Generative AI unlocks PET insights: brain amyloid dynamics and quantification.

Introduction: Studying the spatiotemporal patterns of amyloid accumulation in the brain over time is crucial in understanding Alzheimer's disease (AD). Positron Emission Tomography (PET) imaging plays a pivotal role because it allows for the visualization and quantification of abnormal amyloid beta (Aß) load in the living brain, providing a powerful tool for tracking disease progression and evaluating the efficacy of anti-amyloid therapies. Generative artificial intelligence (AI) can learn complex data distributions and generate realistic synthetic images. In this study, we demonstrate for the first time the potential of Generative Adversarial Networks (GANs) to build a low-dimensional representation space that effectively describes brain amyloid load and its dynamics. Methods: Using a cohort of 1,259 subjects with AV45 PET images from the Alzheimer's Disease Neuroimaging Initiative (ADNI), we develop a 3D GAN model to project images into a latent representation space and generate back synthetic images. Then, we build a progression model on the representation space based on non-parametric ordinary differential equations to study brain amyloid evolution. Results: We found that global SUVR can be accurately predicted with a linear regression model only from the latent representation space (RMSE = 0.08 ± 0.01). We generated synthetic PET trajectories and illustrated predicted Aß change in four years compared with actual progression. Discussion: Generative AI can generate rich representations for statistical prediction and progression modeling and simulate evolution in synthetic patients, providing an invaluable tool for understanding AD, assisting in diagnosis, and designing clinical trials. The aim of this study was to illustrate the huge potential that generative AI has in brain amyloid imaging and to encourage its advancement by providing use cases and ideas for future research tracks.

The STOIC2021 COVID-19 AI challenge: Applying reusable training methodologies to private data.

Challenges drive the state-of-the-art of automated medical image analysis. The quantity of public training data that they provide can limit the performance of their solutions. Public access to the training methodology for these solutions remains absent. This study implements the Type Three (T3) challenge format, which allows for training solutions on private data and guarantees reusable training methodologies. With T3, challenge organizers train a codebase provided by the participants on sequestered training data. T3 was implemented in the STOIC2021 challenge, with the goal of predicting from a computed tomography (CT) scan whether subjects had a severe COVID-19 infection, defined as intubation or death within one month. STOIC2021 consisted of a Qualification phase, where participants developed challenge solutions using 2000 publicly available CT scans, and a Final phase, where participants submitted their training methodologies with which solutions were trained on CT scans of 9724 subjects. The organizers successfully trained six of the eight Final phase submissions. The submitted codebases for training and running inference were released publicly. The winning solution obtained an area under the receiver operating characteristic curve for discerning between severe and non-severe COVID-19 of 0.815. The Final phase solutions of all finalists improved upon their Qualification phase solutions.

Causality-driven multivariate stock movement forecasting.

Our study aims to investigate the interdependence between international stock markets and sentiments from financial news in stock forecasting. We adopt the Temporal Fusion Transformers (TFT) to incorporate intra and inter-market correlations and the interaction between the information flow, i.e. causality, of financial news sentiment and the dynamics of the stock market. The current study distinguishes itself from existing research by adopting Dynamic Transfer Entropy (DTE) to establish an accurate information flow propagation between stock and sentiments. DTE has the advantage of providing time series that mine information flow propagation paths between certain parts of the time series, highlighting marginal events such as spikes or sudden jumps, which are crucial in financial time series. The proposed methodological approach involves the following elements: a FinBERT-based textual analysis of financial news articles to extract sentiment time series, the use of the Transfer Entropy and corresponding heat maps to analyze the net information flows, the calculation of the DTE time series, which are considered as co-occurring covariates of stock Price, and TFT-based stock forecasting. The Dow Jones Industrial Average index of 13 countries, along with daily financial news data obtained through the New York Times API, are used to demonstrate the validity and superiority of the proposed DTE-based causality method along with TFT for accurate stock Price and Return forecasting compared to state-of-the-art time series forecasting methods.

Long-Term Regional Influenza-Like-Illness Forecasting Using Exogenous Data.

Disease forecasting is a longstanding problem for the research community, which aims at informing and improving decisions with the best available evidence. Specifically, the interest in respiratory disease forecasting has dramatically increased since the beginning of the coronavirus pandemic, rendering the accurate prediction of influenza-like-illness (ILI) a critical task. Although methods for short-term ILI forecasting and nowcasting have achieved good accuracy, their performance worsens at long-term ILI forecasts. Machine learning models have outperformed conventional forecasting approaches enabling to utilize diverse exogenous data sources, such as social media, internet users' search query logs, and climate data. However, the most recent deep learning ILI forecasting models use only historical occurrence data achieving state-of-the-art results. Inspired by recent deep neural network architectures in time series forecasting, this work proposes the Regional Influenza-Like-Illness Forecasting (ReILIF) method for regional long-term ILI prediction. The proposed architecture takes advantage of diverse exogenous data, that are, meteorological and population data, introducing an efficient intermediate fusion mechanism to combine the different types of information with the aim to capture the variations of ILI from various views. The efficacy of the proposed approach compared to state-of-the-art ILI forecasting methods is confirmed by an extensive experimental study following standard evaluation measures.

Semi-supervised medical image classification via distance correlation minimization and graph attention regularization.

We propose a novel semi-supervised learning method to leverage unlabeled data alongside minimal annotated data and improve medical imaging classification performance in realistic scenarios with limited labeling budgets to afford data annotations. Our method introduces distance correlation to minimize correlations between feature representations from different views of the same image encoded with non-coupled deep neural networks architectures. In addition, it incorporates a data-driven graph-attention based regularization strategy to model affinities among images within the unlabeled data by exploiting their inherent relational information in the feature space. We conduct extensive experiments on four medical imaging benchmark data sets involving X-ray, dermoscopic, magnetic resonance, and computer tomography imaging on single and multi-label medical imaging classification scenarios. Our experiments demonstrate the effectiveness of our method in achieving very competitive performance and outperforming several state-of-the-art semi-supervised learning methods. Furthermore, they confirm the suitability of distance correlation as a versatile dependence measure and the benefits of the proposed graph-attention based regularization for semi-supervised learning in medical imaging analysis.

A multidimensional ODE-based model of Alzheimer's disease progression.

Data-driven Alzheimer's disease (AD) progression models are useful for clinical prediction, disease mechanism understanding, and clinical trial design. Most dynamic models were inspired by the amyloid cascade hypothesis and described AD progression as a linear chain of pathological events. However, the heterogeneity observed in healthy and sporadic AD populations challenged the amyloid hypothesis, and there is a need for more flexible dynamical models that accompany this conceptual shift. We present a statistical model of the temporal evolution of biomarkers and cognitive tests that allows diverse biomarker paths throughout the disease. The model consists of two elements: a multivariate dynamic model of the joint evolution of biomarkers and cognitive tests; and a clinical prediction model. The dynamic model uses a system of ordinary differential equations to jointly model the rate of change of an individual's biomarkers and cognitive tests. The clinical prediction model is an ordinal logistic model of the diagnostic label. Prognosis and time-to-onset predictions are obtained by computing the clinical label probabilities throughout the forecasted biomarker trajectories. The proposed dynamical model is interpretable, free of one-dimensional progression hypotheses or disease staging paradigms, and can account for the heterogeneous dynamics observed in sporadic AD. We developed the model using longitudinal data from the Alzheimer's Disease Neuroimaging Initiative. We illustrate the patterns of biomarker rates of change and the model performance to predict the time to conversion from MCI to dementia.

Public Covid-19 X-ray datasets and their impact on model bias - A systematic review of a significant problem.

Computer-aided-diagnosis and stratification of COVID-19 based on chest X-ray suffers from weak bias assessment and limited quality-control. Undetected bias induced by inappropriate use of datasets, and improper consideration of confounders prevents the translation of prediction models into clinical practice. By adopting established tools for model evaluation to the task of evaluating datasets, this study provides a systematic appraisal of publicly available COVID-19 chest X-ray datasets, determining their potential use and evaluating potential sources of bias. Only 9 out of more than a hundred identified datasets met at least the criteria for proper assessment of risk of bias and could be analysed in detail. Remarkably most of the datasets utilised in 201 papers published in peer-reviewed journals, are not among these 9 datasets, thus leading to models with high risk of bias. This raises concerns about the suitability of such models for clinical use. This systematic review highlights the limited description of datasets employed for modelling and aids researchers to select the most suitable datasets for their task.

Plasma amyloid ß 42/40 ratios as biomarkers for amyloid ß cerebral deposition in cognitively normal individuals.

INTRODUCTION: Plasma amyloid ß (Aß) peptides have been previously studied as candidate biomarkers to increase recruitment efficiency in secondary prevention clinical trials for Alzheimer's disease. METHODS: Free and total Aß42/40 plasma ratios (FP42/40 and TP42/40, respectively) were determined using ABtest assays in cognitively normal subjects from the Australian Imaging, Biomarker and Lifestyle Flagship Study. This population was followed-up for 72 months and their cortical Aß burden was assessed with positron emission tomography. RESULTS: Cross-sectional and longitudinal analyses showed an inverse association of Aß42/40 plasma ratios and cortical Aß burden. Optimized as a screening tool, TP42/40 reached 81% positive predictive value of high cortical Aß burden, which represents 110% increase over the population prevalence of cortical Aß positivity. DISCUSSION: These findings support the use of plasma Aß42/40 ratios as surrogate biomarkers of cortical Aß deposition and enrichment tools, reducing the number of subjects submitted to invasive tests and, consequently, recruitment costs in clinical trials targeting cognitively normal individuals.

Statistical analysis of relative pose information of subcortical nuclei: application on ADNI data.

Many brain morphometry studies have been performed in order to characterize the brain atrophy pattern of Alzheimer's disease (AD). The earliest studies focused on the volume of particular brain structures, such as hippocampus and entorhinal cortex. Even though volumetry is a powerful, robust and intuitive technique that has yielded a wealth of findings, more complex shape descriptors have been used to perform statistical shape analysis of particular brain structures. However, in shape analysis studies of brain structures the information of the relative pose between neighbor structures is typically disregarded. This work presents a framework to analyse pose information including the following approaches: similarity transformations with either pseudo-Riemannian or left-invariant Riemannian metric, and centered transformations with a bi-invariant Riemannian metric. As an illustration, an analysis of covariance (ANCOVA) and a discrimination analysis were performed on Alzheimer's Disease Neuroimaging Initiative (ADNI) data.

Discrimination of AD and normal subjects from MRI: anatomical versus statistical regions.

This work is a feature-extraction and classification study between Alzheimer's disease (AD) patients and normal subjects. Voxel-wise morphological features of brain MRI are defined as the Jacobian determinants that measure the local volume change between each subject and a given atlas. The goal of this work is to determine the region of interest (ROI) which is best suited for classification. Two types of ROIs are considered: anatomical regions, that were automatically segmented in the atlas (amygdalae, hippocampi and lateral ventricles); and statistical regions, defined from group comparison statistical maps. Classification performance was assessed with five classifiers on 20 pairs of matched training and test groups of subjects from the ADNI database. In this study the statistical masks provided the best classification performance.

Variations in the shape of the frontobasal brain region in obsessive-compulsive disorder.

Obsessive-compulsive disorder (OCD) emerges during childhood through young adulthood coinciding with the late phases of postnatal brain development when fine remodeling of brain anatomy takes place. Previous research has suggested the existence of subtle anatomical alterations in OCD involving focal volume variations in different brain regions including the frontal lobes and basal ganglia. We investigated whether anatomical changes might also involve variations in the shape of the frontobasal region. A total of 101 OCD patients and 101 control subjects were examined using magnetic resonance imaging. A cross-sectional image highly representative of frontal-basal ganglia anatomy was selected in each individual and 25 reliable anatomical landmarks were identified to assess shape changes. A pixel-wise morphing approach was also used to dynamically illustrate the findings. We found significant group differences for overall landmark position and for most individual landmarks delimiting the defined frontobasal region. OCD patients showed a deformation pattern involving shortening of the anterior-posterior dimension of the frontal lobes and basal ganglia, and enlargement of cerebrospinal fluid spaces around the frontal opercula. In addition, we observed significant correlation of brain tissue shape variation with frontal sinus size. Identification of a global change in the shape of the frontobasal region may further contribute to characterizing the nature of brain alterations in OCD. The coincidence of brain shape variations with morphological changes in the frontal sinus indicates a potential association of OCD to late development disturbances, as the frontal sinus macroscopically emerges during the transition between childhood and adulthood.

Tensor-based morphometry with stationary velocity field diffeomorphic registration: application to ADNI.

Tensor-based morphometry (TBM) is an analysis technique where anatomical information is characterized by means of the spatial transformations mapping a customized template with the observed images. Therefore, accurate inter-subject non-rigid registration is an essential prerequisite for both template estimation and image warping. Subsequent statistical analysis on the spatial transformations is performed to highlight voxel-wise differences. Most of previous TBM studies did not explore the influence of the registration parameters, such as the parameters defining the deformation and the regularization models. In this work performance evaluation of TBM using stationary velocity field (SVF) diffeomorphic registration was performed in a subset of subjects from Alzheimer's Disease Neuroimaging Initiative (ADNI) study. A wide range of values of the registration parameters that define the transformation smoothness and the balance between image matching and regularization were explored in the evaluation. The proposed methodology provided brain atrophy maps with very detailed anatomical resolution and with a high significance level compared with results recently published on the same data set using a non-linear elastic registration method.

Tensor-based morphometry with mappings parameterized by stationary velocity fields in Alzheimer's disease neuroimaging initiative.

Tensor-based morphometry (TBM) is an analysis technique where anatomical information is characterized by means of the spatial transformations between a customized template and observed images. Therefore, accurate inter-subject non-rigid registration is an essential prerrequisite. Further statistical analysis of the spatial transformations is used to highlight some useful information, such as local statistical differences among populations. With the new advent of recent and powerful non-rigid registration algorithms based on the large deformation paradigm, TBM is being increasingly used. In this work we evaluate the statistical power of TBM using stationary velocity field diffeomorphic registration in a large population of subjects from Alzheimer's Disease Neuroimaging Initiative project. The proposed methodology provided atrophy maps with very detailed anatomical resolution and with a high significance compared with results published recently on the same data set.

Contributions to 3D diffeomorphic atlas estimation: application to brain images.

This paper focuses on the estimation of statistical atlases of 3D images by means of diffeomorphic transformations. Within a Log-Euclidean framework, the exponential and logarithm maps of diffeomorphisms need to be computed. In this framework, the Inverse Scaling and Squaring (ISS) method has been recently extended for the computation of the logarithm map, which is one of the most time demanding stages. In this work we propose to apply the Baker-Campbell-Hausdorff (BCH) formula instead. In a 3D simulation study, BCH formula and ISS method obtained similar accuracy but BCH formula was more than 100 times faster. This approach allowed us to estimate a 3D statistical brain atlas in a reasonable time, including the average and the modes of variation. Details for the computation of the modes of variation in the Sobolev tangent space of diffeomorphisms are also provided.