Automatic detection of Parkinsonism using significance measures and component analysis in DaTSCAN imaging

Machine learning models for diagnosis and prognosis of Parkinson's disease using brain imaging: general overview, main challenges, and future directions

Parkinson's disease (PD) is a progressive and complex neurodegenerative disorder associated with age that affects motor and cognitive functions. As there is currently no cure, early diagnosis and accurate prognosis are essential to increase the effectiveness of treatment and control its symptoms. Medical imaging, specifically magnetic resonance imaging (MRI), has emerged as a valuable tool for developing support systems to assist in diagnosis and prognosis. The current literature aims to improve understanding of the disease's structural and functional manifestations in the brain. By applying artificial intelligence to neuroimaging, such as deep learning (DL) and other machine learning (ML) techniques, previously unknown relationships and patterns can be revealed in this high-dimensional data. However, several issues must be addressed before these solutions can be safely integrated into clinical practice. This review provides a comprehensive overview of recent ML techniques analyzed for the automatic diagnosis and prognosis of PD in brain MRI. The main challenges in applying ML to medical diagnosis and its implications for PD are also addressed, including current limitations for safe translation into hospitals. These challenges are analyzed at three levels: disease-specific, task-specific, and technology-specific. Finally, potential future directions for each challenge and future perspectives are discussed.

Explainable machine learning models based on multimodal time-series data for the early detection of Parkinson's disease

BACKGROUND AND OBJECTIVES

Parkinson's Disease (PD) is a devastating chronic neurological condition. Machine learning (ML) techniques have been used in the early prediction of PD progression. Fusion of heterogeneous data modalities proved its capability to improve the performance of ML models. Time series data fusion supports the tracking of the disease over time. In addition, the trustworthiness of the resulting models is improved by adding model explainability features. The literature on PD has not sufficiently explored these three points.

METHODS

In this work, we proposed an ML pipeline for predicting the progression of PD that is both accurate and explainable. We explore the fusion of different combinations of five time series modalities from the Parkinson's Progression Markers Initiative (PPMI) real-world dataset, including patient characteristics, biosamples, medication history, motor, and non-motor function data. Each patient has six visits. The problem has been formulated in two ways: ❶ a three-class based progression prediction with 953 patients in each time series modality, and ❷ a four-class based progression prediction with 1,060 patients in each time series modality. The statistical features of these six visits were calculated from each modality and diverse feature selection methods were applied to select the most informative feature sets. The extracted features were used to train a set of well-known ML models including Support vector machines (SVM), random forests (RF), extra tree classifier (ETC), light gradient boosting machines (LGBM), and stochastic gradient descent (SGD). We examined a number of data-balancing strategies in the pipeline with different combinations of modalities. ML models have been optimized using the Bayesian optimizer. A comprehensive evaluation of various ML methods has been conducted, and the best models have been extended to provide different explainability features.

RESULTS

We compare the performance of ML models before and after optimization and using and without using feature selection. In the three-class experiment and with various modality fusions, the LGBM model produced the most accurate results with a 10-fold cross-validation (10-CV) accuracy of 90.73% using non-motor function modality. RF produced the best results in the four-class experiment with various modality fusions with a 10-CV accuracy of 94.57% using non-motor modality. With the fused dataset of non-motor and motor function modalities, the LGBM model outperformed the other ML models in both the 3-class and 4-class experiments (i.e., 10-CV accuracy of 94.89% and 93.73%, respectively). Using the Shapely Additive Explanations (SHAP) framework, we employed global and instance-based explanations to explain the behavior of each ML classifier. Moreover, we extended the explainability by implementing the LIME and SHAPASH local explainers. The consistency of these explainers has been explored. The resultant classifiers were accurate, explainable, and thus medically more relevant and applicable.

CONCLUSIONS

The select modalities and feature sets were confirmed by the literature and medical experts. The various explainers suggest that the bradykinesia (NP3BRADY) feature was the most dominant and consistent. By providing thorough insights into the influence of multiple modalities on the disease risk, the suggested approach is expected to help improve the clinical knowledge of PD progression processes.

Three Dimensional Analysis of SPECT Images for Diagnosing Early Parkinson's Disease using Radial Basis Function Kernel - Extreme Learning Machine

BACKGROUND

Parkinson's Disease (PD) is caused by the deficiency of dopamine, the neurotransmitter that has an effect on specific uptake region of the substantia nigra. Identification of PD is quite tough at an early stage.

OBJECTIVE

The present work proposes an expert system for three dimensional Single-Photon Emission Computed Tomography (SPECT) image to diagnose the early PD.

METHODS

The transaxial image slices are selected on the basis of their high specific uptake region. The processing techniques like preprocessing, segmentation and feature extraction are implemented to extract the quantification parameters like Intensity, correlation, entropy, skewness and kurtosis of the images. The Support Vector Machine (SVM) and Extreme Learning Machine (ELM) classifiers using Radial Basis Function kernel (RBF) are implemented and their results are compared in order to achieve better performance of the system. The performance of the system is evaluated in terms of sensitivity, specificity analysis, accuracy, Receiver Operating Curve (ROC) and Area Under the Curve (AUC).

RESULTS

It is found that RBF-ELM provides high accuracy of 98.2% in diagnosing early PD. In addition, the similarity among the features is found out using K-means clustering algorithm to compute the threshold level for early PD. The computed threshold level is validated using Analysis of Variance (ANOVA).

CONCLUSION

The proposed system has a great potential to assist the clinicians in the early diagnosis process of PD.

Morphological Characterization of Functional Brain Imaging by Isosurface Analysis in Parkinson’s Disease

Finding new biomarkers to model Parkinson’s Disease (PD) is a challenge not only to help discerning between Healthy Control (HC) subjects and patients with potential PD but also as a way to measure quantitatively the loss of dopaminergic neurons mainly concentrated at substantia nigra. Within this context, this work presented here tries to provide a set of imaging features based on morphological characteristics extracted from I[Formula: see text]-Ioflupane SPECT scans to discern between HC and PD participants in a balanced set of [Formula: see text] scans from Parkinson’s Progression Markers Initiative (PPMI) database. These features, obtained from isosurfaces of each scan at different intensity levels, have been classified through the use of classical Machine Learning classifiers such as Support-Vector-Machines (SVM) or Naïve Bayesian and compared with the results obtained using a Multi-Layer Perceptron (MLP).

The proposed system, based on a Mann–Whitney–Wilcoxon U-Test for feature selection and the SVM approach, yielded a [Formula: see text] balanced accuracy when the performance was evaluated using a [Formula: see text]-fold cross-validation. This proves the reliability of these biomarkers, especially those related to sphericity, center of mass, number of vertices, 2D-projected perimeter or the 2D-projected eccentricity, among others, but including both internal and external isosurfaces.

Parkinson's Disease Detection Using Isosurfaces-Based Features and Convolutional Neural Networks

Computer aided diagnosis systems based on brain imaging are an important tool to assist in the diagnosis of Parkinson's disease, whose ultimate goal is the detection by automatic recognizing of patterns that characterize the disease. In recent times Convolutional Neural Networks (CNN) have proved to be amazingly useful for that task. The drawback, however, is that 3D brain images contain a huge amount of information that leads to complex CNN architectures. When these architectures become too complex, classification performances often degrades because the limitations of the training algorithm and overfitting. Thus, this paper proposes the use of isosurfaces as a way to reduce such amount of data while keeping the most relevant information. These isosurfaces are then used to implement a classification system which uses two of the most well-known CNN architectures, LeNet and AlexNet, to classify DaTScan images with an average accuracy of 95.1% and AUC = 97%, obtaining comparable (slightly better) values to those obtained for most of the recently proposed systems. It can be concluded therefore that the computation of isosurfaces reduces the complexity of the inputs significantly, resulting in high classification accuracies with reduced computational burden.

Classification of degenerative parkinsonism subtypes by support-vector-machine analysis and striatal 123I-FP-CIT indices

Objectives

To provide an automated classification method for degenerative parkinsonian syndromes (PS) based on semiquantitative ¹²³I-FP-CIT SPECT striatal indices and support-vector-machine (SVM) analysis.

Methods

¹²³I-FP-CIT SPECT was performed at a single-center level on 370 individuals with PS, including 280 patients with Parkinson’s disease (PD), 21 with multiple system atrophy-parkinsonian type (MSA-P), 41 with progressive supranuclear palsy (PSP) and 28 with corticobasal syndrome (CBS) (mean age 70.3 years, 47% female, mean disease duration at scan 1.4 year), as well as 208 age- and gender-matched control subjects. Striatal volumes-of-interest (VOIs) uptake, VOIs asymmetry indices (AIs) and caudate/putamen (C/P) ratio were used as input for SVM individual classification using fivefold cross-validation.

Results

Univariate analyses showed significantly lower VOIs uptake, higher striatal AI and C/P ratio for each PS in comparison to controls (all p < 0.001). Among PS, higher degree of striatal impairment was observed in MSA-P and PSP, while CBS showed moderate uptake reduction and higher AI. Binary SVM classification showed 92.9% accuracy in distinguishing PS from controls. Classification based on each binary combination of PS ranged 62.9–83.7% accuracy with the most satisfactory results when separating CBS from the other PS. Sensitivity and specificity values were high and balanced ranging from 60 to 80% for all analyses with > 70% accuracy. Overall, striatal AI and C/P ratio on the more affected side had the highest weighting factors.

Conclusion

Semiquantitative ¹²³I-FP-CIT SPECT striatal evaluation combined with SVM represents a promising approach to disentangle PD from non-degenerative conditions and from atypical PS at the early stage.

Empirical Functional PCA for 3D Image Feature Extraction Through Fractal Sampling

Medical image classification is currently a challenging task that can be used to aid the diagnosis of different brain diseases. Thus, exploratory and discriminative analysis techniques aiming to obtain representative features from the images play a decisive role in the design of effective Computer Aided Diagnosis (CAD) systems, which is especially important in the early diagnosis of dementia. In this work, we present a technique that allows using specific time series analysis techniques with 3D images. This is achieved by sampling the image using a fractal-based method which preserves the spatial relationship among voxels. In addition, a method called Empirical functional PCA (EfPCA) is presented, which combines Empirical Mode Decomposition (EMD) with functional PCA to express an image in the space spanned by a basis of empirical functions, instead of using components computed by a predefined basis as in Fourier or Wavelet analysis. The devised technique has been used to classify images from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and the Parkinson Progression Markers Initiative (PPMI), achieving accuracies up to 93% and 92% differential diagnosis tasks (AD versus controls and PD versus Controls, respectively). The results obtained validate the method, proving that the information retrieved by our methodology is significantly linked to the diseases.

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.

Machine Learning for Neurodegenerative Disorder Diagnosis — Survey of Practices and Launch of Benchmark Dataset

Neurodegenerative disorders, such as Alzheimer’s and Parkinson’s, constitute a major factor in long-term disability and are becoming more and more a serious concern in developed countries. As there are, at present, no effective therapies, early diagnosis along with avoidance of misdiagnosis seem to be critical in ensuring a good quality of life for patients. In this sense, the adoption of computer-aided-diagnosis tools can offer significant assistance to clinicians. In the present paper, we provide in the first place a comprehensive recording of medical examinations relevant to those disorders. Then, a review is conducted concerning the use of Machine Learning techniques in supporting diagnosis of neurodegenerative diseases, with reference to at times used medical datasets. Special attention has been given to the field of Deep Learning. In addition to that, we communicate the launch of a newly created dataset for Parkinson’s disease, containing epidemiological, clinical and imaging data, which will be publicly available to researchers for benchmarking purposes. To assess the potential of the new dataset, an experimental study in Parkinson’s diagnosis is carried out, based on state-of-the-art Deep Neural Network architectures and yielding very promising accuracy results.

Comparison of machine learning and semi-quantification algorithms for (I123)FP-CIT classification: the beginning of the end for semi-quantification?

BACKGROUND

Semi-quantification methods are well established in the clinic for assisted reporting of (I123) Ioflupane images. Arguably, these are limited diagnostic tools. Recent research has demonstrated the potential for improved classification performance offered by machine learning algorithms. A direct comparison between methods is required to establish whether a move towards widespread clinical adoption of machine learning algorithms is justified. This study compared three machine learning algorithms with that of a range of semi-quantification methods, using the Parkinson's Progression Markers Initiative (PPMI) research database and a locally derived clinical database for validation. Machine learning algorithms were based on support vector machine classifiers with three different sets of features: Voxel intensities Principal components of image voxel intensities Striatal binding radios from the putamen and caudate. Semi-quantification methods were based on striatal binding ratios (SBRs) from both putamina, with and without consideration of the caudates. Normal limits for the SBRs were defined through four different methods: Minimum of age-matched controls Mean minus 1/1.5/2 standard deviations from age-matched controls Linear regression of normal patient data against age (minus 1/1.5/2 standard errors) Selection of the optimum operating point on the receiver operator characteristic curve from normal and abnormal training data Each machine learning and semi-quantification technique was evaluated with stratified, nested 10-fold cross-validation, repeated 10 times.

RESULTS

The mean accuracy of the semi-quantitative methods for classification of local data into Parkinsonian and non-Parkinsonian groups varied from 0.78 to 0.87, contrasting with 0.89 to 0.95 for classifying PPMI data into healthy controls and Parkinson's disease groups. The machine learning algorithms gave mean accuracies between 0.88 to 0.92 and 0.95 to 0.97 for local and PPMI data respectively.

CONCLUSIONS

Classification performance was lower for the local database than the research database for both semi-quantitative and machine learning algorithms. However, for both databases, the machine learning methods generated equal or higher mean accuracies (with lower variance) than any of the semi-quantification approaches. The gain in performance from using machine learning algorithms as compared to semi-quantification was relatively small and may be insufficient, when considered in isolation, to offer significant advantages in the clinical context.

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 D_2/3 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.

Resting State Effective Connectivity Allows Auditory Hallucination Discrimination

Hallucinations are elusive phenomena that have been associated with psychotic behavior, but that have a high prevalence in healthy population. Some generative mechanisms of Auditory Hallucinations (AH) have been proposed in the literature, but so far empirical evidence is scarce. The most widely accepted generative mechanism hypothesis nowadays consists in the faulty workings of a network of brain areas including the emotional control, the audio and language processing, and the inhibition and self-attribution of the signals in the auditive cortex. In this paper, we consider two methods to analyze resting state fMRI (rs-fMRI) data, in order to measure effective connections between the brain regions involved in the AH generation process. These measures are the Dynamic Causal Modeling (DCM) cross-covariance function (CCF) coefficients, and the partially directed coherence (PDC) coefficients derived from Granger Causality (GC) analysis. Effective connectivity measures are treated as input classifier features to assess their significance by means of cross-validation classification accuracy results in a wrapper feature selection approach. Experimental results using Support Vector Machine (SVM) classifiers on an rs-fMRI dataset of schizophrenia patients with and without a history of AH confirm that the main regions identified in the AH generative mechanism hypothesis have significant effective connection values, under both DCM and PDC evaluation.

Embarrassingly Parallel Acceleration of Global Tractography via Dynamic Domain Partitioning

Global tractography estimates brain connectivity by organizing signal-generating fiber segments in an optimal configuration that best describes the measured diffusion-weighted data, promising better stability than local greedy methods with respect to imaging noise. However, global tractography is computationally very demanding and requires computation times that are often prohibitive for clinical applications. We present here a reformulation of the global tractography algorithm for fast parallel implementation amendable to acceleration using multi-core CPUs and general-purpose GPUs. Our method is motivated by the key observation that each fiber segment is affected by a limited spatial neighborhood. In other words, a fiber segment is influenced only by the fiber segments that are (or can potentially be) connected to its two ends and also by the diffusion-weighted signal in its proximity. This observation makes it possible to parallelize the Markov chain Monte Carlo (MCMC) algorithm used in the global tractography algorithm so that concurrent updating of independent fiber segments can be carried out. Experiments show that the proposed algorithm can significantly speed up global tractography, while at the same time maintain or even improve tractography performance.

Computer-Aided Diagnosis of Parkinson's Disease Using Enhanced Probabilistic Neural Network

Early and accurate diagnosis of Parkinson's disease (PD) remains challenging. Neuropathological studies using brain bank specimens have estimated that a large percentages of clinical diagnoses of PD may be incorrect especially in the early stages. In this paper, a comprehensive computer model is presented for the diagnosis of PD based on motor, non-motor, and neuroimaging features using the recently-developed enhanced probabilistic neural network (EPNN). The model is tested for differentiating PD patients from those with scans without evidence of dopaminergic deficit (SWEDDs) using the Parkinson's Progression Markers Initiative (PPMI) database, an observational, multi-center study designed to identify PD biomarkers for diagnosis and disease progression. The results are compared to four other commonly-used machine learning algorithms: the probabilistic neural network (PNN), support vector machine (SVM), k-nearest neighbors (k-NN) algorithm, and classification tree (CT). The EPNN had the highest classification accuracy at 92.5% followed by the PNN (91.6%), k-NN (90.8%) and CT (90.2%). The EPNN exhibited an accuracy of 98.6% when classifying healthy control (HC) versus PD, higher than any previous studies.

Comparison between Different Intensity Normalization Methods in 123I-Ioflupane Imaging for the Automatic Detection of Parkinsonism

Intensity normalization is an important pre-processing step in the study and analysis of DaTSCAN SPECT imaging. As most automatic supervised image segmentation and classification methods base their assumptions regarding the intensity distributions on a standardized intensity range, intensity normalization takes on a very significant role. In this work, a comparison between different novel intensity normalization methods is presented. These proposed methodologies are based on Gaussian Mixture Model (GMM) image filtering and mean-squared error (MSE) optimization. The GMM-based image filtering method is achieved according to a probability threshold that removes the clusters whose likelihood are negligible in the non-specific regions. The MSE optimization method consists of a linear transformation that is obtained by minimizing the MSE in the non-specific region between the intensity normalized image and the template. The proposed intensity normalization methods are compared to: i) a standard approach based on the specific-to-non-specific binding ratio that is widely used, and ii) a linear approach based on the α-stable distribution. This comparison is performed on a DaTSCAN image database comprising analysis and classification stages for the development of a computer aided diagnosis (CAD) system for Parkinsonian syndrome (PS) detection. In addition, these proposed methods correct spatially varying artifacts that modulate the intensity of the images. Finally, using the leave-one-out cross-validation technique over these two approaches, the system achieves results up to a 92.91% of accuracy, 94.64% of sensitivity and 92.65 % of specificity, outperforming previous approaches based on a standard and a linear approach, which are used as a reference. The use of advanced intensity normalization techniques, such as the GMM-based image filtering and the MSE optimization improves the diagnosis of PS.

Parametrization of textural patterns in 123I-ioflupane imaging for the automatic detection of Parkinsonism

PURPOSE

A novel approach to a computer aided diagnosis system for the Parkinson's disease is proposed. This tool is intended as a supporting tool for physicians, based on fully automated methods that lead to the classification of (123)I-ioflupane SPECT images.

METHODS

(123)I-ioflupane images from three different databases are used to train the system. The images are intensity and spatially normalized, then subimages are extracted and a 3D gray-level co-occurrence matrix is computed over these subimages, allowing the characterization of the texture using Haralick texture features. Finally, different discrimination estimation methods are used to select a feature vector that can be used to train and test the classifier.

RESULTS

Using the leave-one-out cross-validation technique over these three databases, the system achieves results up to a 97.4% of accuracy, and 99.1% of sensitivity, with positive likelihood ratios over 27.

CONCLUSIONS

The system presents a robust feature extraction method that helps physicians in the diagnosis task by providing objective, operator-independent textural information about (123)I-ioflupane images, commonly used in the diagnosis of the Parkinson's disease. Textural features computation has been optimized by using a subimage selection algorithm, and the discrimination estimation methods used here makes the system feature-independent, allowing us to extend it to other databases and diseases.