Searcharxiv⌕ Search

arXiv subjects

Daniel C. Alexander

Publications and source records attributed to Daniel C. Alexander.

At least 91 records · Page 5Linked to original sources
arXiv2021

Mapping complex cell morphology in the grey matter with double diffusion encoding MR: a simulation study

This paper investigates the impact of cell body (soma) size and branching of cellular projections on diffusion MR imaging (dMRI) and spectroscopy (dMRS) signals for both standard single diffusion encoding (SDE) and more advanced double diffusion encoding (DDE) measurements using numerical simulations. The aim is to study the ability of dMRI/dMRS to characterize the complex morphology of brain grey matter, focusing on these two distinctive features. To this end, we employ a recently developed framework to create realistic meshes for Monte Carlo simulations, covering a wide range of soma sizes and branching orders of cellular projections, for diffusivities reflecting both water and metabolites. For SDE sequences, we assess the impact of soma size and branching order on the signal b-value dependence as well as the time dependence of the apparent diffusion coefficient (ADC). For DDE sequences, we assess their impact on the mixing time dependence of the signal angular modulation and of the estimated microscopic anisotropy, a promising contrast derived from DDE measurements. The SDE results show that soma size has a measurable impact on both the b-value and diffusion time dependence, for both water and metabolites. On the other hand, branching order has little impact on either, especially for water. In contrast, the DDE results show that soma size has a measurable impact on the signal angular modulation at short mixing times and the branching order significantly impacts the mixing time dependence of the signal angular modulation as well as of the derived microscopic anisotropy, for both water and metabolites. Our results confirm that soma size can be estimated from SDE based techniques, and most importantly, show for the first time that DDE measurements show sensitivity to the branching of cellular projections, paving the way for non-invasive characterization of grey matter morphology.

physics.med-ph↗
arXiv2021

Learning transition times in event sequences: the Event-Based Hidden Markov Model of disease progression

Progressive diseases worsen over time and are characterised by monotonic change in features that track disease progression. Here we connect ideas from two formerly separate methodologies -- event-based and hidden Markov modelling -- to derive a new generative model of disease progression. Our model can uniquely infer the most likely group-level sequence and timing of events (natural history) from limited datasets. Moreover, it can infer and predict individual-level trajectories (prognosis) even when data are missing, giving it high clinical utility. Here we derive the model and provide an inference scheme based on the expectation maximisation algorithm. We use clinical, imaging and biofluid data from the Alzheimer's Disease Neuroimaging Initiative to demonstrate the validity and utility of our model. First, we train our model to uncover a new group-level sequence of feature changes in Alzheimer's disease over a period of ${\sim}17.3$ years. Next, we demonstrate that our model provides improved utility over a continuous time hidden Markov model by area under the receiver operator characteristic curve ${\sim}0.23$. Finally, we demonstrate that our model maintains predictive accuracy with up to $50\%$ missing data. These results support the clinical validity of our model and its broader utility in resource-limited medical applications.

cs.LG↗
arXiv2021

Uncertainty-Aware Annotation Protocol to Evaluate Deformable Registration Algorithms

Landmark correspondences are a widely used type of gold standard in image registration. However, the manual placement of corresponding points is subject to high inter-user variability in the chosen annotated locations and in the interpretation of visual ambiguities. In this paper, we introduce a principled strategy for the construction of a gold standard in deformable registration. Our framework: (i) iteratively suggests the most informative location to annotate next, taking into account its redundancy with previous annotations; (ii) extends traditional pointwise annotations by accounting for the spatial uncertainty of each annotation, which can either be directly specified by the user, or aggregated from pointwise annotations from multiple experts; and (iii) naturally provides a new strategy for the evaluation of deformable registration algorithms. Our approach is validated on four different registration tasks. The experimental results show the efficacy of suggesting annotations according to their informativeness, and an improved capacity to assess the quality of the outputs of registration algorithms. In addition, our approach yields, from sparse annotations only, a dense visualization of the errors made by a registration method. The source code of our approach supporting both 2D and 3D data is publicly available at https://github.com/LoicPeter/evaluation-deformable-registration.

cs.CV↗
arXiv2020

Joint super-resolution and synthesis of 1 mm isotropic MP-RAGE volumes from clinical MRI exams with scans of different orientation, resolution and contrast

Most existing algorithms for automatic 3D morphometry of human brain MRI scans are designed for data with near-isotropic voxels at approximately 1 mm resolution, and frequently have contrast constraints as well - typically requiring T1 scans (e.g., MP-RAGE). This limitation prevents the analysis of millions of MRI scans acquired with large inter-slice spacing ("thick slice") in clinical settings every year. The inability to quantitatively analyze these scans hinders the adoption of quantitative neuroimaging in healthcare, and precludes research studies that could attain huge sample sizes and hence greatly improve our understanding of the human brain. Recent advances in CNNs are producing outstanding results in super-resolution and contrast synthesis of MRI. However, these approaches are very sensitive to the contrast, resolution and orientation of the input images, and thus do not generalize to diverse clinical acquisition protocols - even within sites. Here we present SynthSR, a method to train a CNN that receives one or more thick-slice scans with different contrast, resolution and orientation, and produces an isotropic scan of canonical contrast (typically a 1 mm MP-RAGE). The presented method does not require any preprocessing, e.g., skull stripping or bias field correction. Crucially, SynthSR trains on synthetic input images generated from 3D segmentations, and can thus be used to train CNNs for any combination of contrasts, resolutions and orientations without high-resolution training data. We test the images generated with SynthSR in an array of common downstream analyses, and show that they can be reliably used for subcortical segmentation and volumetry, image registration (e.g., for tensor-based morphometry), and, if some image quality requirements are met, even cortical thickness morphometry. The source code is publicly available at github.com/BBillot/SynthSR.

eess.IV↗
arXiv2020

Disentangling Human Error from the Ground Truth in Segmentation of Medical Images

Recent years have seen increasing use of supervised learning methods for segmentation tasks. However, the predictive performance of these algorithms depends on the quality of labels. This problem is particularly pertinent in the medical image domain, where both the annotation cost and inter-observer variability are high. In a typical label acquisition process, different human experts provide their estimates of the "true" segmentation labels under the influence of their own biases and competence levels. Treating these noisy labels blindly as the ground truth limits the performance that automatic segmentation algorithms can achieve. In this work, we present a method for jointly learning, from purely noisy observations alone, the reliability of individual annotators and the true segmentation label distributions, using two coupled CNNs. The separation of the two is achieved by encouraging the estimated annotators to be maximally unreliable while achieving high fidelity with the noisy training data. We first define a toy segmentation dataset based on MNIST and study the properties of the proposed algorithm. We then demonstrate the utility of the method on three public medical imaging segmentation datasets with simulated (when necessary) and real diverse annotations: 1) MSLSC (multiple-sclerosis lesions); 2) BraTS (brain tumours); 3) LIDC-IDRI (lung abnormalities). In all cases, our method outperforms competing methods and relevant baselines particularly in cases where the number of annotations is small and the amount of disagreement is large. The experiments also show strong ability to capture the complex spatial characteristics of annotators' mistakes.

cs.CV↗
arXiv2020

Learning To Pay Attention To Mistakes

In convolutional neural network based medical image segmentation, the periphery of foreground regions representing malignant tissues may be disproportionately assigned as belonging to the background class of healthy tissues \cite{attenUnet}\cite{AttenUnet2018}\cite{InterSeg}\cite{UnetFrontNeuro}\cite{LearnActiveContour}. This leads to high false negative detection rates. In this paper, we propose a novel attention mechanism to directly address such high false negative rates, called Paying Attention to Mistakes. Our attention mechanism steers the models towards false positive identification, which counters the existing bias towards false negatives. The proposed mechanism has two complementary implementations: (a) "explicit" steering of the model to attend to a larger Effective Receptive Field on the foreground areas; (b) "implicit" steering towards false positives, by attending to a smaller Effective Receptive Field on the background areas. We validated our methods on three tasks: 1) binary dense prediction between vehicles and the background using CityScapes; 2) Enhanced Tumour Core segmentation with multi-modal MRI scans in BRATS2018; 3) segmenting stroke lesions using ultrasound images in ISLES2018. We compared our methods with state-of-the-art attention mechanisms in medical imaging, including self-attention, spatial-attention and spatial-channel mixed attention. Across all of the three different tasks, our models consistently outperform the baseline models in Intersection over Union (IoU) and/or Hausdorff Distance (HD). For instance, in the second task, the "explicit" implementation of our mechanism reduces the HD of the best baseline by more than $26\%$, whilst improving the IoU by more than $3\%$. We believe our proposed attention mechanism can benefit a wide range of medical and computer vision tasks, which suffer from over-detection of background.

cs.CV↗
arXiv2020

Foveation for Segmentation of Ultra-High Resolution Images

Segmentation of ultra-high resolution images is challenging because of their enormous size, consisting of millions or even billions of pixels. Typical solutions include dividing input images into patches of fixed size and/or down-sampling to meet memory constraints. Such operations incur information loss in the field-of-view (FoV) i.e., spatial coverage and the image resolution. The impact on segmentation performance is, however, as yet understudied. In this work, we start with a motivational experiment which demonstrates that the trade-off between FoV and resolution affects the segmentation performance on ultra-high resolution images---and furthermore, its influence also varies spatially according to the local patterns in different areas. We then introduce foveation module, a learnable "dataloader" which, for a given ultra-high resolution image, adaptively chooses the appropriate configuration (FoV/resolution trade-off) of the input patch to feed to the downstream segmentation model at each spatial location of the image. The foveation module is jointly trained with the segmentation network to maximise the task performance. We demonstrate on three publicly available high-resolution image datasets that the foveation module consistently improves segmentation performance over the cases trained with patches of fixed FoV/resolution trade-off. Our approach achieves the SoTA performance on the DeepGlobe aerial image dataset. On the Gleason2019 histopathology dataset, our model achieves better segmentation accuracy for the two most clinically important and ambiguous classes (Gleason Grade 3 and 4) than the top performers in the challenge by 13.1% and 7.5%, and improves on the average performance of 6 human experts by 6.5% and 7.5%. Our code and trained models are available at $\text{https://github.com/lxasqjc/Foveation-Segmentation}$.

cs.CV↗
arXiv2020

SANDI: a compartment-based model for non-invasive apparent soma and neurite imaging by diffusion MRI

This work introduces a compartment-based model for apparent soma and neurite density imaging (SANDI) using non-invasive diffusion-weighted MRI (DW-MRI). The existing conjecture in brain microstructure imaging trough DW-MRI presents water diffusion in white (WM) and grey (GM) matter as restricted diffusion in neurites, modelled by infinite cylinders of null radius embedded in the hindered extra-neurite water. The extra-neurite pool in WM corresponds to water in the extra-axonal space, but in GM it combines water in the extra-cellular space with water in soma. While several studies showed that this microstructure model successfully describe DW-MRI data in WM and GM at b<3 ms/{\mum^2}, it has been also shown to fail in GM at high b values (b>>3 ms/{\mum^2}). Here we hypothesize that the unmodelled soma compartment may be responsible for this failure and propose SANDI as a new model of brain microstructure where soma (i.e. cell body of any brain cell type: from neuroglia to neurons) is explicitly included. We assess the effects of size and density of soma on the direction-averaged DW-MRI signal at high b values and the regime of validity of the model using numerical simulations and comparison with experimental data from mouse (bmax = 40 ms/{/mum^2}) and human (bmax = 10 ms/{\mum^2}) brain. We show that SANDI defines new contrasts representing new complementary information on the brain cyto- and myelo-architecture. Indeed, we show for the first-time maps from 25 healthy human subjects of MR soma and neurite signal fractions, that remarkably mirror contrasts of histological images of brain cyto- and myelo-architecture. Although still under validation, SANDI might provide new insight into tissue architecture by introducing a new set of biomarkers of potential great value for biomedical applications and pure neuroscience.

physics.med-ph↗
arXiv2020

ConFiG: Contextual Fibre Growth to generate realistic axonal packing for diffusion MRI simulation

This paper presents Contextual Fibre Growth (ConFiG), an approach to generate white matter numerical phantoms by mimicking natural fibre genesis. ConFiG grows fibres one-by-one, following simple rules motivated by real axonal guidance mechanisms. These simple rules enable ConFiG to generate phantoms with tuneable microstructural features by growing fibres while attempting to meet morphological targets such as user-specified density and orientation distribution. We compare ConFiG to the state-of-the-art approach based on packing fibres together by generating phantoms in a range of fibre configurations including crossing fibre bundles and orientation dispersion. Results demonstrate that ConFiG produces phantoms with up to 20% higher densities than the state-of-the-art, particularly in complex configurations with crossing fibres. We additionally show that the microstructural morphology of ConFiG phantoms is comparable to real tissue, producing diameter and orientation distributions close to electron microscopy estimates from real tissue as well as capturing complex fibre cross sections. Signals simulated from ConFiG phantoms match real diffusion MRI data well, showing that ConFiG phantoms can be used to generate realistic diffusion MRI data. This demonstrates the feasibility of ConFiG to generate realistic synthetic diffusion MRI data for developing and validating microstructure modelling approaches.

physics.med-ph↗
arXiv2020

Image Quality Transfer Enhances Contrast and Resolution of Low-Field Brain MRI in African Paediatric Epilepsy Patients

1.5T or 3T scanners are the current standard for clinical MRI, but low-field (<1T) scanners are still common in many lower- and middle-income countries for reasons of cost and robustness to power failures. Compared to modern high-field scanners, low-field scanners provide images with lower signal-to-noise ratio at equivalent resolution, leaving practitioners to compensate by using large slice thickness and incomplete spatial coverage. Furthermore, the contrast between different types of brain tissue may be substantially reduced even at equal signal-to-noise ratio, which limits diagnostic value. Recently the paradigm of Image Quality Transfer has been applied to enhance 0.36T structural images aiming to approximate the resolution, spatial coverage, and contrast of typical 1.5T or 3T images. A variant of the neural network U-Net was trained using low-field images simulated from the publicly available 3T Human Connectome Project dataset. Here we present qualitative results from real and simulated clinical low-field brain images showing the potential value of IQT to enhance the clinical utility of readily accessible low-field MRIs in the management of epilepsy.

eess.IV↗
arXiv2020

TADPOLE Challenge: Accurate Alzheimer's disease prediction through crowdsourced forecasting of future data

The 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, 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 EMC1), 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 (BenchmarkME), 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.

q-bio.PE↗
arXiv2019

Deep Learning for Low-Field to High-Field MR: Image Quality Transfer with Probabilistic Decimation Simulator

MR images scanned at low magnetic field ($<1$T) have lower resolution in the slice direction and lower contrast, due to a relatively small signal-to-noise ratio (SNR) than those from high field (typically 1.5T and 3T). We adapt the recent idea of Image Quality Transfer (IQT) to enhance very low-field structural images aiming to estimate the resolution, spatial coverage, and contrast of high-field images. Analogous to many learning-based image enhancement techniques, IQT generates training data from high-field scans alone by simulating low-field images through a pre-defined decimation model. However, the ground truth decimation model is not well-known in practice, and lack of its specification can bias the trained model, aggravating performance on the real low-field scans. In this paper we propose a probabilistic decimation simulator to improve robustness of model training. It is used to generate and augment various low-field images whose parameters are random variables and sampled from an empirical distribution related to tissue-specific SNR on a 0.36T scanner. The probabilistic decimation simulator is model-agnostic, that is, it can be used with any super-resolution networks. Furthermore we propose a variant of U-Net architecture to improve its learning performance. We show promising qualitative results from clinical low-field images confirming the strong efficacy of IQT in an important new application area: epilepsy diagnosis in sub-Saharan Africa where only low-field scanners are normally available.

eess.IV↗
arXiv2019

Degenerative Adversarial NeuroImage Nets: Generating Images that Mimic Disease Progression

Simulating images representative of neurodegenerative diseases is important for predicting patient outcomes and for validation of computational models of disease progression. This capability is valuable for secondary prevention clinical trials where outcomes and screening criteria involve neuroimaging. Traditional computational methods are limited by imposing a parametric model for atrophy and are extremely resource-demanding. Recent advances in deep learning have yielded data-driven models for longitudinal studies (e.g., face ageing) that are capable of generating synthetic images in real-time. Similar solutions can be used to model trajectories of atrophy in the brain, although new challenges need to be addressed to ensure accurate disease progression modelling. Here we propose Degenerative Adversarial NeuroImage Net (DaniNet) --- a new deep learning approach that learns to emulate the effect of neurodegeneration on MRI by simulating atrophy as a function of ages, and disease progression. DaniNet uses an underlying set of Support Vector Regressors (SVRs) trained to capture the patterns of regional intensity changes that accompany disease progression. DaniNet produces whole output images, consisting of 2D-MRI slices that are constrained to match regional predictions from the SVRs. DaniNet is also able to maintain the unique brain morphology of individuals. Adversarial training ensures realistic brain images and smooth temporal progression. We train our model using 9652 T1-weighted (longitudinal) MRI extracted from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. We perform quantitative and qualitative evaluations on a separate test set of 1283 images (also from ADNI) demonstrating the ability of DaniNet to produce accurate and convincing synthetic images that emulate disease progression.

eess.IV↗
arXiv2019

Stochastic Filter Groups for Multi-Task CNNs: Learning Specialist and Generalist Convolution Kernels

The performance of multi-task learning in Convolutional Neural Networks (CNNs) hinges on the design of feature sharing between tasks within the architecture. The number of possible sharing patterns are combinatorial in the depth of the network and the number of tasks, and thus hand-crafting an architecture, purely based on the human intuitions of task relationships can be time-consuming and suboptimal. In this paper, we present a probabilistic approach to learning task-specific and shared representations in CNNs for multi-task learning. Specifically, we propose "stochastic filter groups'' (SFG), a mechanism to assign convolution kernels in each layer to "specialist'' or "generalist'' groups, which are specific to or shared across different tasks, respectively. The SFG modules determine the connectivity between layers and the structures of task-specific and shared representations in the network. We employ variational inference to learn the posterior distribution over the possible grouping of kernels and network parameters. Experiments demonstrate that the proposed method generalises across multiple tasks and shows improved performance over baseline methods.

cs.CV↗
arXiv2019

BrainPainter: A software for the visualisation of brain structures, biomarkers and associated pathological processes

We present BrainPainter, a software that automatically generates images of highlighted brain structures given a list of numbers corresponding to the output colours of each region. Compared to existing visualisation software (i.e. Freesurfer, SPM, 3D Slicer), BrainPainter has three key advantages: (1) it does not require the input data to be in a specialised format, allowing BrainPainter to be used in combination with any neuroimaging analysis tools, (2) it can visualise both cortical and subcortical structures and (3) it can be used to generate movies showing dynamic processes, e.g. propagation of pathology on the brain. We highlight three use cases where BrainPainter was used in existing neuroimaging studies: (1) visualisation of the degree of atrophy through interpolation along a user-defined gradient of colours, (2) visualisation of the progression of pathology in Alzheimer's disease as well as (3) visualisation of pathology in subcortical regions in Huntington's disease. Moreover, through the design of BrainPainter we demonstrate the possibility of using a powerful 3D computer graphics engine such as Blender to generate brain visualisations for the neuroscience community. Blender's capabilities, e.g. particle simulations, motion graphics, UV unwrapping, raster graphics editing, raytracing and illumination effects, open a wealth of possibilities for brain visualisation not available in current neuroimaging software. BrainPainter is customisable, easy to use, and can run straight from the web browser: https://brainpainter.csail.mit.edu , as well as from source-code packaged in a docker container: https://github.com/mrazvan22/brain-coloring . It can be used to visualise biomarker data from any brain imaging modality, or simply to highlight a particular brain structure for e.g. anatomy courses.

cs.GR↗
arXiv2019

Uncertainty Quantification in Deep Learning for Safer Neuroimage Enhancement

Deep learning (DL) has shown great potential in medical image enhancement problems, such as super-resolution or image synthesis. However, to date, little consideration has been given to uncertainty quantification over the output image. Here we introduce methods to characterise different components of uncertainty in such problems and demonstrate the ideas using diffusion MRI super-resolution. Specifically, we propose to account for $intrinsic$ uncertainty through a heteroscedastic noise model and for $parameter$ uncertainty through approximate Bayesian inference, and integrate the two to quantify $predictive$ uncertainty over the output image. Moreover, we introduce a method to propagate the predictive uncertainty on a multi-channelled image to derived scalar parameters, and separately quantify the effects of intrinsic and parameter uncertainty therein. The methods are evaluated for super-resolution of two different signal representations of diffusion MR images---DTIs and Mean Apparent Propagator MRI---and their derived quantities such as MD and FA, on multiple datasets of both healthy and pathological human brains. Results highlight three key benefits of uncertainty modelling for improving the safety of DL-based image enhancement systems. Firstly, incorporating uncertainty improves the predictive performance even when test data departs from training data. Secondly, the predictive uncertainty highly correlates with errors, and is therefore capable of detecting predictive "failures". Results demonstrate that such an uncertainty measure enables subject-specific and voxel-wise risk assessment of the output images. Thirdly, we show that the method for decomposing predictive uncertainty into its independent sources provides high-level "explanations" for the performance by quantifying how much uncertainty arises from the inherent difficulty of the task or the limited training examples.

eess.IV↗
arXiv2019

Disease Knowledge Transfer across Neurodegenerative Diseases

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, multimodal 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.

cs.LG↗