Bridging Imaging and Clinical Scores in Parkinson's Progression via Multimodal Self-Supervised Deep Learning.

Neurodegenerative diseases pose a formidable challenge to medical research, demanding a nuanced understanding of their progressive nature. In this regard, latent generative models can effectively be used in a data-driven modeling of different dimensions of neurodegeneration, framed within the context of the manifold hypothesis. This paper proposes a joint framework for a multi-modal, common latent generative model to address the need for a more comprehensive understanding of the neurodegenerative landscape in the context of Parkinson's disease (PD). The proposed architecture uses coupled variational autoencoders (VAEs) to joint model a common latent space to both neuroimaging and clinical data from the Parkinson's Progression Markers Initiative (PPMI). Alternative loss functions, different normalization procedures, and the interpretability and explainability of latent generative models are addressed, leading to a model that was able to predict clinical symptomatology in the test set, as measured by the unified Parkinson's disease rating scale (UPDRS), with R2 up to 0.86 for same-modality and 0.441 cross-modality (using solely neuroimaging). The findings provide a foundation for further advancements in the field of clinical research and practice, with potential applications in decision-making processes for PD. The study also highlights the limitations and capabilities of the proposed model, emphasizing its direct interpretability and potential impact on understanding and interpreting neuroimaging patterns associated with PD symptomatology.

Autosomal Dominantly Inherited Alzheimer Disease: Analysis of genetic subgroups by Machine Learning.

Despite subjects with Dominantly-Inherited Alzheimer's Disease (DIAD) represent less than 1% of all Alzheimer's Disease (AD) cases, the Dominantly Inherited Alzheimer Network (DIAN) initiative constitutes a strong impact in the understanding of AD disease course with special emphasis on the presyptomatic disease phase. Until now, the 3 genes involved in DIAD pathogenesis (PSEN1, PSEN2 and APP) have been commonly merged into one group (Mutation Carriers, MC) and studied using conventional statistical analysis. Comparisons between groups using null-hypothesis testing or longitudinal regression procedures, such as the linear-mixed-effects models, have been assessed in the extant literature. Within this context, the work presented here performs a comparison between different groups of subjects by considering the 3 genes, either jointly or separately, and using tools based on Machine Learning (ML). This involves a feature selection step which makes use of ANOVA followed by Principal Component Analysis (PCA) to determine which features would be realiable for further comparison purposes. Then, the selected predictors are classified using a Support-Vector-Machine (SVM) in a nested k-Fold cross-validation resulting in maximum classification rates of 72-74% using PiB PET features, specially when comparing asymptomatic Non-Carriers (NC) subjects with asymptomatic PSEN1 Mutation-Carriers (PSEN1-MC). Results obtained from these experiments led to the idea that PSEN1-MC might be considered as a mixture of two different subgroups including: a first group whose patterns were very close to NC subjects, and a second group much more different in terms of imaging patterns. Thus, using a k-Means clustering algorithm it was determined both subgroups and a new classification scenario was conducted to validate this process. The comparison between each subgroup vs. NC subjects resulted in classification rates around 80% underscoring the importance of considering DIAN as an heterogeneous entity.

Assisted Diagnosis of Parkinsonism Based on the Striatal Morphology.

Parkinsonism is a clinical syndrome characterized by the progressive loss of striatal dopamine. Its diagnosis is usually corroborated by neuroimaging data such as DaTSCAN neuroimages that allow visualizing the possible dopamine deficiency. During the last decade, a number of computer systems have been proposed to automatically analyze DaTSCAN neuroimages, eliminating the subjectivity inherent to the visual examination of the data. In this work, we propose a computer system based on machine learning to separate Parkinsonian patients and control subjects using the size and shape of the striatal region, modeled from DaTSCAN data. First, an algorithm based on adaptative thresholding is used to parcel the striatum. This region is then divided into two according to the brain hemisphere division and characterized with 152 measures, extracted from the volume and its three possible 2-dimensional projections. Afterwards, the Bhattacharyya distance is used to discard the least discriminative measures and, finally, the neuroimage category is estimated by means of a Support Vector Machine classifier. This method was evaluated using a dataset with 189 DaTSCAN neuroimages, obtaining an accuracy rate over 94%. This rate outperforms those obtained by previous approaches that use the intensity of each striatal voxel as a feature.

Usefulness of Dual-Point Amyloid PET Scans in Appropriate Use Criteria: A Multicenter Study.

BACKGROUND: Biomarkers of neurodegeneration play a major role in the diagnosis of Alzheimer's disease (AD). Information on both amyloid-ß accumulation, e.g., from amyloid positron emission tomography (PET), and downstream neuronal injury, e.g., from 18F-fluorodeoxyglucose (FDG) PET, would ideally be obtained in a single procedure. OBJECTIVE: On the basis that the parallelism between brain perfusion and glucose metabolism is well documented, the objective of this work is to evaluate whether brain perfusion estimated in a dual-point protocol of 18F-florbetaben (FBB) PET can be a surrogate of FDG PET in appropriate use criteria (AUC) for amyloid PET. METHODS: This study included 47 patients fulfilling international AUC for amyloid PET. FDG PET, early FBB (pFBB) PET (0-10 min post injection), and standard FBB (sFBB) PET (90-110 min post injection) scans were acquired. Results of clinical subjective reports and of quantitative region of interest (ROI)-based analyses were compared between procedures using statistical techniques such as Pearson's correlation coefficients and t-tests. RESULTS: pFBB and FDG visual reports on the 47 patients showed good agreement (k  >  0.74); ROI quantitative analysis indicated that both data modalities are highly correlated; and the t-test analysis does not reject the null hypothesis that data from pFBB and FDG examinations comes from independent random samples from normal distributions with equal means and variances. CONCLUSIONS: A good agreement was found between pFBB and FDG data as obtained by subjective visual and quantitative analyses. Dual-point FBB PET scans could offer complementary information (similar to that from FDG PET and FBB PET) in a single procedure, considering pFBB as a surrogate of FDG.

Robust Ensemble Classification Methodology for I123-Ioflupane SPECT Images and Multiple Heterogeneous Biomarkers in the Diagnosis of Parkinson's Disease.

In last years, several approaches to develop an effective Computer-Aided-Diagnosis (CAD) system for Parkinson's Disease (PD) have been proposed. Most of these methods have focused almost exclusively on brain images through the use of Machine-Learning algorithms suitable to characterize structural or functional patterns. Those patterns provide enough information about the status and/or the progression at intermediate and advanced stages of Parkinson's Disease. Nevertheless this information could be insufficient at early stages of the pathology. The Parkinson's Progression Markers Initiative (PPMI) database includes neurological images along with multiple biomedical tests. This information opens up the possibility of comparing different biomarker classification results. As data come from heterogeneous sources, it is expected that we could include some of these biomarkers in order to obtain new information about the pathology. Based on that idea, this work presents an Ensemble Classification model with Performance Weighting. This proposal has been tested comparing Healthy Control subjects (HC) vs. patients with PD (considering both PD and SWEDD labeled subjects as the same class). This model combines several Support-Vector-Machine (SVM) with linear kernel classifiers for different biomedical group of tests-including CerebroSpinal Fluid (CSF), RNA, and Serum tests-and pre-processed neuroimages features (Voxels-As-Features and a list of defined Morphological Features) from PPMI database subjects. The proposed methodology makes use of all data sources and selects the most discriminant features (mainly from neuroimages). Using this performance-weighted ensemble classification model, classification results up to 96% were obtained.

Using CT Data to Improve the Quantitative Analysis of 18F-FBB PET Neuroimages.

18F-FBB PET is a neuroimaging modality that is been increasingly used to assess brain amyloid deposits in potential patients with Alzheimer's disease (AD). In this work, we analyze the usefulness of these data to distinguish between AD and non-AD patients. A dataset with 18F-FBB PET brain images from 94 subjects diagnosed with AD and other disorders was evaluated by means of multiple analyses based on t-test, ANOVA, Fisher Discriminant Analysis and Support Vector Machine (SVM) classification. In addition, we propose to calculate amyloid standardized uptake values (SUVs) using only gray-matter voxels, which can be estimated using Computed Tomography (CT) images. This approach allows assessing potential brain amyloid deposits along with the gray matter loss and takes advantage of the structural information provided by most of the scanners used for PET examination, which allow simultaneous PET and CT data acquisition. The results obtained in this work suggest that SUVs calculated according to the proposed method allow AD and non-AD subjects to be more accurately differentiated than using SUVs calculated with standard approaches.

A Heavy Tailed Expectation Maximization Hidden Markov Random Field Model with Applications to Segmentation of MRI.

A wide range of segmentation approaches assumes that intensity histograms extracted from magnetic resonance images (MRI) have a distribution for each brain tissue that can be modeled by a Gaussian distribution or a mixture of them. Nevertheless, intensity histograms of White Matter and Gray Matter are not symmetric and they exhibit heavy tails. In this work, we present a hidden Markov random field model with expectation maximization (EM-HMRF) modeling the components using the α-stable distribution. The proposed model is a generalization of the widely used EM-HMRF algorithm with Gaussian distributions. We test the α-stable EM-HMRF model in synthetic data and brain MRI data. The proposed methodology presents two main advantages: Firstly, it is more robust to outliers. Secondly, we obtain similar results than using Gaussian when the Gaussian assumption holds. This approach is able to model the spatial dependence between neighboring voxels in tomographic brain MRI.

Functional Brain Imaging Synthesis Based on Image Decomposition and Kernel Modeling: Application to Neurodegenerative Diseases.

The rise of neuroimaging in research and clinical practice, together with the development of new machine learning techniques has strongly encouraged the Computer Aided Diagnosis (CAD) of different diseases and disorders. However, these algorithms are often tested in proprietary datasets to which the access is limited and, therefore, a direct comparison between CAD procedures is not possible. Furthermore, the sample size is often small for developing accurate machine learning methods. Multi-center initiatives are currently a very useful, although limited, tool in the recruitment of large populations and standardization of CAD evaluation. Conversely, we propose a brain image synthesis procedure intended to generate a new image set that share characteristics with an original one. Our system focuses on nuclear imaging modalities such as PET or SPECT brain images. We analyze the dataset by applying PCA to the original dataset, and then model the distribution of samples in the projected eigenbrain space using a Probability Density Function (PDF) estimator. Once the model has been built, we can generate new coordinates on the eigenbrain space belonging to the same class, which can be then projected back to the image space. The system has been evaluated on different functional neuroimaging datasets assessing the: resemblance of the synthetic images with the original ones, the differences between them, their generalization ability and the independence of the synthetic dataset with respect to the original. The synthetic images maintain the differences between groups found at the original dataset, with no significant differences when comparing them to real-world samples. Furthermore, they featured a similar performance and generalization capability to that of the original dataset. These results prove that these images are suitable for standardizing the evaluation of CAD pipelines, and providing data augmentation in machine learning systems -e.g. in deep learning-, or even to train future professionals at medical school.

Preprocessing of 18F-DMFP-PET Data Based on Hidden Markov Random Fields and the Gaussian Distribution.

18F-DMFP-PET is an emerging neuroimaging modality used to diagnose Parkinson's disease (PD) that allows us to examine postsynaptic dopamine D2/3 receptors. Like other neuroimaging modalities used for PD diagnosis, most of the total intensity of 18F-DMFP-PET images is concentrated in the striatum. However, other regions can also be useful for diagnostic purposes. An appropriate delimitation of the regions of interest contained in 18F-DMFP-PET data is crucial to improve the automatic diagnosis of PD. In this manuscript we propose a novel methodology to preprocess 18F-DMFP-PET data that improves the accuracy of computer aided diagnosis systems for PD. First, the data were segmented using an algorithm based on Hidden Markov Random Field. As a result, each neuroimage was divided into 4 maps according to the intensity and the neighborhood of the voxels. The maps were then individually normalized so that the shape of their histograms could be modeled by a Gaussian distribution with equal parameters for all the neuroimages. This approach was evaluated using a dataset with neuroimaging data from 87 parkinsonian patients. After these preprocessing steps, a Support Vector Machine classifier was used to separate idiopathic and non-idiopathic PD. Data preprocessed by the proposed method provided higher accuracy results than the ones preprocessed with previous approaches.

Multivariate Analysis of 18F-DMFP PET Data to Assist the Diagnosis of Parkinsonism.

An early and differential diagnosis of parkinsonian syndromes still remains a challenge mainly due to the similarity of their symptoms during the onset of the disease. Recently, 18F-Desmethoxyfallypride (DMFP) has been suggested to increase the diagnostic precision as it is an effective radioligand that allows us to analyze post-synaptic dopamine D2/3 receptors. Nevertheless, the analysis of these data is still poorly covered and its use limited. In order to address this challenge, this paper shows a novel model to automatically distinguish idiopathic parkinsonism from non-idiopathic variants using DMFP data. The proposed method is based on a multiple kernel support vector machine and uses the linear version of this classifier to identify some regions of interest: the olfactory bulb, thalamus, and supplementary motor area. We evaluated the proposed model for both, the binary separation of idiopathic and non-idiopathic parkinsonism and the multigroup separation of parkinsonian variants. These systems achieved accuracy rates higher than 70%, outperforming DaTSCAN neuroimages for this purpose. In addition, a system that combined DaTSCAN and DMFP data was assessed.

Distinguishing Parkinson's disease from atypical parkinsonian syndromes using PET data and a computer system based on support vector machines and Bayesian networks.

Differentiating between Parkinson's disease (PD) and atypical parkinsonian syndromes (APS) is still a challenge, specially at early stages when the patients show similar symptoms. During last years, several computer systems have been proposed in order to improve the diagnosis of PD, but their accuracy is still limited. In this work we demonstrate a full automatic computer system to assist the diagnosis of PD using (18)F-DMFP PET data. First, a few regions of interest are selected by means of a two-sample t-test. The accuracy of the selected regions to separate PD from APS patients is then computed using a support vector machine classifier. The accuracy values are finally used to train a Bayesian network that can be used to predict the class of new unseen data. This methodology was evaluated using a database with 87 neuroimages, achieving accuracy rates over 78%. A fair comparison with other similar approaches is also provided.

Support for distinct subcomponents of spatial working memory: a double dissociation between spatial-simultaneous and spatial-sequential performance in unilateral neglect.

Over the last decade, many studies have demonstrated that visuospatial working memory (VSWM) can be divided into separate subsystems dedicated to the retention of visual patterns and their serial order. Impaired VSWM has been suggested to exacerbate left visual neglect in right-brain-damaged individuals. The aim of this study was to investigate the segregation between spatial-sequential and spatial-simultaneous working memory in individuals with neglect. We demonstrated that patterns of results on these VSWM tasks can be dissociated. Spatial-simultaneous and sequential aspects of VSWM can be selectively impaired in unilateral neglect. Our results support the hypothesis of multiple VSWM subsystems, which should be taken into account to better understand neglect-related deficits.

Projecting MRI brain images for the detection of Alzheimer's Disease.

Recent advances in the process of diagnosis of neurodegenerative diseases, such as Alzheimer's Disease, rely on the use of molecular imaging that allow the interpretation of different metabolic biomarkers in the brain. However these procedures are considered of invasive nature, as they involve the injection of radioactive markers. On the other hand, Magnetic Resonance Imaging (MRI) is perhaps the most widely used and less invasive medical imaging technique, although its ability to detect Alzheimer's Disease has revealed limited. In this paper, a new method that simplifies the process of analysing 3D MRI brain images using a two dimensional projection is proposed. Our system outperforms other methods that use MRI, achieving up to a 86% of accuracy and significantly reducing the computational load. Additionally, it allows the visual analysis and interpretation of the images, which can be of great help in the diagnosis of this and other types of dementia.

Cortical and subcortical contributions to state- and strength-based perceptual judgments.

UNLABELLED: Perceptual judgments can be made on the basis of different kinds of information: state-based access to specific details that differentiate two similar images, or strength-based assessments of relational match/mismatch. We explored state- and strength-based perception in eleven right-hemisphere stroke patients, and examined lesion overlap images to gain insight into the neural underpinnings of these different kinds of perceptual judgments. Patients and healthy controls were presented with pairs of scenes that were either identical or differed in that one scene was slightly expanded or contracted relative to the other. Same/different confidence judgments were used to plot receiver-operating characteristics and estimate the contributions of state- and strength-based perception. The patient group showed a significant and selective impairment of strength-based, but not state-based, perception. This finding was not an artifact of reduced levels of overall performance, because matching perceptual discriminability levels between controls and patients revealed a double dissociation, with higher state-based, and lower strength-based, perception in patients vs. CONTROLS: We then conducted exploratory follow-up analyses on the patient group, based on the observation of substantial individual differences in state-based perception - differences that were masked in analyses based on the group mean. Patients who were relatively spared in state-based perception (but impaired in strength-based perception) had damage that was primarily in temporo-parietal cortical regions. Patients who were relatively impaired in both state- and strength-based perception had overlapping damage in the thalamus, putamen, and adjacent white matter. These patient groups were not different in any other measure, e.g., presence of spatial neglect symptoms, age, education, lesion volume, or time since stroke. These findings shed light on the different roles of right hemisphere regions in high-level perception, suggesting that the thalamus and basal ganglia play a critical role in state- and strength-based perception, whereas temporo-parietal cortical regions are important for intact strength-based perception.

Visual neglect: is there a relationship between impaired spatial working memory and re-cancellation?

In visual search tasks, neglect patients tend to explore and repeatedly re-cancel stimuli on the ipsilesional side, as if they did not realize that they had previously examined the rightward locations favoured by their lateral bias. The aim of this study was to explore the hypothesis that a spatial working memory deficit explains these ipsilesional re-cancellation errors in neglect patients. For the first time, we evaluated spatial working memory and re-cancellation through separate and independent tasks in a group of patients with right hemisphere damage and a diagnosis of left neglect. Results showed impaired spatial working memory in neglect patients. Compared to the control group, neglect patients cancelled fewer targets and made more re-cancellations both on the left side and on the right side. The spatial working memory deficit appears to be related to re-cancellations, but only for some neglect patients. Alternative interpretations of re-exploration of space are discussed.

Identifying endophenotypes of autism: a multivariate approach.

The existence of an endophenotype of autism spectrum condition (ASC) has been recently suggested by several commentators. It can be estimated by finding differences between controls and people with ASC that are also present when comparing controls and the unaffected siblings of ASC individuals. In this work, we used a multivariate methodology applied on magnetic resonance images to look for such differences. The proposed procedure consists of combining a searchlight approach and a support vector machine classifier to identify the differences between three groups of participants in pairwise comparisons: controls, people with ASC and their unaffected siblings. Then we compared those differences selecting spatially collocated as candidate endophenotypes of ASC.

Combining PET images and neuropsychological test data for automatic diagnosis of Alzheimer's disease.

In recent years, several approaches to develop computer aided diagnosis (CAD) systems for dementia have been proposed. Some of these systems analyze neurological brain images by means of machine learning algorithms in order to find the patterns that characterize the disorder, and a few combine several imaging modalities to improve the diagnostic accuracy. However, they usually do not use neuropsychological testing data in that analysis. The purpose of this work is to measure the advantages of using not only neuroimages as data source in CAD systems for dementia but also neuropsychological scores. To this aim, we compared the accuracy rates achieved by systems that use neuropsychological scores beside the imaging data in the classification step and systems that use only one of these data sources. In order to address the small sample size problem and facilitate the data combination, a dimensionality reduction step (implemented using three different algorithms) was also applied on the imaging data. After each image is summarized in a reduced set of image features, the data sources were combined and classified using three different data combination approaches and a Support Vector Machine classifier. That way, by testing different dimensionality reduction methods and several data combination approaches, we aim not only highlighting the advantages of using neuropsychological scores in the classification, but also implementing the most accurate computer system for early dementia detention. The accuracy of the CAD systems were estimated using a database with records from 46 subjects, diagnosed with MCI or AD. A peak accuracy rate of 89% was obtained. In all cases the accuracy achieved using both, neuropsychological scores and imaging data, was substantially higher than the one obtained using only the imaging data.

Analysis of SPECT brain images for the diagnosis of Alzheimer's disease using moments and support vector machines.

This paper presents a computer-aided diagnosis technique for improving the accuracy of diagnosing the Alzheimer's type dementia. The proposed methodology is based on the calculation of the skewness for each m-by-m-by-m sliding block of the SPECT brain images. The center pixel in this m-by-m-by-m block is replaced by the skewness value to build a new 3-D brain image which is used for classification purposes. After that, voxels which present a Welch's t-statistic between classes, Normal and Alzheimer's images, higher (or lower) than a threshold are selected. The mean, standard deviation, skewness and kurtosis are calculated for these selected voxels and they are subjected as features to linear kernel based support vector machine classifier. The proposed methodology reaches accuracy higher than 99% in the classification task.