Sex estimation from coxal bones using deep learning in a population balanced by sex and age.

In the field of forensic anthropology, researchers aim to identify anonymous human remains and determine the cause and circumstances of death from skeletonized human remains. Sex determination is a fundamental step of this procedure because it influences the estimation of other traits, such as age and stature. Pelvic bones are especially dimorphic, and are thus the most useful bones for sex identification. Sex estimation methods are usually based on morphologic traits, measurements, or landmarks on the bones. However, these methods are time-consuming and can be subject to inter- or intra-observer bias. Sex determination can be done using dry bones or CT scans. Recently, artificial neural networks (ANN) have attracted attention in forensic anthropology. Here we tested a fully automated and data-driven machine learning method for sex estimation using CT-scan reconstructions of coxal bones. We studied 580 CT scans of living individuals. Sex was predicted by two networks trained on an independent sample: a disentangled variational auto-encoder (DVAE) alone, and the same DVAE associated with another classifier (Crecon). The DVAE alone exhibited an accuracy of 97.9%, and the DVAE + Crecon showed an accuracy of 99.8%. Sensibility and precision were also high for both sexes. These results are better than those reported from previous studies. These data-driven algorithms are easy to implement, since the pre-processing step is also entirely automatic. Fully automated methods save time, as it only takes a few minutes to pre-process the images and predict sex, and does not require strong experience in forensic anthropology.

Which is the most appropriate strategy for conducting multivariate voxel-based group studies on diffusion tensors?

There is a real need in the neuroscience community for efficient tools to compare Diffusion Tensor Magnetic Resonance Imaging across cohorts of subjects. Most studies focus on the comparison of scalar images such as fractional anisotropy or mean diffusivity. Although different statistical frameworks have been proposed to compare the whole diffusion tensor information, they are still seldom used in neuroimaging studies. In this paper, we investigate on both simulated and real data whether there is a real added value of considering the whole tensor information for conducting voxel-based group studies. Then, we compare two statistical tests dedicated to tensor, namely the Cramér test and a tensor-based extension of the General Linear Model (GLM), the latter presenting the advantage to account for covariates. We also evaluate the impact of different metrics (Euclidean, Log-Euclidean and affine-invariant Riemannian metrics) for estimating the GLM parameters. Finally, we address the problem of interpreting the change detection maps obtained by tensor-based methods by proposing a way to characterize each of the detected clusters according to several scalar indices. Our study suggests that if there is no prior assumption about the nature of the expected changes, it is really preferable to use tensor-based rather than scalar-based statistical analysis. The Cramér test can advantageously be used when no confounding variable hampers the group comparison, otherwise the GLM should be considered. Finally, the different metrics show similar performance in the real scenario, with a significant computational overhead for the Riemannian framework.

The memory gene KIBRA is a bidirectional regulator of synaptic and structural plasticity in the adult brain.

Memory formation is associated with activity-dependent changes in synaptic plasticity. The mechanisms underlying these processes are complex and involve multiple components. Recent work has implicated the protein KIBRA in human memory, but its molecular functions in memory processes remain not fully understood. Here, we show that a selective overexpression of KIBRA in neurons increases hippocampal long-term potentiation (LTP) but prevents the induction of long-term depression (LTD), and impairs spatial long-term memory in adult mice. KIBRA overexpression increases the constitutive recycling of AMPA receptors containing GluA1 (GluA1-AMPARs), and favors their activity-dependent surface expression. It also results in dramatic dendritic rearrangements in pyramidal neurons both in vitro and in vivo. KIBRA knockdown in contrast, abolishes LTP, decreases GluA1-AMPARs recycling and reduces dendritic arborization. These results establish KIBRA as a novel bidirectional regulator of synaptic and structural plasticity in hippocampal neurons, and of long-term memory, highly relevant to cognitive processes and their pathologies.

A human antibody against pathologic IAPP aggregates protects beta cells in type 2 diabetes models.

In patients with type 2 diabetes, pancreatic beta cells progressively degenerate and gradually lose their ability to produce insulin and regulate blood glucose. Beta cell dysfunction and loss is associated with an accumulation of aggregated forms of islet amyloid polypeptide (IAPP) consisting of soluble prefibrillar IAPP oligomers as well as insoluble IAPP fibrils in pancreatic islets. Here, we describe a human monoclonal antibody selectively targeting IAPP oligomers and neutralizing IAPP aggregate toxicity by preventing membrane disruption and apoptosis in vitro. Antibody treatment in male rats and mice transgenic for human IAPP, and human islet-engrafted mouse models of type 2 diabetes triggers clearance of IAPP oligomers resulting in beta cell protection and improved glucose control. These results provide new evidence for the pathological role of IAPP oligomers and suggest that antibody-mediated removal of IAPP oligomers could be a pharmaceutical strategy to support beta cell function in type 2 diabetes.

Longitudinal change detection in diffusion MRI using multivariate statistical testing on tensors.

This paper presents a longitudinal change detection framework for detecting relevant modifications in diffusion MRI, with application to neuromyelitis optica (NMO) and multiple sclerosis (MS). The core problem is to identify image regions that are significantly different between two scans. The proposed method is based on multivariate statistical testing which was initially introduced for tensor population comparison. We use this method in the context of longitudinal change detection by considering several strategies to build sets of tensors characterizing the variability of each voxel. These strategies make use of the variability existing in the diffusion weighted images (thanks to a bootstrap procedure), or in the spatial neighborhood of the considered voxel, or a combination of both. Results on synthetic evolutions and on real data are presented. Interestingly, experiments on NMO patients highlight the ability of the proposed approach to detect changes in the normal-appearing white matter (according to conventional MRI) that are related with physical status outcome. Experiments on MS patients highlight the ability of the proposed approach to detect changes in evolving and non-evolving lesions (according to conventional MRI). These findings might open promising prospects for the follow-up of NMO and MS pathologies.

Spatially Constrained Online Dictionary Learning for Source Separation.

Whether in medical imaging, astronomy or remote sensing, the data are increasingly complex. In addition to the spatial dimension, the data may contain temporal or spectral information that characterises the different sources present in the image. The compromise between spatial resolution and temporal/spectral resolution is often at the expense of spatial resolution, resulting in a potentially large mixing of sources in the same pixel/voxel. Source separation methods must incorporate spatial information to estimate the contribution and signature of each source in the image. We consider the particular case where the position of the sources is approximately known thanks to external information that may come from another imaging modality or from a priori knowledge. We propose a spatially constrained dictionary learning source separation algorithm that uses e.g. high resolution segmentation map or regions of interest defined by an expert to regularise the source contribution estimation. The originality of the proposed model is the replacement of the sparsity constraint classically expressed in the form of an l1 penalty on the localisation of sources by an indicator function exploiting the external source localisation information. The model is easily adaptable to different applications by adding or modifying the constraints on the sources properties in the optimisation problem. The performance of this algorithm has been validated on synthetic and quasi-real data, before being applied to real data previously analysed by other methods of the literature in order to compare the results. To illustrate the potential of the approach, different applications have been considered, from scintigraphic data to astronomy or fMRI data.

Protein phosphatase 1 regulates the histone code for long-term memory.

Chromatin remodeling through histone posttranslational modifications (PTMs) and DNA methylation has recently been implicated in cognitive functions, but the mechanisms involved in such epigenetic regulation remain poorly understood. Here, we show that protein phosphatase 1 (PP1) is a critical regulator of chromatin remodeling in the mammalian brain that controls histone PTMs and gene transcription associated with long-term memory. Our data show that PP1 is present at the chromatin in brain cells and interacts with enzymes of the epigenetic machinery including HDAC1 (histone deacetylase 1) and histone demethylase JMJD2A (jumonji domain-containing protein 2A). The selective inhibition of the nuclear pool of PP1 in forebrain neurons in transgenic mice is shown to induce several histone PTMs that include not only phosphorylation but also acetylation and methylation. These PTMs are residue-specific and occur at the promoter of genes important for memory formation like CREB (cAMP response element-binding protein) and NF-kappaB (nuclear factor-kappaB). These histone PTMs further co-occur with selective binding of RNA polymerase II and altered gene transcription, and are associated with improved long-term memory for objects and space. Together, these findings reveal a novel mechanism for the epigenetic control of gene transcription and long-term memory in the adult brain that depends on PP1.

Liver tissue segmentation in multiphase CT scans using cascaded convolutional neural networks.

PURPOSE: We address the automatic segmentation of healthy and cancerous liver tissues (parenchyma, active and necrotic parts of hepatocellular carcinoma (HCC) tumor) on multiphase CT images using a deep learning approach. METHODS: We devise a cascaded convolutional neural network based on the U-Net architecture. Two strategies for dealing with multiphase information are compared: Single-phase images are concatenated in a multi-dimensional features map on the input layer, or output maps are computed independently for each phase before being merged to produce the final segmentation. Each network of the cascade is specialized in the segmentation of a specific tissue. The performances of these networks taken separately and of the cascaded architecture are assessed on both single-phase and on multiphase images. RESULTS: In terms of Dice coefficients, the proposed method is on par with a state-of-the-art method designed for automatic MR image segmentation and outperforms previously used technique for interactive CT image segmentation. We validate the hypothesis that several cascaded specialized networks have a higher prediction accuracy than a single network addressing all tasks simultaneously. Although the portal venous phase alone seems to provide sufficient contrast for discriminating tumors from healthy parenchyma, the multiphase information brings significant improvement for the segmentation of cancerous tissues (active versus necrotic part). CONCLUSION: The proposed cascaded multiphase architecture showed promising performances for the automatic segmentation of liver tissues, allowing to reliably estimate the necrosis rate, a valuable imaging biomarker of the clinical outcome.

Accurate inversion of 3-D transformation fields.

This correspondence addresses the inversion of 3-D transformation fields, which is a problem that typically arises in image warping problems. A topology preserving parametric B-spline-based representation of the deformation field is considered. Topology preservation ensures that the transformation is a one-to-one mapping and consequently that it is invertible. Inverting such transformation fields amounts to solving a system of nonlinear equations. To tackle this problem, we rely on interval analysis techniques. The proposed algorithm yields a solution whose accuracy is user-controlled. This method may be extended to any dense transformation field and also to deformations defined on a grid of points, by considering a projection in the space of topology preserving B-spline-based deformation fields. The performance of the algorithm is illustrated on transformation fields coming from intersubject brain registration.

Robust pose estimation and recognition using non-gaussian modeling of appearance subspaces.

We present an original appearance model that generalizes the usual Gaussian visual subspace model to non-Gaussian and nonparametric distributions. It can be useful for the modeling and recognition of images under difficult conditions such as large occlusions and cluttered backgrounds. Inference under the model is efficiently solved using the mean shift algorithm.

Scale-adaptive supervoxel-based random forests for liver tumor segmentation in dynamic contrast-enhanced CT scans.

PURPOSE: Toward an efficient clinical management of hepatocellular carcinoma (HCC), we propose a classification framework dedicated to tumor necrosis rate estimation from dynamic contrast-enhanced CT scans. Based on machine learning, it requires weak interaction efforts to segment healthy, active and necrotic liver tissues. METHODS: Our contributions are two-fold. First, we apply random forest (RF) on supervoxels using multi-phase supervoxel-based features that discriminate tissues based on their dynamic in response to contrast agent injection. Second, we extend this technique in a hierarchical multi-scale fashion to deal with multiple spatial extents and appearance heterogeneity. It translates in an adaptive data sampling scheme combining RF and hierarchical multi-scale tree resulting from recursive supervoxel decomposition. By concatenating multi-phase features across the hierarchical multi-scale tree to describe leaf supervoxels, we enable RF to automatically infer the most informative scales without defining any explicit rules on how to combine them. RESULTS: Assessment on clinical data confirms the benefits of multi-phase information embedded in a multi-scale supervoxel representation for HCC tumor segmentation. CONCLUSION: Dedicated but not limited only to HCC management, both contributions reach further steps toward more accurate multi-label tissue classification.

Affine-invariant geometric shape priors for region-based active contours.

We present a new way of constraining the evolution of a region-based active contour with respect to a reference shape. Minimizing a shape prior, defined as a distance between shape descriptors based on the Legendre moments of the characteristic function, leads to a geometric flow that can be used with benefits in a two-class segmentation application. The shape model includes intrinsic invariance with regard to pose and affine deformations.

Unsupervised learning and mapping of active brain functional MRI signals based on hidden semi-Markov event sequence models.

In this paper, a novel functional magnetic resonance imaging (fMRI) brain mapping method is presented within the statistical modeling framework of hidden semi-Markov event sequence models (HSMESMs). Neural activation detection is formulated at the voxel level in terms of time coupling between the sequence of hemodynamic response onsets (HROs) observed in the fMRI signal, and an HSMESM of the hidden sequence of task-induced neural activations. The sequence of HRO events is derived from a continuous wavelet transform (CWT) of the fMRI signal. The brain activation HSMESM is built from the timing information of the input stimulation protocol. The rich mathematical framework of HSMESMs makes these models an effective and versatile approach for fMRI data analysis. Solving for the HSMESM Evaluation and Learning problems enables the model to automatically detect neural activation embedded in a given set of fMRI signals, without requiring any template basis function or prior shape assumption for the fMRI response. Solving for the HSMESM Decoding problem allows to enrich brain mapping with activation lag mapping, activation mode visualizing, and hemodynamic response function analysis. Activation detection results obtained on synthetic and real epoch-related fMRI data demonstrate the superiority of the HSMESM mapping method with respect to a real application case of the statistical parametric mapping (SPM) approach. In addition, the HSMESM mapping method appears clearly insensitive to timing variations of the hemodynamic response, and exhibits low sensitivity to fluctuations of its shape.

Hidden Markov event sequence models: toward unsupervised functional MRI brain mapping.

RATIONALE AND OBJECTIVES: Most methods used in functional MRI (fMRI) brain mapping require restrictive assumptions about the shape and timing of the fMRI signal in activated voxels. Consequently, fMRI data may be partially and misleadingly characterized, leading to suboptimal or invalid inference. To limit these assumptions and to capture the broad range of possible activation patterns, a novel statistical fMRI brain mapping method is proposed. It relies on hidden semi-Markov event sequence models (HSMESMs), a special class of hidden Markov models (HMMs) dedicated to the modeling and analysis of event-based random processes. MATERIALS AND METHODS: Activation detection is formulated in terms of time coupling between (1) the observed sequence of hemodynamic response onset (HRO) events detected in the voxel's fMRI signal and (2) the "hidden" sequence of task-induced neural activation onset (NAO) events underlying the HROs. Both event sequences are modeled within a single HSMESM. The resulting brain activation model is trained to automatically detect neural activity embedded in the input fMRI data set under analysis. The data sets considered in this article are threefold: synthetic epoch-related, real epoch-related (auditory lexical processing task), and real event-related (oddball detection task) fMRI data sets. RESULTS: Synthetic data: Activation detection results demonstrate the superiority of the HSMESM mapping method with respect to a standard implementation of the statistical parametric mapping (SPM) approach. They are also very close, sometimes equivalent, to those obtained with an "ideal" implementation of SPM in which the activation patterns synthesized are reused for analysis. The HSMESM method appears clearly insensitive to timing variations of the hemodynamic response and exhibits low sensitivity to fluctuations of its shape (unsustained activation during task). Real epoch-related data: HSMESM activation detection results compete with those obtained with SPM, without requiring any prior definition of the expected activation patterns thanks to the unsupervised character of the HSMESM mapping approach. Along with activation maps, the method offers a wide range of additional fMRI analysis functionalities, including activation lag mapping, activation mode visualization, and hemodynamic response function analysis. Real event-related data: Activation detection results confirm and validate the overall strategy that consists in focusing the analysis on the transients, time-localized events that are the HROs. CONCLUSION: All the experiments performed on synthetic and real fMRI data demonstrate the relevance of HSMESMs in fMRI brain mapping. In particular, the statistical character of these models, along with their learning and generalizing abilities are of particular interest when dealing with strong variabilities of the active fMRI signal across time, space, experiments, and subjects.

3-D deformable image registration: a topology preservation scheme based on hierarchical deformation models and interval analysis optimization.

This paper deals with topology preservation in three-dimensional (3-D) deformable image registration. This work is a nontrivial extension of, which addresses the case of two-dimensional (2-D) topology preserving mappings. In both cases, the deformation map is modeled as a hierarchical displacement field, decomposed on a multiresolution B-spline basis. Topology preservation is enforced by controlling the Jacobian of the transformation. Finding the optimal displacement parameters amounts to solving a constrained optimization problem: The residual energy between the target image and the deformed source image is minimized under constraints on the Jacobian. Unlike the 2-D case, in which simple linear constraints are derived, the 3-D B-spline-based deformable mapping yields a difficult (until now, unsolved) optimization problem. In this paper, we tackle the problem by resorting to interval analysis optimization techniques. Care is taken to keep the computational burden as low as possible. Results on multipatient 3-D MRI registration illustrate the ability of the method to preserve topology on the continuous image domain.

A robust statistics-based global energy function for the alignment of serially acquired autoradiographic sections.

Autoradiographic analysis of the functional changes occurring in the rat brain are most often performed on coronal sections that allow a good insight into the events occurring at the structural level but lacks the 3D context which is necessary to fully understand the involvement of the brain structures in specific situations like focal seizures with or without generalization. Therefore a robust, fully-automated algorithm for the registration of serially acquired autoradiographic sections is presented. The method accounts for the main difficulties of autoradiographic alignment: corrupted data (cuts and tears), dissimilarities or discontinuities between slices, non parallel or missing slices. The approach relies on the minimization of a global energy function based on robust statistics. The energy function measures the similarity between a slice and its neighborhood in the 3D volume. No particular direction is privileged in the method, so that global offsets, biases in the estimation or error propagations are avoided. The method is evaluated qualitatively and quantitatively on real autoradiographic data. Rat brain autoradiographic volumes are reconstructed with registration errors less than 1 degree in rotation and less than 1 pixel in translation.

Heritable and inducible gene knockdown in astrocytes or neurons in vivo by a combined lentiviral and RNAi approach.

Gene knockout by homologous recombination is a popular method to study gene functions in the mouse in vivo. However, its lack of temporal control has limited the interpretation of knockout studies because the complete elimination of a gene product often alters developmental processes, and can induce severe malformations or lethality. Conditional gene knockdown has emerged as a compelling alternative to gene knockout, an approach well-established in vitro but that remains challenging in vivo, especially in the adult brain. Here, we report a method for conditional and cell-specific gene knockdown in the mouse brain in vivo that combines Cre-mediated RNA interference (RNAi) with classical and lentivirus-mediated transgenesis. The method is based on the inducible expression of a silencing short hairpin RNA (shRNA) introduced in mice by lentivirus-mediated transgenesis, and on its activation by excision of a floxed stop EGFP reporter with an inducible Cre recombinase expressed in astrocytes or in neurons. This dual system should be of broad utility for comparative studies of gene functions in these two cell types in vivo.

On the estimation and correction of bias in local atrophy estimations using example atrophy simulations.

Brain atrophy is considered an important marker of disease progression in many chronic neuro-degenerative diseases such as multiple sclerosis (MS). A great deal of attention is being paid toward developing tools that manipulate magnetic resonance (MR) images for obtaining an accurate estimate of atrophy. Nevertheless, artifacts in MR images, inaccuracies of intermediate steps and inadequacies of the mathematical model representing the physical brain volume change, make it rather difficult to obtain a precise and unbiased estimate. This work revolves around the nature and magnitude of bias in atrophy estimations as well as a potential way of correcting them. First, we demonstrate that for different atrophy estimation methods, bias estimates exhibit varying relations to the expected atrophy and these bias estimates are of the order of the expected atrophies for standard algorithms, stressing the need for bias correction procedures. Next, a framework for estimating uncertainty in longitudinal brain atrophy by means of constructing confidence intervals is developed. Errors arising from MRI artifacts and bias in estimations are learned from example atrophy simulations and anatomies. Results are discussed for three popular non-rigid registration approaches with the help of simulated localized brain atrophy in real MR images.

Longitudinal change detection: inference on the diffusion tensor along white matter pathways.

Diffusion weighted magnetic resonance imaging (DW-MRI) makes it possible to probe brain connections in vivo. This paper presents a change detection framework that relies on white matter pathways with application to neuromyelitis optica (NMO). The objective is to detect local or global fiber diffusion property modifications between two longitudinal DW-MRI acquisitions of a patient. To this end, we develop two frameworks based on statistical tests on tensor eigenvalues to detect local or global changes along the white matter pathways: a pointwise test that compares tensor populations extracted in bundles cross sections and a fiberwise test that compares paired tensors along all the fiber bundles. Experiments on both synthetic and real data highlight the benefit of considering fiber based statistical tests compared to standard voxelwise strategies.

Generalized likelihood ratio tests for change detection in diffusion tensor images: application to multiple sclerosis.

The automatic analysis of subtle changes between MRI scans is an important tool for monitoring disease evolution. Several methods have been proposed to detect changes in serial conventional MRI but few works have considered Diffusion Tensor Imaging (DTI), which is a promising modality for monitoring neurodegenerative disease and particularly Multiple Sclerosis (MS). In this paper, we introduce a comprehensive framework for detecting changes between two DTI acquisitions by considering different levels of representation of diffusion imaging, namely the Apparent Diffusion Coefficient (ADC) images, the diffusion tensor fields, and scalar images characterizing diffusion properties such as the fractional anisotropy and the mean diffusivity. The proposed statistical method for change detection is based on the Generalized Likelihood Ratio Test (GLRT) that has been derived for the different diffusion imaging representations, based on the core assumption of a Gaussian diffusion model and of an additive Gaussian noise on the ADCs. Results on synthetic and real images demonstrate the ability of the different tests to bring useful and complementary information in the context of the follow-up of MS patients.