A parameter-efficient deep learning approach to predict conversion from mild cognitive impairment to Alzheimer's disease.

Some forms of mild cognitive impairment (MCI) are the clinical precursors of Alzheimer's disease (AD), while other MCI types tend to remain stable over-time and do not progress to AD. To identify and choose effective and personalized strategies to prevent or slow the progression of AD, we need to develop objective measures that are able to discriminate the MCI patients who are at risk of AD from those MCI patients who have less risk to develop AD. Here, we present a novel deep learning architecture, based on dual learning and an ad hoc layer for 3D separable convolutions, which aims at identifying MCI patients who have a high likelihood of developing AD within 3 years. Our deep learning procedures combine structural magnetic resonance imaging (MRI), demographic, neuropsychological, and APOe4 genetic data as input measures. The most novel characteristics of our machine learning model compared to previous ones are the following: 1) our deep learning model is multi-tasking, in the sense that it jointly learns to simultaneously predict both MCI to AD conversion as well as AD vs. healthy controls classification, which facilitates relevant feature extraction for AD prognostication; 2) the neural network classifier employs fewer parameters than other deep learning architectures which significantly limits data-overfitting (we use ∼550,000 network parameters, which is orders of magnitude lower than other network designs); 3) both structural MRI images and their warp field characteristics, which quantify local volumetric changes in relation to the MRI template, were used as separate input streams to extract as much information as possible from the MRI data. All analyses were performed on a subset of the database made publicly available via the Alzheimer's Disease Neuroimaging Initiative (ADNI), (n = 785 participants, n = 192 AD patients, n = 409 MCI patients (including both MCI patients who convert to AD and MCI patients who do not covert to AD), and n = 184 healthy controls). The most predictive combination of inputs were the structural MRI images and the demographic, neuropsychological, and APOe4 data. In contrast, the warp field metrics were of little added predictive value. The algorithm was able to distinguish the MCI patients developing AD within 3 years from those patients with stable MCI over the same time-period with an area under the curve (AUC) of 0.925 and a 10-fold cross-validated accuracy of 86%, a sensitivity of 87.5%, and specificity of 85%. To our knowledge, this is the highest performance achieved so far using similar datasets. The same network provided an AUC of 1 and 100% accuracy, sensitivity, and specificity when classifying patients with AD from healthy controls. Our classification framework was also robust to the use of different co-registration templates and potentially irrelevant features/image portions. Our approach is flexible and can in principle integrate other imaging modalities, such as PET, and diverse other sets of clinical data. The convolutional framework is potentially applicable to any 3D image dataset and gives the flexibility to design a computer-aided diagnosis system targeting the prediction of several medical conditions and neuropsychiatric disorders via multi-modal imaging and tabular clinical data.

Early downregulation of hsa-miR-144-3p in serum from drug-naïve Parkinson's disease patients.

Advanced age represents one of the major risk factors for Parkinson's Disease. Recent biomedical studies posit a role for microRNAs, also known to be remodelled during ageing. However, the relationship between microRNA remodelling and ageing in Parkinson's Disease, has not been fully elucidated. Therefore, the aim of the present study is to unravel the relevance of microRNAs as biomarkers of Parkinson's Disease within the ageing framework. We employed Next Generation Sequencing to profile serum microRNAs from samples informative for Parkinson's Disease (recently diagnosed, drug-naïve) and healthy ageing (centenarians) plus healthy controls, age-matched with Parkinson's Disease patients. Potential microRNA candidates markers, emerging from the combination of differential expression and network analyses, were further validated in an independent cohort including both drug-naïve and advanced Parkinson's Disease patients, and healthy siblings of Parkinson's Disease patients at higher genetic risk for developing the disease. While we did not find evidences of microRNAs co-regulated in Parkinson's Disease and ageing, we report that hsa-miR-144-3p is consistently down-regulated in early Parkinson's Disease patients. Moreover, interestingly, functional analysis revealed that hsa-miR-144-3p is involved in the regulation of coagulation, a process known to be altered in Parkinson's Disease. Our results consistently show the down-regulation of hsa-mir144-3p in early Parkinson's Disease, robustly confirmed across a variety of analytical and experimental analyses. These promising results ask for further research to unveil the functional details of the involvement of hsa-mir144-3p in Parkinson's Disease.

A geroscience approach for Parkinson's disease: Conceptual framework and design of PROPAG-AGEING project.

Advanced age is the major risk factor for idiopathic Parkinson's disease (PD), but to date the biological relationship between PD and ageing remains elusive. Here we describe the rationale and the design of the H2020 funded project "PROPAG-AGEING", whose aim is to characterize the contribution of the ageing process to PD development. We summarize current evidences that support the existence of a continuum between ageing and PD and justify the use of a Geroscience approach to study PD. We focus in particular on the role of inflammaging, the chronic, low-grade inflammation characteristic of elderly physiology, which can propagate and transmit both locally and systemically. We then describe PROPAG-AGEING design, which is based on the multi-omic characterization of peripheral samples from clinically characterized drug-naïve and advanced PD, PD discordant twins, healthy controls and "super-controls", i.e. centenarians, who never showed clinical signs of motor disability, and their offspring. Omic results are then validated in a large number of samples, including in vitro models of dopaminergic neurons and healthy siblings of PD patients, who are at higher risk of developing PD, with the final aim of identifying the molecular perturbations that can deviate the trajectories of healthy ageing towards PD development.

Unsupervised stratification in neuroimaging through deep latent embeddings.

There is growing evidence that the use of stringent and dichotomic diagnostic categories in many medical disciplines (particularly 'brain sciences' as neurology and psychiatry) is an oversimplification. Although clear diagnostic boundaries remain useful for patients, families, and their access to dedicated NHS and health care services, the traditional dichotomic categories are not helpful to describe the complexity and large heterogeneity of symptoms across many and overlapping clinical phenotypes. With the advent of 'big' multimodal neuroimaging databases, data-driven stratification of the wide spectrum of healthy human physiology or disease based on neuroimages is theoretically become possible. However, this conceptual framework is hampered by severe computational constraints. In this paper we present a novel, deep learning based encode-decode architecture which leverages several parameter efficiency techniques generate latent deep embedding which compress the information contained in a full 3D neuroimaging volume by a factor 1000 while still retaining anatomical detail and hence rendering the subsequent stratification problem tractable. We train our architecture on 1003 brain scan derived from the human connectome project and demonstrate the faithfulness of the obtained reconstructions. Further, we employ a data driven clustering technique driven by a grid search in hyperparameter space to identify six different strata within the 1003 healthy community dwelling individuals which turn out to correspond to highly significant group differences in both physiological and cognitive data. Indicating that the well-known relationships between such variables and brain structure can be probed in an unsupervised manner through our novel architecture and pipeline. This opens the door to a variety of previously inaccessible applications in the realm of data driven stratification of large cohorts based on neuroimaging data.Clinical Relevance -With our approach, each person can be described and classified within a multi-dimensional space of data, where they are uniquely classified according to their individual anatomy, physiology and disease-related anatomical and physiological alterations.

Integration of Machine Learning Methods to Dissect Genetically Imputed Transcriptomic Profiles in Alzheimer's Disease.

The genetic component of many common traits is associated with the gene expression and several variants act as expression quantitative loci, regulating the gene expression in a tissue specific manner. In this work, we applied tissue-specific cis-eQTL gene expression prediction models on the genotype of 808 samples including controls, subjects with mild cognitive impairment, and patients with Alzheimer's Disease. We then dissected the imputed transcriptomic profiles by means of different unsupervised and supervised machine learning approaches to identify potential biological associations. Our analysis suggests that unsupervised and supervised methods can provide complementary information, which can be integrated for a better characterization of the underlying biological system. In particular, a variational autoencoder representation of the transcriptomic profiles, followed by a support vector machine classification, has been used for tissue-specific gene prioritizations. Interestingly, the achieved gene prioritizations can be efficiently integrated as a feature selection step for improving the accuracy of deep learning classifier networks. The identified gene-tissue information suggests a potential role for inflammatory and regulatory processes in gut-brain axis related tissues. In line with the expected low heritability that can be apportioned to eQTL variants, we were able to achieve only relatively low prediction capability with deep learning classification models. However, our analysis revealed that the classification power strongly depends on the network structure, with recurrent neural networks being the best performing network class. Interestingly, cross-tissue analysis suggests a potentially greater role of models trained in brain tissues also by considering dementia-related endophenotypes. Overall, the present analysis suggests that the combination of supervised and unsupervised machine learning techniques can be used for the evaluation of high dimensional omics data.

OptiJ: Open-source optical projection tomography of large organ samples.

The three-dimensional imaging of mesoscopic samples with Optical Projection Tomography (OPT) has become a powerful tool for biomedical phenotyping studies. OPT uses visible light to visualize the 3D morphology of large transparent samples. To enable a wider application of OPT, we present OptiJ, a low-cost, fully open-source OPT system capable of imaging large transparent specimens up to 13 mm tall and 8 mm deep with 50 µm resolution. OptiJ is based on off-the-shelf, easy-to-assemble optical components and an ImageJ plugin library for OPT data reconstruction. The software includes novel correction routines for uneven illumination and sample jitter in addition to CPU/GPU accelerated reconstruction for large datasets. We demonstrate the use of OptiJ to image and reconstruct cleared lung lobes from adult mice. We provide a detailed set of instructions to set up and use the OptiJ framework. Our hardware and software design are modular and easy to implement, allowing for further open microscopy developments for imaging large organ samples.

A Multi-modal Convolutional Neural Network Framework for the Prediction of Alzheimer's Disease.

This paper presents a multi-modal Alzheimer's disease (AD) classification framework based on a convolutional neural network (CNN) architecture. The devised model takes structural MRI, and clinical assessment and genetic (APOe4) measures as inputs. Our CNN structure is designed to be efficient in its use of parameters which reduces overfitting, computational complexity, memory requirements and speed of prototyping. This is achieved by factorising the convolutional layers in parallel streams which also enables the simultaneous extraction of high and low level feature representations. Our method consistently achieves high classification results in discriminating between AD and control subjects with an average of 99% accuracy, 98% sensitivity, 100% specificity and an AUC of 1 across all test folds. Our study confirms that careful tuning of CNN characteristics can result in a framework which delivers extremely accurate predictions in a clinical problem despite data paucity, opening new avenues for application to prediction tasks which regard patient stratification, prediction of clinical evolution and eventually personalised medicine applications.