Use of Overlapping Group LASSO Sparse Deep Belief Network to Discriminate Parkinson's Disease and Normal Control

Parkinson's disease diagnosis using deep learning: A bibliometric analysis and literature review

Parkinson's Disease (PD) is a progressive neurodegenerative illness triggered by decreased dopamine secretion. Deep Learning (DL) has gained substantial attention in PD diagnosis research, with an increase in the number of published papers in this discipline. PD detection using DL has presented more promising outcomes as compared with common machine learning approaches. This article aims to conduct a bibliometric analysis and a literature review focusing on the prominent developments taking place in this area. To achieve the target of the study, we retrieved and analyzed the available research papers in the Scopus database. Following that, we conducted a bibliometric analysis to inspect the structure of keywords, authors, and countries in the surveyed studies by providing visual representations of the bibliometric data using VOSviewer software. The study also provides an in-depth review of the literature focusing on different indicators of PD, deployed approaches, and performance metrics. The outcomes indicate the firm development of PD diagnosis using DL approaches over time and a large diversity of studies worldwide. Additionally, the literature review presented a research gap in DL approaches related to incremental learning, particularly in relation to big data analysis.

Random forest analysis of midbrain hypometabolism using [18F]-FDG PET identifies Parkinson's disease at the subject-level

Parkinson's disease (PD) is currently diagnosed largely on the basis of expert judgement with neuroimaging serving only as a supportive tool. In a recent study, we identified a hypometabolic midbrain cluster, which includes parts of the substantia nigra, as the best differentiating metabolic feature for PD-patients based on group comparison of [18F]-fluorodeoxyglucose ([18F]-FDG) PET scans. Longitudinal analyses confirmed progressive metabolic changes in this region and, an independent study showed great potential of nigral metabolism for diagnostic workup of parkinsonian syndromes. In this study, we applied a machine learning approach to evaluate midbrain metabolism measured by [18F]-FDG PET as a diagnostic marker for PD. In total, 51 mid-stage PD-patients and 16 healthy control subjects underwent high-resolution [18F]-FDG PET. Normalized tracer update values of the midbrain cluster identified by between-group comparison were extracted voxel-wise from individuals' scans. Extracted uptake values were subjected to a random forest feature classification algorithm. An adapted leave-one-out cross validation approach was applied for testing robustness of the model for differentiating between patients and controls. Performance of the model across all runs was evaluated by calculating sensitivity, specificity and model accuracy for the validation data set and the percentage of correctly categorized subjects for test data sets. The random forest feature classification of voxel-based uptake values from the midbrain cluster identified patients in the validation data set with an average sensitivity of 0.91 (Min: 0.82, Max: 0.94). For all 67 runs, in which each of the individuals was treated once as test data set, the test data set was correctly categorized by our model. The applied feature importance extraction consistently identified a subset of voxels within the midbrain cluster with highest importance across all runs which spatially converged with the left substantia nigra. Our data suggest midbrain metabolism measured by [18F]-FDG PET as a promising diagnostic imaging tool for PD. Given its close relationship to PD pathophysiology and very high discriminatory accuracy, this approach could help to objectify PD diagnosis and enable more accurate classification in relation to clinical trials, which could also be applicable to patients with prodromal disease.

Diagnostic performance of artificial intelligence-assisted PET imaging for Parkinson's disease: a systematic review and meta-analysis

Artificial intelligence (AI)-assisted PET imaging is emerging as a promising tool for the diagnosis of Parkinson's disease (PD). We aim to systematically review the diagnostic accuracy of AI-assisted PET in detecting PD. The Ovid MEDLINE, Ovid Embase, Web of Science, and IEEE Xplore databases were systematically searched for related studies that developed an AI algorithm in PET imaging for diagnostic performance from PD and were published by August 17, 2023. Binary diagnostic accuracy data were extracted for meta-analysis to derive outcomes of interest: area under the curve (AUC). 23 eligible studies provided sufficient data to construct contingency tables that allowed the calculation of diagnostic accuracy. Specifically, 11 studies were identified that distinguished PD from normal control, with a pooled AUC of 0.96 (95% CI: 0.94-0.97) for presynaptic dopamine (DA) and 0.90 (95% CI: 0.87-0.93) for glucose metabolism (18F-FDG). 13 studies were identified that distinguished PD from the atypical parkinsonism (AP), with a pooled AUC of 0.93 (95% CI: 0.91 - 0.95) for presynaptic DA, 0.79 (95% CI: 0.75-0.82) for postsynaptic DA, and 0.97 (95% CI: 0.96-0.99) for 18F-FDG. Acceptable diagnostic performance of PD with AI algorithms-assisted PET imaging was highlighted across the subgroups. More rigorous reporting standards that take into account the unique challenges of AI research could improve future studies.

Discrimination between leucine-rich glioma-inactivated 1 antibody encephalitis and gamma-aminobutyric acid B receptor antibody encephalitis based on ResNet18

This study aims to discriminate between leucine-rich glioma-inactivated 1 (LGI1) antibody encephalitis and gamma-aminobutyric acid B (GABAB) receptor antibody encephalitis using a convolutional neural network (CNN) model. A total of 81 patients were recruited for this study. ResNet18, VGG16, and ResNet50 were trained and tested separately using 3828 positron emission tomography image slices that contained the medial temporal lobe (MTL) or basal ganglia (BG). Leave-one-out cross-validation at the patient level was used to evaluate the CNN models. The receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC) were generated to evaluate the CNN models. Based on the prediction results at slice level, a decision strategy was employed to evaluate the CNN models' performance at patient level. The ResNet18 model achieved the best performance at the slice (AUC = 0.86, accuracy = 80.28%) and patient levels (AUC = 0.98, accuracy = 96.30%). Specifically, at the slice level, 73.28% (1445/1972) of image slices with GABAB receptor antibody encephalitis and 87.72% (1628/1856) of image slices with LGI1 antibody encephalitis were accurately detected. At the patient level, 94.12% (16/17) of patients with GABAB receptor antibody encephalitis and 96.88% (62/64) of patients with LGI1 antibody encephalitis were accurately detected. Heatmaps of the image slices extracted using gradient-weighted class activation mapping indicated that the model focused on the MTL and BG for classification. In general, the ResNet18 model is a potential approach for discriminating between LGI1 and GABAB receptor antibody encephalitis. Metabolism in the MTL and BG is important for discriminating between these two encephalitis subtypes.

Relevance of 18F-DOPA visual and semi-quantitative PET metrics for the diagnostic of Parkinson disease in clinical practice: a machine learning-based inference study

PURPOSE

To decipher the relevance of visual and semi-quantitative 6-fluoro-(18F)-L-DOPA (¹⁸F-DOPA) interpretation methods for the diagnostic of idiopathic Parkinson disease (IPD) in hybrid positron emission tomography (PET) and magnetic resonance imaging.

MATERIAL AND METHODS

A total of 110 consecutive patients (48 IPD and 62 controls) with 11 months of median clinical follow-up (reference standard) were included. A composite visual assessment from five independent nuclear imaging readers, together with striatal standard uptake value (SUV) to occipital SUV ratio, striatal gradients and putamen asymmetry-based semi-quantitative PET metrics automatically extracted used to train machine learning models to classify IPD versus controls. Using a ratio of 70/30 for training and testing sets, respectively, five classification models-k-NN, LogRegression, support vector machine, random forest and gradient boosting-were trained by using 100 times repeated nested cross-validation procedures. From the best model on average, the contribution of PET parameters was deciphered using the Shapley additive explanations method (SHAP). Cross-validated receiver operating characteristic curves (cv-ROC) of the most contributive PET parameters were finally estimated and compared.

RESULTS

The best machine learning model (k-NN) provided final cv-ROC of 0.81. According to SHAP analyses, visual PET metric was the most important contributor to the model overall performance, followed by the minimum between left and right striatal to occipital SUV ratio. The 10-time cv-ROC curves of visual, min SUVr or both showed quite similar performance (mean area under the ROC of 0.81, 0.81 and 0.79, respectively, for visual, min SUVr or both).

CONCLUSION

Visual expert analysis remains the most relevant parameter to predict IPD diagnosis at 11 months of median clinical follow-up in ¹⁸F-FDOPA. The min SUV ratio appears interesting in the perspective of simple semi-automated diagnostic workflows.

Head-to-Head Comparison Between Rabbit Sign and EANM/SNMMI Criteria for the 18F-DOPA Visual Assessment of Parkinsonian Syndromes in PET/MRI: A Multiple Expert-Based and Blinded Controlled Study

PURPOSE

The aim of this study was to compare the diagnostic performance of the rabbit visual pattern versus the one endorsed by the EANM/SNMMI for the diagnosis of parkinsonian syndromes in PET/MRI.

PATIENTS AND METHODS

The 18F-DOPA PET images of 129 consecutive patients (65 Park+ and 64 controls) with 1 year of clinical follow-up were reviewed independently by 5 experienced readers on the same imaging workstation, blinded to the final clinical diagnosis. Two visual methods were assessed independently, with several days to months of interval: the criteria endorsed by EANM/SNMMI and the "rabbit" shape of the striate assessed on 3D MIP images. The sensitivities, specificities, likelihood ratios, and predictive values of the 2 diagnostic tests were estimated simultaneously by using the "comparison of 2 binary diagnostic tests to a paired design" method.

RESULTS

The estimated 95% confidence interval (CI) of sensitivities and specificities ranged from 49.4% to 76.5% and from 83.2% to 97.7%, respectively. The 95% CI estimates of positive and negative likelihood ratios ranged from 3.8 to 26.7 and from 0.26 to 0.56, respectively. The 95% CI estimates of the positive and negative predictive values ranged from 78.1% to 96.7% and from 60.3% to 81.4%, respectively. For all the parameters, no statistical difference was observed between the 2 methods (P > 0.05). The rabbit sign reduced the readers' discrepancies by 25%, while maintaining the same performance.

CONCLUSIONS

The rabbit visual pattern appears at least comparable to the current EANM/SNMMI reference procedure for the assessment of parkinsonian syndromes in daily clinical practice, without the need of any image postprocessing. Further multicenter prospective studies would be of relevance to validate these findings.

Molecular Imaging in Parkinsonian Disorders—What’s New and Hot?

Highlights

Abstract

Neurodegenerative parkinsonian disorders are characterized by a great diversity of clinical symptoms and underlying neuropathology, yet differential diagnosis during lifetime remains probabilistic. Molecular imaging is a powerful method to detect pathological changes in vivo on a cellular and molecular level with high specificity. Thereby, molecular imaging enables to investigate functional changes and pathological hallmarks in neurodegenerative disorders, thus allowing to better differentiate between different forms of degenerative parkinsonism, improve the accuracy of the clinical diagnosis and disentangle the pathophysiology of disease-related symptoms. The past decade led to significant progress in the field of molecular imaging, including the development of multiple new and promising radioactive tracers for single photon emission computed tomography (SPECT) and positron emission tomography (PET) as well as novel analytical methods. Here, we review the most recent advances in molecular imaging for the diagnosis, prognosis, and mechanistic understanding of parkinsonian disorders. First, advances in imaging of neurotransmission abnormalities, metabolism, synaptic density, inflammation, and pathological protein aggregation are reviewed, highlighting our renewed understanding regarding the multiplicity of neurodegenerative processes involved in parkinsonian disorders. Consequently, we review the role of molecular imaging in the context of disease-modifying interventions to follow neurodegeneration, ensure stratification, and target engagement in clinical trials.

Construction and Multiple Feature Classification Based on a High-Order Functional Hypernetwork on fMRI Data

Resting-state functional connectivity hypernetworks, in which multiple nodes can be connected, are an effective technique for diagnosing brain disease and performing classification research. Conventional functional hypernetworks can characterize the complex interactions within the human brain in a static form. However, an increasing body of evidence demonstrates that even in a resting state, neural activity in the brain still exhibits transient and subtle dynamics. These dynamic changes are essential for understanding the basic characteristics underlying brain organization and may correlate significantly with the pathological mechanisms of brain diseases. Therefore, considering the dynamic changes of functional connections in the resting state, we proposed methodology to construct resting state high-order functional hyper-networks (rs-HOFHNs) for patients with depression and normal subjects. Meanwhile, we also introduce a novel property (the shortest path) to extract local features with traditional local properties (cluster coefficients). A subgraph feature-based method was introduced to characterize information relating to global topology. Two features, local features and subgraph features that showed significant differences after feature selection were subjected to multi-kernel learning for feature fusion and classification. Compared with conventional hyper network models, the high-order hyper network obtained the best classification performance, 92.18%, which indicated that better classification performance can be achieved if we needed to consider multivariate interactions and the time-varying characteristics of neural interaction simultaneously when constructing a network.

Mining imaging and clinical data with machine learning approaches for the diagnosis and early detection of Parkinson's disease

Parkinson’s disease (PD) is a common, progressive, and currently incurable neurodegenerative movement disorder. The diagnosis of PD is challenging, especially in the differential diagnosis of parkinsonism and in early PD detection. Due to the advantages of machine learning such as learning complex data patterns and making inferences for individuals, machine-learning techniques have been increasingly applied to the diagnosis of PD, and have shown some promising results. Machine-learning-based imaging applications have made it possible to help differentiate parkinsonism and detect PD at early stages automatically in a number of neuroimaging studies. Comparative studies have shown that machine-learning-based SPECT image analysis applications in PD have outperformed conventional semi-quantitative analysis in detecting PD-associated dopaminergic degeneration, performed comparably well as experts’ visual inspection, and helped improve PD diagnostic accuracy of radiologists. Using combined multi-modal (imaging and clinical) data in these applications may further enhance PD diagnosis and early detection. To integrate machine-learning-based diagnostic applications into clinical systems, further validation and optimization of these applications are needed to make them accurate and reliable. It is anticipated that machine-learning techniques will further help improve differential diagnosis of parkinsonism and early detection of PD, which may reduce the error rate of PD diagnosis and help detect PD at pre-motor stage to make it possible for early treatments (e.g., neuroprotective treatment) to slow down PD progression, prevent severe motor symptoms from emerging, and relieve patients from suffering.

Application of Deep Learning Models for Automated Identification of Parkinson's Disease: A Review (2011-2021)

Parkinson’s disease (PD) is the second most common neurodegenerative disorder affecting over 6 million people globally. Although there are symptomatic treatments that can increase the survivability of the disease, there are no curative treatments. The prevalence of PD and disability-adjusted life years continue to increase steadily, leading to a growing burden on patients, their families, society and the economy. Dopaminergic medications can significantly slow down the progression of PD when applied during the early stages. However, these treatments often become less effective with the disease progression. Early diagnosis of PD is crucial for immediate interventions so that the patients can remain self-sufficient for the longest period of time possible. Unfortunately, diagnoses are often late, due to factors such as a global shortage of neurologists skilled in early PD diagnosis. Computer-aided diagnostic (CAD) tools, based on artificial intelligence methods, that can perform automated diagnosis of PD, are gaining attention from healthcare services. In this review, we have identified 63 studies published between January 2011 and July 2021, that proposed deep learning models for an automated diagnosis of PD, using various types of modalities like brain analysis (SPECT, PET, MRI and EEG), and motion symptoms (gait, handwriting, speech and EMG). From these studies, we identify the best performing deep learning model reported for each modality and highlight the current limitations that are hindering the adoption of such CAD tools in healthcare. Finally, we propose new directions to further the studies on deep learning in the automated detection of PD, in the hopes of improving the utility, applicability and impact of such tools to improve early detection of PD globally.

Machine Learning for the Diagnosis of Parkinson's Disease: A Review of Literature

Diagnosis of Parkinson's disease (PD) is commonly based on medical observations and assessment of clinical signs, including the characterization of a variety of motor symptoms. However, traditional diagnostic approaches may suffer from subjectivity as they rely on the evaluation of movements that are sometimes subtle to human eyes and therefore difficult to classify, leading to possible misclassification. In the meantime, early non-motor symptoms of PD may be mild and can be caused by many other conditions. Therefore, these symptoms are often overlooked, making diagnosis of PD at an early stage challenging. To address these difficulties and to refine the diagnosis and assessment procedures of PD, machine learning methods have been implemented for the classification of PD and healthy controls or patients with similar clinical presentations (e.g., movement disorders or other Parkinsonian syndromes). To provide a comprehensive overview of data modalities and machine learning methods that have been used in the diagnosis and differential diagnosis of PD, in this study, we conducted a literature review of studies published until February 14, 2020, using the PubMed and IEEE Xplore databases. A total of 209 studies were included, extracted for relevant information and presented in this review, with an investigation of their aims, sources of data, types of data, machine learning methods and associated outcomes. These studies demonstrate a high potential for adaptation of machine learning methods and novel biomarkers in clinical decision making, leading to increasingly systematic, informed diagnosis of PD.

Artificial intelligence for molecular neuroimaging

In recent years, artificial intelligence (AI) or the study of how computers and machines can gain intelligence, has been increasingly applied to problems in medical imaging, and in particular to molecular imaging of the central nervous system. Many AI innovations in medical imaging include improving image quality, segmentation, and automating classification of disease. These advances have led to an increased availability of supportive AI tools to assist physicians in interpreting images and making decisions affecting patient care. This review focuses on the role of AI in molecular neuroimaging, primarily applied to positron emission tomography (PET) and single photon emission computed tomography (SPECT). We emphasize technical innovations such as AI in computed tomography (CT) generation for the purposes of attenuation correction and disease localization, as well as applications in neuro-oncology and neurodegenerative diseases. Limitations and future prospects for AI in molecular brain imaging are also discussed. Just as new equipment such as SPECT and PET revolutionized the field of medical imaging a few decades ago, AI and its related technologies are now poised to bring on further disruptive changes. An understanding of these new technologies and how they work will help physicians adapt their practices and succeed with these new tools.

Application and Construction of Deep Learning Networks in Medical Imaging

Deep learning (DL) approaches are part of the machine learning (ML) subfield concerned with the development of computational models to train artificial intelligence systems. DL models are characterized by automatically extracting high-level features from the input data to learn the relationship between matching datasets. Thus, its implementation offers an advantage over common ML methods that often require the practitioner to have some domain knowledge of the input data to select the best latent representation. As a result of this advantage, DL has been successfully applied within the medical imaging field to address problems, such as disease classification and tumor segmentation for which it is difficult or impossible to determine which image features are relevant. Therefore, taking into consideration the positive impact of DL on the medical imaging field, this article reviews the key concepts associated with its evolution and implementation. The sections of this review summarize the milestones related to the development of the DL field, followed by a description of the elements of deep neural network and an overview of its application within the medical imaging field. Subsequently, the key steps necessary to implement a supervised DL application are defined, and associated limitations are discussed.

Use of a Sparse-Response Deep Belief Network and Extreme Learning Machine to Discriminate Alzheimer's Disease, Mild Cognitive Impairment, and Normal Controls Based on Amyloid PET/MRI Images

In recent years, interest has grown in using computer-aided diagnosis (CAD) for Alzheimer's disease (AD) and its prodromal stage, mild cognitive impairment (MCI). However, existing CAD technologies often overfit data and have poor generalizability. In this study, we proposed a sparse-response deep belief network (SR-DBN) model based on rate distortion (RD) theory and an extreme learning machine (ELM) model to distinguish AD, MCI, and normal controls (NC). We used [¹⁸F]-AV45 positron emission computed tomography (PET) and magnetic resonance imaging (MRI) images from 340 subjects enrolled in the ADNI database, including 116 AD, 82 MCI, and 142 NC subjects. The model was evaluated using five-fold cross-validation. In the whole model, fast principal component analysis (PCA) served as a dimension reduction algorithm. An SR-DBN extracted features from the images, and an ELM obtained the classification. Furthermore, to evaluate the effectiveness of our method, we performed comparative trials. In contrast experiment 1, the ELM was replaced by a support vector machine (SVM). Contrast experiment 2 adopted DBN without sparsity. Contrast experiment 3 consisted of fast PCA and an ELM. Contrast experiment 4 used a classic convolutional neural network (CNN) to classify AD. Accuracy, sensitivity, specificity, and area under the curve (AUC) were examined to validate the results. Our model achieved 91.68% accuracy, 95.47% sensitivity, 86.68% specificity, and an AUC of 0.87 separating between AD and NC groups; 87.25% accuracy, 79.74% sensitivity, 91.58% specificity, and an AUC of 0.79 separating MCI and NC groups; and 80.35% accuracy, 85.65% sensitivity, 72.98% specificity, and an AUC of 0.71 separating AD and MCI groups, which gave better classification than other models assessed.

A Survey on Deep Learning for Neuroimaging-Based Brain Disorder Analysis

Deep learning has recently been used for the analysis of neuroimages, such as structural magnetic resonance imaging (MRI), functional MRI, and positron emission tomography (PET), and it has achieved significant performance improvements over traditional machine learning in computer-aided diagnosis of brain disorders. This paper reviews the applications of deep learning methods for neuroimaging-based brain disorder analysis. We first provide a comprehensive overview of deep learning techniques and popular network architectures by introducing various types of deep neural networks and recent developments. We then review deep learning methods for computer-aided analysis of four typical brain disorders, including Alzheimer's disease, Parkinson's disease, Autism spectrum disorder, and Schizophrenia, where the first two diseases are neurodegenerative disorders and the last two are neurodevelopmental and psychiatric disorders, respectively. More importantly, we discuss the limitations of existing studies and present possible future directions.

Use of radiomic features and support vector machine to distinguish Parkinson's disease cases from normal controls

Background

Parkinson's disease (PD) is an irreversible neurodegenerative disease. The diagnosis of PD based on neuroimaging is usually with low-level or deep learning features, which results in difficulties in achieving precision classification or interpreting the clinical significance. Herein, we aimed to extract high-order features by using radiomics approach and achieve acceptable diagnosis accuracy in PD.

Methods

In this retrospective multicohort study, we collected ¹⁸F-fluorodeoxyglucose positron emission tomography (¹⁸F-FDG PET) images and clinical scale [the Unified Parkinson's Disease Rating Scale (UPDRS) and Hoehn & Yahr scale (H&Y)] from two cohorts. One cohort from Huashan Hospital had 91 normal controls (NC) and 91 PD patients (UPDRS: 22.7±11.7, H&Y: 1.8±0.8), and the other cohort from Wuxi 904 Hospital had 26 NC and 22 PD patients (UPDRS: 20.9±11.6, H&Y: 1.7±0.9). The Huashan cohort was used as the training and test sets by 5-fold cross-validation and the Wuxi cohort was used as another separate test set. After identifying regions of interests (ROIs) based on the atlas-based method, radiomic features were extracted and selected by using autocorrelation and fisher score algorithm. A support vector machine (SVM) was trained to classify PD and NC based on selected radiomic features. In the comparative experiment, we compared our method with the traditional voxel values method. To guarantee the robustness, above processes were repeated in 500 times.

Results

Twenty-six brain ROIs were identified. Six thousand one hundred and ten radiomic features were extracted in total. Among them 30 features were remained after feature selection. The accuracies of the proposed method achieved 90.97%±4.66% and 88.08%±5.27% in Huashan and Wuxi test sets, respectively.

Conclusions

This study showed that radiomic features and SVM could be used to distinguish between PD and NC based on 18F-FDG PET images.