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/.
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.
Cerebral microbleeds (CMBs), a common manifestation of mild traumatic brain injury (mTBI), have been sporadically implicated in the neurocognitive deficits of mTBI victims but their clinical significance has not been established adequately. Here we investigate the longitudinal effects of post-mTBI CMBs upon the fractional anisotropy (FA) of white matter (WM) in 21 older mTBI patients across the first ~6 months post-injury. CMBs were segmented automatically from susceptibility-weighted imaging (SWI) by leveraging the intensity gradient properties of SWI to identify CMB-related hypointensities using gradient-based edge detection. A detailed diffusion magnetic resonance imaging (dMRI) atlas of WM was used to segment and cluster tractography streamlines whose prototypes were then identified. The correlation coefficient was calculated between (A) FA values at vertices along streamline prototypes and (B) topological (along-streamline) distances between these vertices and the nearest CMB. Across subjects, the CMB identification approach achieved a sensitivity of 97.1% ± 4.7% and a precision of 72.4% ± 11.0% across subjects. The correlation coefficient was found to be negative and, additionally, statistically significant for 12.3% ± 3.5% of WM clusters (p <; 0.05, corrected), whose FA was found to decrease, on average, by 11.8% ± 5.3% across the first 6 months post-injury. These results suggest that CMBs can be associated with deleterious effects upon peri-lesional WM and highlight the vulnerability of older mTBI patients to neurovascular injury.
OBJECTIVE: Deep brain stimulation (DBS) in zona incerta (Zi) is used for symptom alleviation in essential tremor (ET). Zi is positioned along the dentato-rubro-thalamic tract (DRT). Electric field simulations with the finite element method (FEM) can be used for estimation of a volume where the stimulation affects the tissue by applying a fixed isolevel (V). This work aims to develop a workflow for combined patient-specific electric field simulation and white matter tracing of the DRT, and to investigate the influence on the V from different brain tissue models, lead design and stimulation modes. The novelty of this work lies in the combination of all these components. METHOD: Patients with ET were implanted in Zi (lead 3389, n = 3, voltage mode; directional lead 6172, n = 1, current mode). Probabilistic reconstruction from diffusion MRI (dMRI) of the DRT (n = 8) was computed with FSL Toolbox. Brain tissue models were created for each patient (two homogenous, one heterogenous isotropic, one heterogenous anisotropic) and the respective V (n = 48) calculated from the Comsol Multiphysics FEM simulations. The DRT and V were visualized with 3DSlicer and superimposed on the preoperative T2 MRI, and the common volumes calculated. Dice Coefficient (DC) and level of anisotropy were used to evaluate and compare the brain models. RESULT: Combined patient-specific tractography and electric field simulation was designed and evaluated, and all patients showed benefit from DBS. All V overlapped the reconstructed DRT. Current stimulation showed prominent difference between the tissue models, where the homogenous grey matter deviated most (67 < DC < 69). Result from heterogenous isotropic and anisotropic models were similar (DC > 0.95), however the anisotropic model consistently generated larger volumes related to a greater extension of the electric field along the DBS lead. Independent of tissue model, the steering effect of the directional lead was evident and consistent. CONCLUSION: A workflow for patient-specific electric field simulations in combination with reconstruction of DRT was successfully implemented. Accurate tissue classification is essential for electric field simulations, especially when using the current control stimulation. With an accurate targeting and tractography reconstruction, directional leads have the potential to tailor the electric field into the desired region.
We address the problem of interpolating randomly non-uniformly spatiotemporally scattered uncertain motion measurements, which arises in the context of soft tissue motion estimation. Soft tissue motion estimation is of great interest in the field of image-guided soft-tissue intervention and surgery navigation, because it enables the registration of pre-interventional/pre-operative navigation information on deformable soft-tissue organs. To formally define the measurements as spatiotemporally scattered motion signal samples, we propose a novel motion field representation. To perform the interpolation of the motion measurements in an uncertainty-aware optimal unbiased fashion, we devise a novel Gaussian process (GP) regression model with a non-constant-mean prior and an anisotropic covariance function and show through an extensive evaluation that it outperforms the state-of-the-art GP models that have been deployed previously for similar tasks. The employment of GP regression enables the quantification of uncertainty in the interpolation result, which would allow the amount of uncertainty present in the registered navigation information governing the decisions of the surgeon or intervention specialist to be conveyed.
Schizophrenia has been characterized as a neurodevelopmental disorder, with structural brain abnormalities reported at all stages. However, at present, it remains unclear whether gray and white matter abnormalities represent related or independent pathologies in schizophrenia. In this study, we present findings from an integrative analysis exploring the morphological relationship between gray and white matter in 45 schizophrenia participants and 49 healthy controls. We utilized mutual information (MI), a measure of how much information two variables share, to assess the morphological dependence between gray and white matter in three segments of the corpus callsoum, and the gray matter regions these segments connect: (1) the genu and the left and right rostral middle frontal gyrus (rMFG), (2) the isthmus and the left and right superior temporal gyrus (STG), (3) the splenium and the left and right lateral occipital gyrus (LOG). We report significantly reduced MI between white matter tract dispersion of the right hemispheric callosal connections to the STG and both cortical thickness and area in the right STG in schizophrenia patients, despite a lack of group differences in cortical thickness, surface area, or dispersion. We believe that this reduction in morphological dependence between gray and white matter may reflect a possible decoupling of the developmental processes that shape morphological features of white and gray matter early in life. The present study also demonstrates the importance of studying the relationship between gray and white matter measures, as opposed to restricting analyses to gray and white matter measures independently.
RATIONALE AND OBJECTIVES: Analysis of dynamic contrast-enhanced (DCE) magnetic resonance imaging is notable for the variability of calculated parameters. The purpose of this study was to evaluate the level of measurement variability and error/variability due to modeling in DCE magnetic resonance imaging parameters. MATERIALS AND METHODS: Two prostate DCE scans were performed on 11 treatment-naïve patients with suspected or confirmed prostate peripheral zone cancer within an interval of less than two weeks. Tumor-suspicious and normal-appearing regions of interest (ROI) in the prostate peripheral zone were segmented. Different Tofts-Kety based models and different arterial input functions, with and without bolus arrival time (BAT) correction, were used to extract pharmacokinetic parameters. The percent repeatability coefficient (%RC) of fitted model parameters K, v, and k was calculated. Paired t-tests comparing parameters in tumor-suspicious ROIs and in normal-appearing tissue evaluated each parameter's sensitivity to pathology. RESULTS: Although goodness-of-fit criteria favored the four-parameter extended Tofts-Kety model with the BAT correction included, the simplest two-parameter Tofts-Kety model overall yielded the best repeatability scores. The best %RC in the tumor-suspicious ROI was 63% for k, 28% for v and 83% for K . The best p values for discrimination between tissues were p <10 for k and K, and p = 0.11 for v. Addition of the BAT correction to the models did not improve repeatability. CONCLUSION: The parameter k, using an arterial input functions directly measured from blood signals, was more repeatable than K. Both K and k values were highly discriminatory between healthy and diseased tissues in all cases. The parameter v had high repeatability but could not distinguish the two tissue types.
This paper presents an efficient approach to quantifying image registration uncertainty based on a low-dimensional representation of geometric deformations. In contrast to previous methods, we develop a Bayesian diffeomorphic registration framework in a bandlimited space, rather than a high-dimensional image space. We show that a dense posterior distribution on deformation fields can be fully characterized by much fewer parameters, which dramatically reduces the computational complexity of model inferences. To further avoid heavy computation loads introduced by random sampling algorithms, we approximate a marginal posterior by using Laplace's method at the optimal solution of log-posterior distribution. Experimental results on both 2D synthetic data and real 3D brain magnetic resonance imaging (MRI) scans demonstrate that our method is significantly faster than the state-of-the-art diffeomorphic registration uncertainty quantification algorithms, while producing comparable results.
Although brain functionality is often remarkably robust to lesions and other insults, it may be fragile when these take place in specific locations. Previous attempts to quantify robustness and fragility sought to understand how the functional connectivity of brain networks is affected by structural changes, using either model-based predictions or empirical studies of the effects of lesions. We advance a geometric viewpoint relying on a notion of network curvature, the so-called Ollivier-Ricci curvature. This approach has been proposed to assess financial market robustness and to differentiate biological networks of cancer cells from healthy ones. Here, we apply curvature-based measures to brain structural networks to identify robust and fragile brain regions in healthy subjects. We show that curvature can also be used to track changes in brain connectivity related to age and autism spectrum disorder (ASD), and we obtain results that are in agreement with previous MRI studies.
The Human Placenta Project has focused attention on the need for noninvasive magnetic resonance imaging (MRI)-based techniques to diagnose and monitor placental function throughout pregnancy. The hope is that the management of placenta-related pathologies would be improved if physicians had more direct, real-time measures of placental health to guide clinical decision making. As oxygen alters signal intensity on MRI and oxygen transport is a key function of the placenta, many of the MRI methods under development are focused on quantifying oxygen transport or oxygen content of the placenta. For example, measurements from blood oxygen level-dependent imaging of the placenta during maternal hyperoxia correspond to outcomes in twin pregnancies, suggesting that some aspects of placental oxygen transport can be monitored by MRI. Additional methods are being developed to accurately quantify baseline placental oxygenation by MRI relaxometry. However, direct validation of placental MRI methods is challenging and therefore animal studies and ex vivo studies of human placentas are needed. Here we provide an overview of the current state of the art of oxygen transport and quantification with MRI. We suggest that as these techniques are being developed, increased focus be placed on ensuring they are robust and reliable across individuals and standardized to enable predictive diagnostic models to be generated from the data. The field is still several years away from establishing the clinical benefit of monitoring placental function in real time with MRI, but the promise of individual personalized diagnosis and monitoring of placental disease in real time continues to motivate this effort.
Estimating the uncertainty in (probabilistic) image registration enables, e.g., surgeons to assess the operative risk based on the trustworthiness of the registered image data. If surgeons receive inaccurately calculated registration uncertainty and misplace unwarranted confidence in the alignment solutions, severe consequences may result. For probabilistic image registration (PIR), the predominant way to quantify the registration uncertainty is using summary statistics of the distribution of transformation parameters. The majority of existing research focuses on trying out different summary statistics as well as means to exploit them. Distinctively, in this paper, we study two rarely examined topics: (1) whether those summary statistics of the transformation distribution most informatively represent the registration uncertainty; (2) Does utilizing the registration uncertainty always be beneficial. We show that there are two types of uncertainties: the transformation uncertainty, Ut, and label uncertainty Ul. The conventional way of using Ut to quantify Ul is inappropriate and can be misleading. By a real data experiment, we also share a potentially critical finding that making use of the registration uncertainty may not always be an improvement.
External-beam radiotherapy followed by high dose rate (HDR) brachytherapy is the standard-of-care for treating gynecologic cancers. The enhanced soft-tissue contrast provided by magnetic resonance imaging (MRI) makes it a valuable imaging modality for diagnosing and treating these cancers. However, in contrast to computed tomography (CT) imaging, the appearance of the brachytherapy catheters, through which radiation sources are inserted to reach the cancerous tissue later on, is often variable across images. This paper reports, for the first time, a new deep-learning-based method for fully automatic segmentation of multiple closely spaced brachytherapy catheters in intraoperative MRI. Represented in the data are 50 gynecologic cancer patients treated by MRI-guided HDR brachytherapy. For each patient, a single intraoperative MRI was used. 826 catheters in the images were manually segmented by an expert radiation physicist who is also a trained radiation oncologist. The number of catheters in a patient ranged between 10 and 35. A deep 3D convolutional neural network (CNN) model was developed and trained. In order to make the learning process more robust, the network was trained 5 times, each time using a different combination of shown patients. Finally, each test case was processed by the five networks and the final segmentation was generated by voting on the obtained five candidate segmentations. 4-fold validation was executed and all the patients were segmented. An average distance error of 2.0 ± 3.4 mm was achieved. False positive and false negative catheters were 6.7% and 1.5% respectively. Average Dice score was equal to 0.60 ± 0.17. The algorithm is available for use in the open source software platform 3D Slicer allowing for wide scale testing and research discussion. In conclusion, to the best of our knowledge, fully automatic segmentation of multiple closely spaced catheters from intraoperative MR images was achieved for the first time in gynecological brachytherapy.
Computational biomechanics of the brain for neurosurgery is an emerging area of research recently gaining in importance and practical applications. This review paper presents the contributions of the Intelligent Systems for Medicine Laboratory and its collaborators to this field, discussing the modeling approaches adopted and the methods developed for obtaining the numerical solutions. We adopt a physics-based modeling approach and describe the brain deformation in mechanical terms (such as displacements, strains, and stresses), which can be computed using a biomechanical model, by solving a continuum mechanics problem. We present our modeling approaches related to geometry creation, boundary conditions, loading, and material properties. From the point of view of solution methods, we advocate the use of fully nonlinear modeling approaches, capable of capturing very large deformations and nonlinear material behavior. We discuss finite element and meshless domain discretization, the use of the total Lagrangian formulation of continuum mechanics, and explicit time integration for solving both time-accurate and steady-state problems. We present the methods developed for handling contacts and for warping 3D medical images using the results of our simulations. We present two examples to showcase these methods: brain shift estimation for image registration and brain deformation computation for neuronavigation in epilepsy treatment.
Mastering detailed anatomy of the human deep brain in clinical neurosciences is challenging. Although numerous pioneering works have gathered a large dataset of structural and topographic information, it is still difficult to transfer this knowledge into practice, even with advanced magnetic resonance imaging techniques. Thus, classical histological atlases continue to be used to identify structures for stereotactic targeting in functional neurosurgery. Physicians mainly use these atlases as a template co-registered with the patient's brain. However, it is possible to directly identify stereotactic targets on MRI scans, enabling personalized targeting. In order to help clinicians directly identify deep brain structures relevant to present and future medical applications, we built a volumetric MRI atlas of the deep brain (MDBA) on a large scale (infra millimetric). Twelve hypothalamic, 39 subthalamic, 36 telencephalic, and 32 thalamic structures were identified, contoured, and labeled. Nineteen coronal, 18 axial, and 15 sagittal MRI plates were created. Although primarily designed for direct labeling, the anatomic space was also subdivided in twelfths of AC-PC distance, leading to proportional scaling in the coronal, axial, and sagittal planes. This extensive work is now available to clinicians and neuroscientists, offering another representation of the human deep brain ([https://hal.archives-ouvertes.fr/] [hal-02116633]). The atlas may also be used by computer scientists who are interested in deciphering the topography of this complex region.
Intraoperative tissue deformation, known as brain shift, decreases the benefit of using preoperative images to guide neurosurgery. Non-rigid registration of preoperative magnetic resonance (MR) to intraoperative ultrasound (US) has been proposed as a means to compensate for brain shift. We focus on the initial registration from MR to predurotomy US. We present a method that builds on previous work to address the need for accuracy and generality of MR-iUS registration algorithms in multi-site clinical data. To improve accuracy of registration, we use high-dimensional texture attributes instead of image intensities and propose to replace the standard difference-based attribute matching with correlation-based attribute matching. We also present a strategy that deals explicitly with the large field-of-view mismatch between MR and iUS images. We optimize key parameters across independent MR-iUS brain tumor datasets acquired at three different institutions, with a total of 43 tumor patients and 758 corresponding landmarks to validate the registration algorithm. Despite differences in imaging protocols, patient demographics and landmark distributions, our algorithm was able to reduce landmark errors prior to registration in three data sets (5.37 ± 4.27, 4.18 ± 1.97 and 6.18 ± 3.38 mm, respectively) to a consistently low level (2.28 ± 0.71, 2.08 ± 0.37 and 2.24 ± 0.78 mm, respectively). Our algorithm is compared to 15 other algorithms that have been previously tested on MR-iUS registration and it is competitive with the state-of-the-art on multiple datasets. We show that our algorithm has one of the lowest errors in all datasets (accuracy), and this is achieved while sticking to a fixed set of parameters for multi-site data (generality). In contrast, other algorithms/tools of similar performance need per-dataset parameter tuning (high accuracy but lower generality), and those that stick to fixed parameters have larger errors or inconsistent performance (generality but not the top accuracy). We further characterized landmark errors according to brain regions and tumor types, a topic so far missing in the literature. We found that landmark errors were higher in high-grade than low-grade glioma patients, and higher in tumor regions than in other brain regions.
PURPOSE: In image-guided surgery for glioma removal, neurosurgeons usually plan the resection on images acquired before surgery and use them for guidance during the subsequent intervention. However, after the surgical procedure has begun, the preplanning images become unreliable due to the brain shift phenomenon, caused by modifications of anatomical structures and imprecisions in the neuronavigation system. To obtain an updated view of the resection cavity, a solution is to collect intraoperative data, which can be additionally acquired at different stages of the procedure in order to provide a better understanding of the resection. A spatial mapping between structures identified in subsequent acquisitions would be beneficial. We propose here a fully automated segmentation-based registration method to register ultrasound (US) volumes acquired at multiple stages of neurosurgery. METHODS: We chose to segment sulci and falx cerebri in US volumes, which remain visible during resection. To automatically segment these elements, first we trained a convolutional neural network on manually annotated structures in volumes acquired before the opening of the dura mater and then we applied it to segment corresponding structures in different surgical phases. Finally, the obtained masks are used to register US volumes acquired at multiple resection stages. RESULTS: Our method reduces the mean target registration error (mTRE) between volumes acquired before the opening of the dura mater and during resection from 3.49 mm (± 1.55 mm) to 1.36 mm (± 0.61 mm). Moreover, the mTRE between volumes acquired before opening the dura mater and at the end of the resection is reduced from 3.54 mm (± 1.75 mm) to 2.05 mm (± 1.12 mm). CONCLUSION: The segmented structures demonstrated to be good candidates to register US volumes acquired at different neurosurgical phases. Therefore, our solution can compensate brain shift in neurosurgical procedures involving intraoperative US data.
Recently, several biophysical models and signal representations have been proposed for microstructure imaging based on tensor-valued, or multidimensional, diffusion MRI. The acquisition of the necessary data requires non-conventional pulse sequences, and data is therefore not available to the wider diffusion MRI community. To facilitate exploration and development of analysis techniques based on tensor-valued diffusion encoding, we share a comprehensive data set acquired in a healthy human brain. The data encompasses diffusion weighted images using linear, planar and spherical diffusion tensor encoding at multiple b-values and diffusion encoding directions. We also supply data acquired in several phantoms that may support validation. The data is hosted by GitHub: https://github.com/filip-szczepankiewicz/Szczepankiewicz_DIB_2019.
PURPOSE: To demonstrate the feasibility of multidimensional diffusion MRI to probe and quantify microscopic fractional anisotropy (µFA) in human kidneys in vivo. METHODS: Linear tensor encoded (LTE) and spherical tensor encoded (STE) renal diffusion MRI scans were performed in 10 healthy volunteers. Respiratory triggering and image registration were used to minimize motion artefacts during the acquisition. Kidney cortex-medulla were semi-automatically segmented based on fractional anisotropy (FA) values. A model-free analysis of LTE and STE signal dependence on b-value in the renal cortex and medulla was performed. Subsequently, µFA was estimated using a single-shell approach. Finally, a comparison of conventional FA and µFA is shown. RESULTS: The hallmark effect of µFA (divergence of LTE and STE signal with increasing b-value) was observed in all subjects. A statistically significant difference between LTE and STE signal was found in the cortex and medulla, starting from b = 750 s/mm and b = 500 s/mm , respectively. This difference was maximal at the highest b-value sampled (b = 1000 s/mm ) which suggests that relatively high b-values are required for µFA mapping in the kidney compared to conventional FA. Cortical and medullary µFA were, respectively, 0.53 ± 0.09 and 0.65 ± 0.05, both respectively higher than conventional FA (0.19 ± 0.02 and 0.40 ± 0.02). CONCLUSION: The feasibility of combining LTE and STE diffusion MRI to probe and quantify µFA in human kidneys is demonstrated for the first time. By doing so, we show that novel microstructure information-not accessible by conventional diffusion encoding-can be probed by multidimensional diffusion MRI. We also identify relevant technical limitations that warrant further development of the technique for body MRI.
Age- and sex-related alterations in gene transcription have been demonstrated, however the underlying mechanisms are unresolved. Neuroepigenetic pathways regulate gene transcription in the brain. Here, we measure in vivo expression of the epigenetic enzymes, histone deacetylases (HDACs), across healthy human aging and between sexes using [C]Martinostat positron emission tomography (PET) neuroimaging (n = 41). Relative HDAC expression increases with age in cerebral white matter, and correlates with age-associated disruptions in white matter microstructure. A post mortem study confirmed that HDAC1 and HDAC2 paralogs are elevated in white matter tissue from elderly donors. There are also sex-specific in vivo HDAC expression differences in brain regions associated with emotion and memory, including the amygdala and hippocampus. Hippocampus and white matter HDAC expression negatively correlates with emotion regulation skills (n = 23). Age and sex are associated with HDAC expression in vivo, which could drive age- and sex-related transcriptional changes and impact human behavior.