[123I]Metaiodobenzylguanidine (MIBG) Cardiac Scintigraphy and Automated Classification Techniques in Parkinsonian Disorders

Assessing the reproducibility of machine-learning-based biomarker discovery in Parkinson's disease

Feature selection and machine learning algorithms can be used to analyze Single Nucleotide Polymorphisms (SNPs) data and identify potential disease biomarkers. Reproducibility of identified biomarkers is critical for them to be useful for clinical research; however, genotyping platforms and selection criteria for individuals to be genotyped affect the reproducibility of identified biomarkers. To assess biomarkers reproducibility, we collected five SNPs datasets from the database of Genotypes and Phenotypes (dbGaP) and explored several data integration strategies. While combining datasets can lead to a reduction in classification accuracy, it has the potential to improve the reproducibility of potential biomarkers. We evaluated the agreement among different strategies in terms of the SNPs that were identified as potential Parkinson's disease (PD) biomarkers. Our findings indicate that, on average, 93% of the SNPs identified in a single dataset fail to be identified in other datasets. However, through dataset integration, this lack of replication is reduced to 62%. We discovered fifty SNPs that were identified at least twice, which could potentially serve as novel PD biomarkers. These SNPs are indirectly linked to PD in the literature but have not been directly associated with PD before. These findings open up new potential avenues of investigation.

Cardiac 123I-Metaiodobenzylguanidine (MIBG) Scintigraphy in Parkinson's Disease: A Comprehensive Review

Cardiac sympathetic denervation, as documented on 123I-metaiodobenzylguanidine (MIBG) myocardial scintigraphy, is relatively sensitive and specific for distinguishing Parkinson's disease (PD) from other neurodegenerative causes of parkinsonism. The present study aims to comprehensively review the literature regarding the use of cardiac MIBG in PD. MIBG is an analog to norepinephrine. They share the same uptake, storage, and release mechanisms. An abnormal result in the cardiac MIBG uptake in individuals with parkinsonism can be an additional criterion for diagnosing PD. However, a normal result of cardiac MIBG in individuals with suspicious parkinsonian syndrome does not exclude the diagnosis of PD. The findings of cardiac MIBG studies contributed to elucidating the pathophysiology of PD. We investigated the sensitivity and specificity of cardiac MIBG scintigraphy in PD. A total of 54 studies with 3114 individuals diagnosed with PD were included. The data were described as means with a Hoehn and Yahr stage of 2.5 and early and delayed registration H/M ratios of 1.70 and 1.51, respectively. The mean cutoff for the early and delayed phases were 1.89 and 1.86. The sensitivity for the early and delayed phases was 0.81 and 0.83, respectively. The specificity for the early and delayed phases were 0.86 and 0.80, respectively.

Role of Functional Neuroimaging with 123I-MIBG and 123I-FP-CIT in De Novo Parkinson's Disease: A Multicenter Study

BACKGROUND

Parkinson's disease is a progressive neurodegenerative disorder, with incidence and prevalence rates of 8-18 per 100,000 people per year and 0.3-1%, respectively. As parkinsonian symptoms do not appear until approximately 50-60% of the nigral DA-releasing neurons have been lost, the impact of routine structural imaging findings is minimal at early stages, making Parkinson's disease an ideal condition for the application of functional imaging techniques. The aim of this multicenter study is to assess whether 123I-FP-CIT (DAT-SPECT), 123I-MIBG (mIBG-scintigraphy) or an association of both exams presents the highest diagnostic accuracy in de novo PD patients.

METHODS

288 consecutive patients with suspected diagnoses of Parkinson's disease or non- Parkinson's disease syndromes were analyzed in the present Italian multicenter retrospective study. All subjects were de novo, drug-naive patients and met the inclusion criteria of having undergone both DAT-SPECT and mIBG-scintigraphy within one month of each other.

RESULTS

The univariate analysis including age and both mIBG-SPECT and DAT-SPECT parameters showed that the only significant values for predicting Parkinson's disease in our population were eH/M, lH/M, ESS and LSS obtained from mIBG-scintigraphy (p < 0.001).

CONCLUSIONS

mIBG-scintigraphy shows higher diagnostic accuracy in de novo Parkinson's disease patients than DAT-SPECT, so given the superiority of the MIBG study, the combined use of both exams does not appear to be mandatory in the early phase of Parkinson's disease.

Bayesian Optimization with Support Vector Machine Model for Parkinson Disease Classification

Parkinson's disease (PD) has become widespread these days all over the world. PD affects the nervous system of the human and also affects a lot of human body parts that are connected via nerves. In order to make a classification for people who suffer from PD and who do not suffer from the disease, an advanced model called Bayesian Optimization-Support Vector Machine (BO-SVM) is presented in this paper for making the classification process. Bayesian Optimization (BO) is a hyperparameter tuning technique for optimizing the hyperparameters of machine learning models in order to obtain better accuracy. In this paper, BO is used to optimize the hyperparameters for six machine learning models, namely, Support Vector Machine (SVM), Random Forest (RF), Logistic Regression (LR), Naive Bayes (NB), Ridge Classifier (RC), and Decision Tree (DT). The dataset used in this study consists of 23 features and 195 instances. The class label of the target feature is 1 and 0, where 1 refers to the person suffering from PD and 0 refers to the person who does not suffer from PD. Four evaluation metrics, namely, accuracy, F1-score, recall, and precision were computed to evaluate the performance of the classification models used in this paper. The performance of the six machine learning models was tested on the dataset before and after the process of hyperparameter tuning. The experimental results demonstrated that the SVM model achieved the best results when compared with other machine learning models before and after the process of hyperparameter tuning, with an accuracy of 92.3% obtained using BO.

High clinical diagnostic accuracy of combined salivary gland and myocardial metaiodobenzylguanidine scintigraphy in the diagnosis of Parkinson's disease

Background

Decreased myocardial uptake of ¹³¹I-metaiodobenzylguanidine (MIBG) is known to be an important feature to diagnose Parkinson's disease (PD). However, the diagnosis accuracy of myocardial MIBG scintigraphy alone is often unsatisfying. Recent studies have found that the MIBG uptake of the major salivary glands was reduced in PD patients as well.

Purpose

To evaluate the diagnostic value of major salivary gland MIBG scintigraphy in PD, and explore the potential role of myocardial MIBG scintigraphy combined with salivary gland MIBG scintigraphy in distinguishing PD from non-PD (NPD).

Methods

Thirty-seven subjects were performed with ¹³¹I-MIBG scintigraphy. They were classified into the PD group (N = 18) and the NPD group (N = 19), based on clinical diagnostic criteria, DAT PET and ¹⁸F-FDG PET imaging findings. Images of salivary glands and myocardium were outlined to calculated the MIBG uptake ratios.

Results

The combination of left parotid and left submandibular gland early images had a good performance in distinguishing PD from NPD, with sensitivity, specificity, and accuracy of 50.00, 94.74, and 72.37%, respectively. Combining the major salivary gland and myocardial scintigraphy results in the early period showed a good diagnostic value with AUC, sensitivity and specificity of 0.877, 77.78, and 94.74%, respectively. Meanwhile, in the delayed period yield an excellent diagnostic value with AUC, sensitivity and specificity of 0.904, 88.89, and 84.21%, respectively.

Conclusion

¹³¹I-MIBG salivary gland scintigraphy assisted in the diagnosis and differential diagnosis of PD. The combination of major salivary gland and myocardial ¹³¹I-MIBG scintigraphy further increased the accuracy of PD diagnosis.

Analysis of Parkinson's Disease Using an Imbalanced-Speech Dataset by Employing Decision Tree Ensemble Methods

Parkinson's disease (PD) currently affects approximately 10 million people worldwide. The detection of PD positive subjects is vital in terms of disease prognostics, diagnostics, management and treatment. Different types of early symptoms, such as speech impairment and changes in writing, are associated with Parkinson disease. To classify potential patients of PD, many researchers used machine learning algorithms in various datasets related to this disease. In our research, we study the dataset of the PD vocal impairment feature, which is an imbalanced dataset. We propose comparative performance evaluation using various decision tree ensemble methods, with or without oversampling techniques. In addition, we compare the performance of classifiers with different sizes of ensembles and various ratios of the minority class and the majority class with oversampling and undersampling. Finally, we combine feature selection with best-performing ensemble classifiers. The result shows that AdaBoost, random forest, and decision tree developed for the RUSBoost imbalanced dataset perform well in performance metrics such as precision, recall, F1-score, area under the receiver operating characteristic curve (AUROC) and the geometric mean. Further, feature selection methods, namely lasso and information gain, were used to screen the 10 best features using the best ensemble classifiers. AdaBoost with information gain feature selection method is the best performing ensemble method with an F1-score of 0.903.

Differential Diagnosis of Alzheimer Disease vs. Mild Cognitive Impairment Based on Left Temporal Lateral Lobe Hypomethabolism on 18F-FDG PET/CT and Automated Classifiers

Purpose: We evaluate the ability of Artificial Intelligence with automatic classification methods applied to semi-quantitative data from brain ¹⁸F-FDG PET/CT to improve the differential diagnosis between Alzheimer Disease (AD) and Mild Cognitive Impairment (MCI). Procedures: We retrospectively analyzed a total of 150 consecutive patients who underwent diagnostic evaluation for suspected AD (n = 67) or MCI (n = 83). All patients received brain 18F-FDG PET/CT according to the international guidelines, and images were analyzed both Qualitatively (QL) and Quantitatively (QN), the latter by a fully automated post-processing software that produced a z score metabolic map of 25 anatomically different cortical regions. A subset of n = 122 cases with a confirmed diagnosis of AD (n = 53) or MDI (n = 69) by 18–24-month clinical follow-up was finally included in the study. Univariate analysis and three automated classification models (classification tree –ClT-, ridge classifier –RC- and linear Support Vector Machine –lSVM-) were considered to estimate the ability of the z scores to discriminate between AD and MCI cases in. Results: The univariate analysis returned 14 areas where the z scores were significantly different between AD and MCI groups, and the classification accuracy ranged between 74.59% and 76.23%, with ClT and RC providing the best results. The best classification strategy consisted of one single split with a cut-off value of ≈ −2.0 on the z score from temporal lateral left area: cases below this threshold were classified as AD and those above the threshold as MCI. Conclusions: Our findings confirm the usefulness of brain 18F-FDG PET/CT QL and QN analyses in differentiating AD from MCI. Moreover, the combined use of automated classifications models can improve the diagnostic process since its use allows identification of a specific hypometabolic area involved in AD cases in respect to MCI. This data improves the traditional 18F-FDG PET/CT image interpretation and the diagnostic assessment of cognitive disorders.

Diagnostic classification of Parkinson’s disease based on non-motor manifestations and machine learning strategies

Non-motor manifestations of Parkinson’s disease (PD) appear early and have a significant impact on the quality of life of patients, but few studies have evaluated their predictive potential with machine learning algorithms. We evaluated 9 algorithms for discriminating PD patients from controls using a wide collection of non-motor clinical PD features from two databases: Biocruces (96 subjects) and PPMI (687 subjects). In addition, we evaluated whether the combination of both databases could improve the individual results. For each database 2 versions with different granularity were created and a feature selection process was performed. We observed that most of the algorithms were able to detect PD patients with high accuracy (>80%). Support Vector Machine and Multi-Layer Perceptron obtained the best performance, with an accuracy of 86.3% and 84.7%, respectively. Likewise, feature selection led to a significant reduction in the number of variables and to better performance. Besides, the enrichment of Biocruces database with data from PPMI moderately benefited the performance of the classification algorithms, especially the recall and to a lesser extent the accuracy, while the precision worsened slightly. The use of interpretable rules obtained by the RIPPER algorithm showed that simply using two variables (autonomic manifestations and olfactory dysfunction), it was possible to achieve an accuracy of 84.4%. Our study demonstrates that the analysis of non-motor parameters of PD through machine learning techniques can detect PD patients with high accuracy and recall, and allows us to select the most discriminative non-motor variables to create potential tools for PD screening.

Manual and semi-automated approaches to MIBG myocardial scintigraphy in patients with Parkinson's disease

Objective

This study investigates the effects of manual and semi-automatic methods for assessing MIBG semi-quantitative indices in a clinical setting.

Materials and methods

We included ¹²³I-MIBG scans obtained in 35 patients with idiopathic Parkinson's Disease. Early and late heart-to-mediastinum (H/M) ratios were calculated from ¹²³I-MIBG images using regions of interest (ROIs) placed over the heart and the mediastinum. The ROIs were derived using two approaches: (i) manually drawn and (ii) semi-automatic fixed-size ROIs using anatomical landmarks. Expert, moderate-expert, and not expert raters applied the ROIs procedures and interpreted the ¹²³I-MIBG images. We evaluated the inter and intra-rater agreements in assessing ¹²³I-MIBG H/M ratios.

Results

A moderate agreement in the raters' classification of pathological and non-pathological scores emerged regarding early and late H/M ratio values (κ = 0.45 and 0.69 respectively), applying the manual method, while the early and late H/M ratios obtained with the semi-automatic method reached a good agreement among observers (κ = 0.78). Cohen-Kappa values revealed that the semi-automatic method improved the agreement between expert and inexpert raters: the agreement improved from a minimum of 0.29 (fair, for early H/M) and 0.69 (substantial, in late H/M) with the manual method, to 0.90 (perfect, in early H/M) and 0.87 (perfect, in late H/M) with the semi-automatic method.

Conclusion

The use of the semi-automatic method improves the agreement among raters in classifying' H/M ratios as pathological or non-pathological, namely for inexpert readers. These results have important implications for semi-quantitative assessment of ¹²³I-MIBG images in clinical routine.

123I-Ioflupane SPECT and 18F-FDG PET Combined Use in the Characterization of Movement and Cognitive Associated Disorders in Neurodegenerative Diseases

BACKGROUND

Both movement (MD) and cognitive (CD) disorders can occur associated in some neurodegenerative diseases, such as Parkinson's disease (PD) and Alzheimer's disease (AD).

OBJECTIVE

We further investigated the usefulness of 123I-Ioflupane SPECT and 18F-FDG PET combined use in patients with these disorders in the early stage.

METHODS

We retrospectively enrolled twenty-five consecutive patients with MD and CD clinical symptoms of recent appearance. All patients had undergone neurologic examination, neuropsychological tests, and magnetic resonance imaging. 123I-Ioflupane SPECT was performed in all cases, followed by 18F-FDG PET two weeks later. In the two procedures, both qualitative (QL) and quantitative (QN) image analyses were determined.

RESULTS

In patients with both 123I-Ioflupane SPECT and 18F-FDG PET pathologic data, associated dopaminergic and cognitive impairments were confirmed in 56% of cases. Pathologic SPECT with normal PET in 16% of cases could diagnose MD and exclude an associated CD, despite clinical symptoms. On the contrary, normal SPECT with pathologic PET in 28% of cases could exclude basal ganglia damage while confirming CD. QN 123I-Ioflupane SPECT analysis showed better performance than QL since QN correctly characterized two cases of MD with normal QL. Moreover, correct classification of normal metabolism was made only by QN analysis of 18F-FDG PET in four cases, despite suspect areas of hypometabolism at QL.

CONCLUSION

The combined use of these imaging procedures proved a reliable diagnostic tool to accurately identify and characterize MD and CD in early stage. QN analysis was effective in supporting QL evaluation, and its routine use is suggested, especially with inconclusive QL.

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 techniques support nuclear medicine modalities to improve the diagnosis of Parkinson’s disease and Parkinsonian syndromes

Purpose

The aim of this review is to discuss the most significant contributions about the role of Artificial Intelligence (AI) techniques to support the diagnosis of movement disorders through nuclear medicine modalities.

Methods

The work is based on a selection of papers available on PubMed, Scopus and Web of Sciences. Articles not written in English were not considered in this study.

Results

Many papers are available concerning the increasing contribution of machine learning techniques to classify Parkinson’s disease (PD), Parkinsonian syndromes and Essential Tremor (ET) using data derived from brain SPECT with dopamine transporter radiopharmaceuticals. Other papers investigate by AI techniques data obtained by 123I-MIBG myocardial scintigraphy to differentially diagnose PD and other Parkinsonian syndromes.

Conclusion

The recent literature provides strong evidence that AI techniques can play a fundamental role in the diagnosis of movement disorders by means of nuclear medicine modalities, therefore paving the way towards personalized medicine.

Machine Learning in Nuclear Medicine: Part 2-Neural Networks and Clinical Aspects

This article is the second part in our machine learning series. Part 1 provided a general overview of machine learning in nuclear medicine. Part 2 focuses on neural networks. We start with an example illustrating how neural networks work and a discussion of potential applications. Recognizing that there is a spectrum of applications, we focus on recent publications in the areas of image reconstruction, low-dose PET, disease detection, and models used for diagnosis and outcome prediction. Finally, since the way machine learning algorithms are reported in the literature is extremely variable, we conclude with a call to arms regarding the need for standardized reporting of design and outcome metrics and we propose a basic checklist our community might follow going forward.