Towards cascading genetic risk in Alzheimer's disease.

Alzheimer's disease typically progresses in stages, which have been defined by the presence of disease-specific biomarkers: Amyloid (A), Tau (T) and neurodegeneration (N). This progression of biomarkers has been condensed into the ATN framework, where each of the biomarkers can be either positive (+) or negative (-). Over the past decades genome wide association studies have implicated about 90 different loci involved with the development of late onset Alzheimer's disease. Here we investigate whether genetic risk for Alzheimer's disease contributes equally to the progression in different disease stages or whether it exhibits a stage-dependent effect. Amyloid (A) and tau (T) status was defined using a combination of available PET and CSF biomarkers in the Alzheimer's Disease Neuroimaging Initiative cohort. In 312 participants with biomarker-confirmed A-T- status, we employed Cox proportional hazards models to estimate the contribution of APOE and polygenic risk scores (beyond APOE) to convert to A+T- status (65 conversions). Furthermore, we repeated the analysis in 290 participants with A+T- status and investigated the genetic contribution to conversion to A+T+ (45 conversions). Both survival analyses were adjusted for age, sex, and years of education. For progression from A-T- to A+T-, APOE-e4 burden showed significant effect (HR=2.88; 95% CI: 1.70-4.89; P<0.001), while polygenic risk did not (HR=1.09; 95% CI: 0.84-1.42; P=0.53). Conversely, for the transition from A+T- to A+T+, the APOE-e4 burden contribution was reduced (HR=1.62 95% CI: 1.05-2.51; P=0.031), while the polygenic risk showed an increased contribution (HR=1.73; 95% CI:1.27-2.36; P<0.001). The marginal APOE effect was driven by e4 homozygotes (HR=2.58; 95% CI: 1.05-6.35; P=0.039) as opposed to e4 heterozygotes (HR=1.74; 95% CI: 0.87-3.49; P=0.12). The genetic risk for late-onset Alzheimer's disease unfolds in a disease stage-dependent fashion. A better understanding of the interplay between disease stage and genetic risk can lead to a more mechanistic understanding of transition between ATN stages, a better understanding of the molecular processes leading to Alzheimer's disease as well as opening therapeutic windows for targeted interventions.

Symptom-based staging for logopenic variant primary progressive aphasia.

BACKGROUND AND PURPOSE: Logopenic variant primary progressive aphasia (lvPPA) is a major variant presentation of Alzheimer's disease (AD) that signals the importance of communication dysfunction across AD phenotypes. A clinical staging system is lacking for the evolution of AD-associated communication difficulties that could guide diagnosis and care planning. Our aim was to create a symptom-based staging scheme for lvPPA, identifying functional milestones relevant to the broader AD spectrum. METHODS: An international lvPPA caregiver cohort was surveyed on symptom development under an 'exploratory' survey (34 UK caregivers). Feedback from this survey informed the development of a 'consolidation' survey (27 UK, 10 Australian caregivers) in which caregivers were presented with six provisional clinical stages and feedback was analysed using a mixed-methods approach. RESULTS: Six clinical stages were endorsed. Early symptoms included word-finding difficulty, with loss of message comprehension and speech intelligibility signalling later-stage progression. Additionally, problems with hearing in noise, memory and route-finding were prominent early non-verbal symptoms. 'Milestone' symptoms were identified that anticipate daily-life functional transitions and care needs. CONCLUSIONS: This work introduces a new symptom-based staging scheme for lvPPA, and highlights milestone symptoms that could inform future clinical scales for anticipating and managing communication dysfunction across the AD spectrum.

Expectation maximisation pseudo labels.

In this paper, we study pseudo-labelling. Pseudo-labelling employs raw inferences on unlabelled data as pseudo-labels for self-training. We elucidate the empirical successes of pseudo-labelling by establishing a link between this technique and the Expectation Maximisation algorithm. Through this, we realise that the original pseudo-labelling serves as an empirical estimation of its more comprehensive underlying formulation. Following this insight, we present a full generalisation of pseudo-labels under Bayes' theorem, termed Bayesian Pseudo Labels. Subsequently, we introduce a variational approach to generate these Bayesian Pseudo Labels, involving the learning of a threshold to automatically select high-quality pseudo labels. In the remainder of the paper, we showcase the applications of pseudo-labelling and its generalised form, Bayesian Pseudo-Labelling, in the semi-supervised segmentation of medical images. Specifically, we focus on: (1) 3D binary segmentation of lung vessels from CT volumes; (2) 2D multi-class segmentation of brain tumours from MRI volumes; (3) 3D binary segmentation of whole brain tumours from MRI volumes; and (4) 3D binary segmentation of prostate from MRI volumes. We further demonstrate that pseudo-labels can enhance the robustness of the learned representations. The code is released in the following GitHub repository: https://github.com/moucheng2017/EMSSL.

Crop filling: A pipeline for repairing memory clinic MRI corrupted by partial brain coverage.

Data-driven solutions offer great promise for improving healthcare. However, standard clinical neuroimaging data is subject to real-world imaging artefacts that can render the data unusable for computational research and quantitative neuroradiology. T1 weighted structural MRI is used in dementia research to obtain volumetric measurements from cortical and subcortical brain regions. However, clinical radiologists often prioritise T2 weighted or FLAIR scans for visual assessment. As such, T1 weighted scans are often acquired but may not be a priority, resulting in artefacts such as partial brain coverage being systematically present in memory clinic data. Here we present "MRI Crop Filling", a pipeline to replace the missing T1 data with synthetic data generated from the T2 scan, making real-world clinical T1 data usable for computational research including the latest AI innovations. Our method consists of the following steps:•Register scans: T2 and (cropped) T1.•Synthesise a new T1 using an open source deep learning tool.•Replace missing (cropped) T1 data in original T1 scan and super-resolve to improve image quality.

Data-driven modelling of neurodegenerative disease progression: thinking outside the black box.

Data-driven disease progression models are an emerging set of computational tools that reconstruct disease timelines for long-term chronic diseases, providing unique insights into disease processes and their underlying mechanisms. Such methods combine a priori human knowledge and assumptions with large-scale data processing and parameter estimation to infer long-term disease trajectories from short-term data. In contrast to 'black box' machine learning tools, data-driven disease progression models typically require fewer data and are inherently interpretable, thereby aiding disease understanding in addition to enabling classification, prediction and stratification. In this Review, we place the current landscape of data-driven disease progression models in a general framework and discuss their enhanced utility for constructing a disease timeline compared with wider machine learning tools that construct static disease profiles. We review the insights they have enabled across multiple neurodegenerative diseases, notably Alzheimer disease, for applications such as determining temporal trajectories of disease biomarkers, testing hypotheses about disease mechanisms and uncovering disease subtypes. We outline key areas for technological development and translation to a broader range of neuroscience and non-neuroscience applications. Finally, we discuss potential pathways and barriers to integrating disease progression models into clinical practice and trial settings.

Symptom-led staging for semantic and non-fluent/agrammatic variants of primary progressive aphasia.

INTRODUCTION: Here we set out to create a symptom-led staging system for the canonical semantic and non-fluent/agrammatic variants of primary progressive aphasia (PPA), which present unique diagnostic and management challenges not well captured by functional scales developed for Alzheimer's disease and other dementias. METHODS: An international PPA caregiver cohort was surveyed on symptom development under six provisional clinical stages and feedback was analyzed using a mixed-methods sequential explanatory design. RESULTS: Both PPA syndromes were characterized by initial communication dysfunction and non-verbal behavioral changes, with increasing syndromic convergence and functional dependency at later stages. Milestone symptoms were distilled to create a prototypical progression and severity scale of functional impairment: the PPA Progression Planning Aid ("PPA-Squared"). DISCUSSION: This work introduces a symptom-led staging scheme and functional scale for semantic and non-fluent/agrammatic variants of PPA. Our findings have implications for diagnostic and care pathway guidelines, trial design, and personalized prognosis and treatment for PPA. HIGHLIGHTS: We introduce new symptom-led perspectives on primary progressive aphasia (PPA). The focus is on non-fluent/agrammatic (nfvPPA) and semantic (svPPA) variants. Foregrounding of early and non-verbal features of PPA and clinical trajectories is featured. We introduce a symptom-led staging scheme for PPA. We propose a prototype for a functional impairment scale, the PPA Progression Planning Aid.

The temporal event-based model: Learning event timelines in progressive diseases.

Timelines of events, such as symptom appearance or a change in biomarker value, provide powerful signatures that characterise progressive diseases. Understanding and predicting the timing of events is important for clinical trials targeting individuals early in the disease course when putative treatments are likely to have the strongest effect. However, previous models of disease progression cannot estimate the time between events and provide only an ordering in which they change. Here, we introduce the temporal event-based model (TEBM), a new probabilistic model for inferring timelines of biomarker events from sparse and irregularly sampled datasets. We demonstrate the power of the TEBM in two neurodegenerative conditions: Alzheimer's disease (AD) and Huntington's disease (HD). In both diseases, the TEBM not only recapitulates current understanding of event orderings but also provides unique new ranges of timescales between consecutive events. We reproduce and validate these findings using external datasets in both diseases. We also demonstrate that the TEBM improves over current models; provides unique stratification capabilities; and enriches simulated clinical trials to achieve a power of 80% with less than half the cohort size compared with random selection. The application of the TEBM naturally extends to a wide range of progressive conditions.

Artificial intelligence for dementia drug discovery and trials optimization.

Drug discovery and clinical trial design for dementia have historically been challenging. In part these challenges have arisen from patient heterogeneity, length of disease course, and the tractability of a target for the brain. Applying big data analytics and machine learning tools for drug discovery and utilizing them to inform successful clinical trial design has the potential to accelerate progress. Opportunities arise at multiple stages in the therapy pipeline and the growing availability of large medical data sets opens possibilities for big data analyses to answer key questions in clinical and therapeutic challenges. However, before this goal is reached, several challenges need to be overcome and only a multi-disciplinary approach can promote data-driven decision-making to its full potential. Herein we review the current state of machine learning applications to clinical trial design and drug discovery, while presenting opportunities and recommendations that can break down the barriers to implementation.

A data-driven study of Alzheimer's disease related amyloid and tau pathology progression.

Amyloid-ß is thought to facilitate the spread of tau throughout the neocortex in Alzheimer's disease, though how this occurs is not well understood. This is because of the spatial discordance between amyloid-ß, which accumulates in the neocortex, and tau, which accumulates in the medial temporal lobe during ageing. There is evidence that in some cases amyloid-ß-independent tau spreads beyond the medial temporal lobe where it may interact with neocortical amyloid-ß. This suggests that there may be multiple distinct spatiotemporal subtypes of Alzheimer's-related protein aggregation, with potentially different demographic and genetic risk profiles. We investigated this hypothesis, applying data-driven disease progression subtyping models to post-mortem neuropathology and in vivo PET-based measures from two large observational studies: the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Religious Orders Study and Rush Memory and Aging Project (ROSMAP). We consistently identified 'amyloid-first' and 'tau-first' subtypes using cross-sectional information from both studies. In the amyloid-first subtype, extensive neocortical amyloid-ß precedes the spread of tau beyond the medial temporal lobe, while in the tau-first subtype, mild tau accumulates in medial temporal and neocortical areas prior to interacting with amyloid-ß. As expected, we found a higher prevalence of the amyloid-first subtype among apolipoprotein E (APOE) ε4 allele carriers while the tau-first subtype was more common among APOE ε4 non-carriers. Within tau-first APOE ε4 carriers, we found an increased rate of amyloid-ß accumulation (via longitudinal amyloid PET), suggesting that this rare group may belong within the Alzheimer's disease continuum. We also found that tau-first APOE ε4 carriers had several fewer years of education than other groups, suggesting a role for modifiable risk factors in facilitating amyloid-ß-independent tau. Tau-first APOE ε4 non-carriers, in contrast, recapitulated many of the features of primary age-related tauopathy. The rate of longitudinal amyloid-ß and tau accumulation (both measured via PET) within this group did not differ from normal ageing, supporting the distinction of primary age-related tauopathy from Alzheimer's disease. We also found reduced longitudinal subtype consistency within tau-first APOE ε4 non-carriers, suggesting additional heterogeneity within this group. Our findings support the idea that amyloid-ß and tau may begin as independent processes in spatially disconnected regions, with widespread neocortical tau resulting from the local interaction of amyloid-ß and tau. The site of this interaction may be subtype-dependent: medial temporal lobe in amyloid-first, neocortex in tau-first. These insights into the dynamics of amyloid-ß and tau may inform research and clinical trials that target these pathologies.

MisMatch: Calibrated Segmentation via Consistency on Differential Morphological Feature Perturbations With Limited Labels.

Semi-supervised learning (SSL) is a promising machine learning paradigm to address the ubiquitous issue of label scarcity in medical imaging. The state-of-the-art SSL methods in image classification utilise consistency regularisation to learn unlabelled predictions which are invariant to input level perturbations. However, image level perturbations violate the cluster assumption in the setting of segmentation. Moreover, existing image level perturbations are hand-crafted which could be sub-optimal. In this paper, we propose MisMatch, a semi-supervised segmentation framework based on the consistency between paired predictions which are derived from two differently learnt morphological feature perturbations. MisMatch consists of an encoder and two decoders. One decoder learns positive attention for foreground on unlabelled data thereby generating dilated features of foreground. The other decoder learns negative attention for foreground on the same unlabelled data thereby generating eroded features of foreground. We normalise the paired predictions of the decoders, along the batch dimension. A consistency regularisation is then applied between the normalised paired predictions of the decoders. We evaluate MisMatch on four different tasks. Firstly, we develop a 2D U-net based MisMatch framework and perform extensive cross-validation on a CT-based pulmonary vessel segmentation task and show that MisMatch statistically outperforms state-of-the-art semi-supervised methods. Secondly, we show that 2D MisMatch outperforms state-of-the-art methods on an MRI-based brain tumour segmentation task. We then further confirm that 3D V-net based MisMatch outperforms its 3D counterpart based on consistency regularisation with input level perturbations, on two different tasks including, left atrium segmentation from 3D CT images and whole brain tumour segmentation from 3D MRI images. Lastly, we find that the performance improvement of MisMatch over the baseline might originate from its better calibration. This also implies that our proposed AI system makes safer decisions than the previous methods.

Transferability of Alzheimer's disease progression subtypes to an independent population cohort.

In the past, methods to subtype or biotype patients using brain imaging data have been developed. However, it is unclear whether and how these trained machine learning models can be successfully applied to population cohorts to study the genetic and lifestyle factors underpinning these subtypes. This work, using the Subtype and Stage Inference (SuStaIn) algorithm, examines the generalisability of data-driven Alzheimer's disease (AD) progression models. We first compared SuStaIn models trained separately on Alzheimer's disease neuroimaging initiative (ADNI) data and an AD-at-risk population constructed from the UK Biobank dataset. We further applied data harmonization techniques to remove cohort effects. Next, we built SuStaIn models on the harmonized datasets, which were then used to subtype and stage subjects in the other harmonized dataset. The first key finding is that three consistent atrophy subtypes were found in both datasets, which match the previously identified subtype progression patterns in AD: 'typical', 'cortical' and 'subcortical'. Next, the subtype agreement was further supported by high consistency in individuals' subtypes and stage assignment based on the different models: more than 92% of the subjects, with reliable subtype assignment in both ADNI and UK Biobank dataset, were assigned to an identical subtype under the model built on the different datasets. The successful transferability of AD atrophy progression subtypes across cohorts capturing different phases of disease development enabled further investigations of associations between AD atrophy subtypes and risk factors. Our study showed that (1) the average age is highest in the typical subtype and lowest in the subcortical subtype; (2) the typical subtype is associated with statistically more-AD-like cerebrospinal fluid biomarkers values in comparison to the other two subtypes; and (3) in comparison to the subcortical subtype, the cortical subtype subjects are more likely to associate with prescription of cholesterol and high blood pressure medications. In summary, we presented cross-cohort consistent recovery of AD atrophy subtypes, showing how the same subtypes arise even in cohorts capturing substantially different disease phases. Our study opened opportunities for future detailed investigations of atrophy subtypes with a broad range of early risk factors, which will potentially lead to a better understanding of the disease aetiology and the role of lifestyle and behaviour on AD.

Symptom-led staging for primary progressive aphasia.

The primary progressive aphasias (PPA) present complex and diverse challenges of diagnosis, management and prognosis. A clinically-informed, syndromic staging system for PPA would take a substantial step toward meeting these challenges. This study addressed this need using detailed, multi-domain mixed-methods symptom surveys of people with lived experience in a large international PPA cohort. We administered structured online surveys to caregivers of patients with a canonical PPA syndromic variant (nonfluent/agrammatic (nvPPA), semantic (svPPA) or logopenic (lvPPA)). In an 'exploratory' survey, a putative list and ordering of verbal communication and nonverbal functioning (nonverbal thinking, conduct and wellbeing, physical) symptoms was administered to 118 caregiver members of the UK national PPA Support Group. Based on feedback, we expanded the symptom list and created six provisional clinical stages for each PPA subtype. In a 'consolidation' survey, these stages were presented to 110 caregiver members of UK and Australian PPA Support Groups, and refined based on quantitative and qualitative feedback. Symptoms were retained if rated as 'present' by a majority (at least 50%) of respondents representing that PPA syndrome, and assigned to a consolidated stage based on majority consensus; the confidence of assignment was estimated for each symptom as the proportion of respondents in agreement with the final staging for that symptom. Qualitative responses were analysed using framework analysis. For each PPA syndrome, six stages ranging from 1 ('Very mild') to 6 ('Profound') were identified; earliest stages were distinguished by syndromic hallmark symptoms of communication dysfunction, with increasing trans-syndromic convergence and dependency for basic activities of daily living at later stages. Spelling errors, hearing changes and nonverbal behavioural features were reported at early stages in all syndromes. As the illness evolved, swallowing and mobility problems were reported earlier in nfvPPA than other syndromes, while difficulty recognising familiar people and household items characterised svPPA and visuospatial symptoms were more prominent in lvPPA. Overall confidence of symptom staging was higher for svPPA than other syndromes. Across syndromes, functional milestones were identified as key deficits that predict the sequence of major daily life impacts and associated management needs. Qualitatively, we identified five major themes encompassing 15 subthemes capturing respondents' experiences of PPA and suggestions for staging implementation. This work introduces a prototypical, symptom-led staging scheme for canonical PPA syndromes: the PPA Progression Planning Aid (PPA 2 ). Our findings have implications for diagnostic and care pathway guidelines, trial design and personalised prognosis and treatment for people living with these diseases.

Heterogeneity in Preclinical Alzheimer's Disease Trial Cohort Identified by Image-based Data-Driven Disease Progression Modelling.

Importance: Undetected biological heterogeneity adversely impacts trials in Alzheimer's disease because rate of cognitive decline - and perhaps response to treatment - differs in subgroups. Recent results show that data-driven approaches can unravel the heterogeneity of Alzheimer's disease progression. The resulting stratification is yet to be leveraged in clinical trials. Objective: Investigate whether image-based data-driven disease progression modelling could identify baseline biological heterogeneity in a clinical trial, and whether these subgroups have prognostic or predictive value. Design: Screening data from the Anti-Amyloid Treatment in Asymptomatic Alzheimer Disease (A4) Study collected between April 2014 and December 2017, and longitudinal data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) observational study downloaded in February 2022 were used. Setting: The A4 Study is an interventional trial involving 67 sites in the US, Canada, Australia, and Japan. ADNI is a multi-center observational study in North America. Participants: Cognitively unimpaired amyloid-positive participants with a 3-Tesla T1-weighted MRI scan. Amyloid positivity was determined using florbetapir PET imaging (in A4) and CSF Aß(1-42) (in ADNI). Main Outcomes and Measures: Regional volumes estimated from MRI scans were used as input to the Subtype and Stage Inference (SuStaIn) algorithm. Outcomes included cognitive test scores and SUVr values from florbetapir and flortaucipir PET. Results: We included 1,240 Aß+ participants (and 407 Aß- controls) from the A4 Study, and 731 A4-eligible ADNI participants. SuStaIn identified three neurodegeneration subtypes - Typical, Cortical, Subcortical - comprising 523 (42%) individuals. The remainder are designated subtype zero (insufficient atrophy). Baseline PACC scores (A4 primary outcome) were significantly worse in the Cortical subtype (median = -1.27, IQR=[-3.34,0.83]) relative to both subtype zero (median=-0.013, IQR=[-1.85,1.67], P<.0001) and the Subcortical subtype (median=0.03, IQR=[-1.78,1.61], P=.0006). In ADNI, over a four-year period (comparable to A4), greater cognitive decline in the mPACC was observed in both the Typical (-0.23/yr; 95% CI, [-0.41,-0.05]; P=.01) and Cortical (-0.24/yr; [-0.42,-0.06]; P=.009) subtypes, as well as the CDR-SB (Typical: +0.09/yr, [0.06,0.12], P<.0001; and Cortical: +0.07/yr, [0.04,0.10], P<.0001). Conclusions and Relevance: In a large secondary prevention trial, our image-based model detected neurodegenerative heterogeneity predictive of cognitive heterogeneity. We argue that such a model is a valuable tool to be considered in future trial design to control for previously undetected variance.

Harnessing the potential of machine learning and artificial intelligence for dementia research.

Progress in dementia research has been limited, with substantial gaps in our knowledge of targets for prevention, mechanisms for disease progression, and disease-modifying treatments. The growing availability of multimodal data sets opens possibilities for the application of machine learning and artificial intelligence (AI) to help answer key questions in the field. We provide an overview of the state of the science, highlighting current challenges and opportunities for utilisation of AI approaches to move the field forward in the areas of genetics, experimental medicine, drug discovery and trials optimisation, imaging, and prevention. Machine learning methods can enhance results of genetic studies, help determine biological effects and facilitate the identification of drug targets based on genetic and transcriptomic information. The use of unsupervised learning for understanding disease mechanisms for drug discovery is promising, while analysis of multimodal data sets to characterise and quantify disease severity and subtype are also beginning to contribute to optimisation of clinical trial recruitment. Data-driven experimental medicine is needed to analyse data across modalities and develop novel algorithms to translate insights from animal models to human disease biology. AI methods in neuroimaging outperform traditional approaches for diagnostic classification, and although challenges around validation and translation remain, there is optimism for their meaningful integration to clinical practice in the near future. AI-based models can also clarify our understanding of the causality and commonality of dementia risk factors, informing and improving risk prediction models along with the development of preventative interventions. The complexity and heterogeneity of dementia requires an alternative approach beyond traditional design and analytical approaches. Although not yet widely used in dementia research, machine learning and AI have the potential to unlock current challenges and advance precision dementia medicine.

Neurodegenerative disease of the brain: a survey of interdisciplinary approaches.

Neurodegenerative diseases of the brain pose a major and increasing global health challenge, with only limited progress made in developing effective therapies over the last decade. Interdisciplinary research is improving understanding of these diseases and this article reviews such approaches, with particular emphasis on tools and techniques drawn from physics, chemistry, artificial intelligence and psychology.

Event-based modeling in temporal lobe epilepsy demonstrates progressive atrophy from cross-sectional data.

OBJECTIVE: Recent work has shown that people with common epilepsies have characteristic patterns of cortical thinning, and that these changes may be progressive over time. Leveraging a large multicenter cross-sectional cohort, we investigated whether regional morphometric changes occur in a sequential manner, and whether these changes in people with mesial temporal lobe epilepsy and hippocampal sclerosis (MTLE-HS) correlate with clinical features. METHODS: We extracted regional measures of cortical thickness, surface area, and subcortical brain volumes from T1-weighted (T1W) magnetic resonance imaging (MRI) scans collected by the ENIGMA-Epilepsy consortium, comprising 804 people with MTLE-HS and 1625 healthy controls from 25 centers. Features with a moderate case-control effect size (Cohen d ≥ .5) were used to train an event-based model (EBM), which estimates a sequence of disease-specific biomarker changes from cross-sectional data and assigns a biomarker-based fine-grained disease stage to individual patients. We tested for associations between EBM disease stage and duration of epilepsy, age at onset, and antiseizure medicine (ASM) resistance. RESULTS: In MTLE-HS, decrease in ipsilateral hippocampal volume along with increased asymmetry in hippocampal volume was followed by reduced thickness in neocortical regions, reduction in ipsilateral thalamus volume, and finally, increase in ipsilateral lateral ventricle volume. EBM stage was correlated with duration of illness (Spearman ρ = .293, p = 7.03 × 10-16 ), age at onset (ρ = -.18, p = 9.82 × 10-7 ), and ASM resistance (area under the curve = .59, p = .043, Mann-Whitney U test). However, associations were driven by cases assigned to EBM Stage 0, which represents MTLE-HS with mild or nondetectable abnormality on T1W MRI. SIGNIFICANCE: From cross-sectional MRI, we reconstructed a disease progression model that highlights a sequence of MRI changes that aligns with previous longitudinal studies. This model could be used to stage MTLE-HS subjects in other cohorts and help establish connections between imaging-based progression staging and clinical features.

Targeted Screening for Alzheimer's Disease Clinical Trials Using Data-Driven Disease Progression Models.

Heterogeneity in Alzheimer's disease progression contributes to the ongoing failure to demonstrate efficacy of putative disease-modifying therapeutics that have been trialed over the past two decades. Any treatment effect present in a subgroup of trial participants (responders) can be diluted by non-responders who ideally should have been screened out of the trial. How to identify (screen-in) the most likely potential responders is an important question that is still without an answer. Here, we pilot a computational screening tool that leverages recent advances in data-driven disease progression modeling to improve stratification. This aims to increase the sensitivity to treatment effect by screening out non-responders, which will ultimately reduce the size, duration, and cost of a clinical trial. We demonstrate the concept of such a computational screening tool by retrospectively analyzing a completed double-blind clinical trial of donepezil in people with amnestic mild cognitive impairment (clinicaltrials.gov: NCT00000173), identifying a data-driven subgroup having more severe cognitive impairment who showed clearer treatment response than observed for the full cohort.

Comparison and aggregation of event sequences across ten cohorts to describe the consensus biomarker evolution in Alzheimer's disease.

BACKGROUND: Previous models of Alzheimer's disease (AD) progression were primarily hypothetical or based on data originating from single cohort studies. However, cohort datasets are subject to specific inclusion and exclusion criteria that influence the signals observed in their collected data. Furthermore, each study measures only a subset of AD-relevant variables. To gain a comprehensive understanding of AD progression, the heterogeneity and robustness of estimated progression patterns must be understood, and complementary information contained in cohort datasets be leveraged. METHODS: We compared ten event-based models that we fit to ten independent AD cohort datasets. Additionally, we designed and applied a novel rank aggregation algorithm that combines partially overlapping, individual event sequences into a meta-sequence containing the complementary information from each cohort. RESULTS: We observed overall consistency across the ten event-based model sequences (average pairwise Kendall's tau correlation coefficient of 0.69 ± 0.28), despite variance in the positioning of mainly imaging variables. The changes described in the aggregated meta-sequence are broadly consistent with the current understanding of AD progression, starting with cerebrospinal fluid amyloid beta, followed by tauopathy, memory impairment, FDG-PET, and ultimately brain deterioration and impairment of visual memory. CONCLUSION: Overall, the event-based models demonstrated similar and robust disease cascades across independent AD cohorts. Aggregation of data-driven results can combine complementary strengths and information of patient-level datasets. Accordingly, the derived meta-sequence draws a more complete picture of AD pathology compared to models relying on single cohorts.

Ten years of image analysis and machine learning competitions in dementia.

Machine learning methods exploiting multi-parametric biomarkers, especially based on neuroimaging, have huge potential to improve early diagnosis of dementia and to predict which individuals are at-risk of developing dementia. To benchmark algorithms in the field of machine learning and neuroimaging in dementia and assess their potential for use in clinical practice and clinical trials, seven grand challenges have been organized in the last decade: MIRIAD (2012), Alzheimer's Disease Big Data DREAM (2014), CADDementia (2014), Machine Learning Challenge (2014), MCI Neuroimaging (2017), TADPOLE (2017), and the Predictive Analytics Competition (2019). Based on two challenge evaluation frameworks, we analyzed how these grand challenges are complementing each other regarding research questions, datasets, validation approaches, results and impact. The seven grand challenges addressed questions related to screening, clinical status estimation, prediction and monitoring in (pre-clinical) dementia. There was little overlap in clinical questions, tasks and performance metrics. Whereas this aids providing insight on a broad range of questions, it also limits the validation of results across challenges. The validation process itself was mostly comparable between challenges, using similar methods for ensuring objective comparison, uncertainty estimation and statistical testing. In general, winning algorithms performed rigorous data pre-processing and combined a wide range of input features. Despite high state-of-the-art performances, most of the methods evaluated by the challenges are not clinically used. To increase impact, future challenges could pay more attention to statistical analysis of which factors (i.e., features, models) relate to higher performance, to clinical questions beyond Alzheimer's disease, and to using testing data beyond the Alzheimer's Disease Neuroimaging Initiative. Grand challenges would be an ideal venue for assessing the generalizability of algorithm performance to unseen data of other cohorts. Key for increasing impact in this way are larger testing data sizes, which could be reached by sharing algorithms rather than data to exploit data that cannot be shared. Given the potential and lessons learned in the past ten years, we are excited by the prospects of grand challenges in machine learning and neuroimaging for the next ten years and beyond.

Degenerative adversarial neuroimage nets for brain scan simulations: Application in ageing and dementia.

Accurate and realistic simulation of high-dimensional medical images has become an important research area relevant to many AI-enabled healthcare applications. However, current state-of-the-art approaches lack the ability to produce satisfactory high-resolution and accurate subject-specific images. In this work, we present a deep learning framework, namely 4D-Degenerative Adversarial NeuroImage Net (4D-DANI-Net), to generate high-resolution, longitudinal MRI scans that mimic subject-specific neurodegeneration in ageing and dementia. 4D-DANI-Net is a modular framework based on adversarial training and a set of novel spatiotemporal, biologically-informed constraints. To ensure efficient training and overcome memory limitations affecting such high-dimensional problems, we rely on three key technological advances: i) a new 3D training consistency mechanism called Profile Weight Functions (PWFs), ii) a 3D super-resolution module and iii) a transfer learning strategy to fine-tune the system for a given individual. To evaluate our approach, we trained the framework on 9852 T1-weighted MRI scans from 876 participants in the Alzheimer's Disease Neuroimaging Initiative dataset and held out a separate test set of 1283 MRI scans from 170 participants for quantitative and qualitative assessment of the personalised time series of synthetic images. We performed three evaluations: i) image quality assessment; ii) quantifying the accuracy of regional brain volumes over and above benchmark models; and iii) quantifying visual perception of the synthetic images by medical experts. Overall, both quantitative and qualitative results show that 4D-DANI-Net produces realistic, low-artefact, personalised time series of synthetic T1 MRI that outperforms benchmark models.