) dataset from the TADPOLE Challenge, and 2) a smaller unimodal Posterior Cortical Atrophy (PCA) dataset from the Dementia Research Centre (DRC), for which only a limited number of Magnetic Resonance Imaging (MRI) scans are available. Although validation is challenging due to lack of data in PCA, we validate DKT on synthetic data and two patient datasets (TADPOLE and PCA cohorts), showing it can estimate the ground truth parameters in the simulation and predict unseen biomarkers on the two patient datasets. While we demonstrated DKT on Alzheimer’s variants, we note DKT is generalisable to other forms of related neurodegenerative diseases. Source code for DKT is available online: https://github.com/mrazvan22/dkt.

Chronic traumatic encephalopathy (CTE) is a neurodegenerative disease associated with exposure to repetitive head impacts. CTE has been linked to disruptions in cognition, mood, and behavior. Unfortunately, the diagnosis of CTE can only be made post-mortem. Neuropathological evidence suggests limbic structures may provide an opportunity to characterize CTE in the living. Using 3 T magnetic resonance imaging, we compared select limbic brain regional volumes - the amygdala, hippocampus, and cingulate gyrus - between symptomatic former National Football League (NFL) players (n = 86) and controls (n = 22). Moreover, within the group of former NFL players, we examined the relationship between those limbic structures and neurobehavioral functioning (n = 75). The former NFL group comprised eighty-six men (mean age = 55.2 ± 8.0 years) with at least 12 years of organized football experience, at least 2 years of active participation in the NFL, and self-reported declines in cognition, mood, and behavior within the last 6 months. The control group consisted of men (mean age = 57.0 ± 6.6 years) with no history of contact-sport involvement or traumatic brain injury. All control participants provided neurobehavioral data. Compared to controls, former NFL players exhibited reduced volumes of the amygdala, hippocampus, and cingulate gyrus. Within the NFL group, reduced bilateral cingulate gyrus volume was associated with worse attention and psychomotor speed (r = 0.4 (right), r = 0.42 (left); both p < 0.001), while decreased right hippocampal volume was associated with worse visual memory (r = 0.25, p = 0.027). Reduced volumes of limbic system structures in former NFL players are associated with neurocognitive features of CTE. Volume reductions in the amygdala, hippocampus, and cingulate gyrus may be potential biomarkers of neurodegeneration in those at risk for CTE.

Alterations in parietal and temporal white matter microstructure derived from diffusion tensor imaging occur in preclinical and clinical Alzheimer’s disease. Amyloid beta (Aβ) deposition and such white matter alterations are two pathological hallmarks of Alzheimer’s disease. However, the relationship between these pathologies is not yet understood, partly since conventional diffusion MRI methods cannot distinguish between cellular and extracellular processes. Thus, we studied Aβ-associated longitudinal diffusion MRI changes in Aβ-positive (N = 21) and Aβ-negative (N = 51) cognitively normal elderly obtained from the Alzheimer’s Disease Neuroimaging Initiative dataset using linear mixed models. Aβ-positivity was based on Alzheimer’s Disease Neuroimaging Initiative amyloid-PET recommendations using a standardized uptake value ratio cut-off of 1.11. We used free-water imaging to distinguish cellular and extracellular changes. We found that Aβ-positive subjects had increased baseline right uncinate fasciculus free-water fraction (FW), associated with worse baseline Alzheimer’s disease assessment scale scores. Furthermore, Aβ-positive subjects showed faster decrease in fractional anisotropy (FW-corrected) in the right uncinate fasciculus and faster age-dependent right inferior longitudinal fasciculus FW increases over time. Right inferior longitudinal fasciculus FW increases were associated with greater memory decline. Importantly, these results remained significant after controlling for gray and white matter volume and hippocampal volume. This is the first study to illustrate the influence of Aβ burden on early longitudinal (in addition to baseline) white matter changes in cognitively normal elderly individuals at-risk of Alzheimer’s disease, thus underscoring the importance of longitudinal studies in assessing microstructural alterations in individuals at risk of Alzheimer’s disease prior to symptoms onset.

BACKGROUND: Pulmonary insufficiency is a consequence of transannular patch repair in Tetralogy of Fallot (ToF) leading to late morbidity and mortality. Transcatheter native outflow tract pulmonary valve replacement has become a reality. However, predicting a secure, atraumatic implantation of a catheter-based device remains a significant challenge due to the complex and dynamic nature of the right ventricular outflow tract (RVOT). We sought to quantify the differences in compression and volume for actual implants, and those predicted by pre-implant modeling. METHODS: We used custom software to interactively place virtual transcatheter pulmonary valves (TPVs) into RVOT models created from pre-implant and post Harmony valve implant CT scans of 5 ovine surgical models of TOF to quantify and visualize device volume and compression. RESULTS: Virtual device placement visually mimicked actual device placement and allowed for quantification of device volume and radius. On average, simulated proximal and distal device volumes and compression did not vary statistically throughout the cardiac cycle (P = 0.11) but assessment was limited by small sample size. In comparison to actual implants, there was no significant pairwise difference in the proximal third of the device (P > 0.80), but the simulated distal device volume was significantly underestimated relative to actual device implant volume (P = 0.06). CONCLUSIONS: This study demonstrates that pre-implant modeling which assumes a rigid vessel wall may not accurately predict the degree of distal RVOT expansion following actual device placement. We suggest the potential for virtual modeling of TPVR to be a useful adjunct to procedural planning, but further development is needed.