Machine Learning Models for Diagnosis of Parkinson's Disease Using Multiple Structural Magnetic Resonance Imaging Features

Unlocking the potential: T1-weighed MRI as a powerful predictor of levodopa response in Parkinson's disease

BACKGROUND

The efficacy of levodopa, the most crucial metric for Parkinson's disease diagnosis and treatment, is traditionally gauged through the levodopa challenge test, which lacks a predictive model. This study aims to probe the predictive power of T1-weighted MRI, the most accessible modality for levodopa response.

METHODS

This retrospective study used two datasets: from the Parkinson's Progression Markers Initiative (219 records) and the external clinical dataset from Ruijin Hospital (217 records). A novel feature extraction method using MedicalNet, a pre-trained deep learning network, along with three previous approaches was applied. Three machine learning models were trained and tested on the PPMI dataset and included clinical features, imaging features, and their union set, using the area under the curve (AUC) as the metric. The most significant brain regions were visualized. The external clinical dataset was further evaluated using trained models. A paired one-tailed t-test was performed between the two sets; statistical significance was set at p < 0.001.

RESULTS

For 46 test set records (mean age, 62 ± 9 years, 28 men), MedicalNet-extracted features demonstrated a consistent improvement in all three machine learning models (SVM 0.83 ± 0.01 versus 0.73 ± 0.01, XgBoost 0.80 ± 0.04 versus 0.74 ± 0.02, MLP 0.80 ± 0.03 versus 0.70 ± 0.07, p < 0.001). Both feature sets were validated on the clinical dataset using SVM, where MedicalNet features alone achieved an AUC of 0.64 ± 0.03. Key responsible brain regions were visualized.

CONCLUSION

The T1-weighed MRI features were more robust and generalizable than the clinical features in prediction; their combination provided the best results. T1-weighed MRI provided insights on specific regions responsible for levodopa response prediction.

CRITICAL RELEVANCE STATEMENT

This study demonstrated that T1w MRI features extracted by a deep learning model have the potential to predict the levodopa response of PD patients and are more robust than widely used clinical information, which might help in determining treatment strategy.

KEY POINTS

This study investigated the predictive value of T1w features for levodopa response. MedicalNet extractor outperformed all other previously published methods with key region visualization. T1w features are more effective than clinical information in levodopa response prediction.

Brain connectivity for subtypes of parkinson's disease using structural MRI

Objective. Delineating Parkinson's disease (PD) into distinct subtypes is a major challenge. Most studies use clinical symptoms to label PD subtypes while our work uses an imaging-based data-mining approach to subtype PD. Our study comprises two major objectives - firstly, subtyping Parkinson's patients based on grey matter information from structural magnetic resonance imaging scans of human brains; secondly, comparative structural brain connectivity analysis of PD subtypes derived from the former step.Approach. Source-based-morphometry decomposition was performed on 131 Parkinson's patients and 78 healthy controls from PPMI dataset, to derive at components (regions) with significance in disease and high effect size. The loading coefficients of significant components were thresholded for arriving at subtypes. Further, regional grey matter maps of subtype-specific subjects were separately parcellated and employed for construction of subtype-specific association matrices using Pearson correlation. These association matrices were binarized using sparsity threshold and leveraged for structural brain connectivity analysis using network metrics.Main results. Two distinct Parkinson's subtypes (namely A and B) were detected employing loadings of two components satisfying the selection criteria, and a third subtype (AB) was detected, common to these two components. Subtype A subjects were highly weighted in inferior, middle and superior frontal gyri while subtype B subjects in inferior, middle and superior temporal gyri. Network metrics analyses through permutation test revealed significant inter-subtype differences (p < 0.05) in clustering coefficient, local efficiency, participation coefficient and betweenness centrality. Moreover, hubs were obtained using betweenness centrality and mean network degree.Significance. MRI-based data-driven subtypes show frontal and temporal lobes playing a key role in PD. Graph theory-driven brain network analyses could untangle subtype-specific differences in structural brain connections showing differential network architecture. Replication of these initial results in other Parkinson's datasets may be explored in future. Clinical Relevance- Investigating structural brain connections in Parkinson's disease may provide subtype-specific treatment.

Comparison of Anatomical and Diffusion MRI for detecting Parkinson's Disease using Deep Convolutional Neural Network

Parkinson's disease (PD) is a progressive neurodegenerative disease that affects over 10 million people worldwide. Brain atrophy and microstructural abnormalities tend to be more subtle in PD than in other age-related conditions such as Alzheimer's disease, so there is interest in how well machine learning methods can detect PD in radiological scans. Deep learning models based on convolutional neural networks (CNNs) can automatically distil diagnostically useful features from raw MRI scans, but most CNN-based deep learning models have only been tested on T1-weighted brain MRI. Here we examine the added value of diffusion-weighted MRI (dMRI) - a variant of MRI, sensitive to microstructural tissue properties - as an additional input in CNN-based models for PD classification. Our evaluations used data from 3 separate cohorts - from Chang Gung University, the University of Pennsylvania, and the PPMI dataset. We trained CNNs on various combinations of these cohorts to find the best predictive model. Although tests on more diverse data are warranted, deep-learned models from dMRI show promise for PD classification.Clinical Relevance- This study supports the use of diffusion-weighted images as an alternative to anatomical images for AI-based detection of Parkinson's disease.

Comparison of Anatomical and Diffusion MRI for detecting Parkinson's Disease using Deep Convolutional Neural Network

Parkinson's disease (PD) is a progressive neurodegenerative disease that affects over 10 million people worldwide. Brain atrophy and microstructural abnormalities tend to be more subtle in PD than in other age-related conditions such as Alzheimer's disease, so there is interest in how well machine learning methods can detect PD in radiological scans. Deep learning models based on convolutional neural networks (CNNs) can automatically distil diagnostically useful features from raw MRI scans, but most CNN-based deep learning models have only been tested on T1-weighted brain MRI. Here we examine the added value of diffusion-weighted MRI (dMRI) - a variant of MRI, sensitive to microstructural tissue properties - as an additional input in CNN-based models for PD classification. Our evaluations used data from 3 separate cohorts - from Chang Gung University, the University of Pennsylvania, and the PPMI dataset. We trained CNNs on various combinations of these cohorts to find the best predictive model. Although tests on more diverse data are warranted, deep-learned models from dMRI show promise for PD classification.

Clinical Relevance

This study supports the use of diffusion-weighted images as an alternative to anatomical images for AI-based detection of Parkinson's disease.

Long-term cognitive decline prediction based on multi-modal data using Multimodal3DSiameseNet: transfer learning from Alzheimer's disease to Parkinson's disease

PURPOSE

Monitoring and predicting the cognitive state of subjects with neurodegenerative disorders is crucial to provide appropriate treatment as soon as possible. In this work, we present a machine learning approach using multimodal data (brain MRI and clinical) from two early medical visits, to predict the longer-term cognitive decline of patients. Using transfer learning, our model can be successfully transferred from one neurodegenerative disease (Alzheimer's) to another (Parkinson's).

METHODS

Our model is a Deep Neural Network with siamese sub-modules dedicated to extracting features from each modality. We pre-train it with data from ADNI (Alzheimer's disease), then transfer it on the smaller PPMI dataset (Parkinson's disease). We show that, even when we do not fine-tune the filters learnt from the ADNI MRIs, the transferred model's results are satisfying on PPMI.

RESULTS

The first main result is that our model provides satisfying long-term predictions of cognitive decline from any pair of early visits, with no fixed time delay between these visits (provided the potential decline has started at the second visit). The second main result is that the prediction performance on Parkinson's dataset (PPMI) reaches an AUC of 0.81 on PPMI after transfer learning from Alzheimer's dataset (ADNI), without even having to re-train the image filters, versus an AUC of 0.72 for the model trained from scratch on PPMI.

CONCLUSIONS

First, our model is effective for predicting long-term cognitive decline from only two visits, even with irregular intervals of time. When dealing with neurodegenerative diseases, where patients often miss some control visits, this is an important finding. Second, our model is able to transfer the knowledge learnt from one neurodegenerative disease (Alzheimer's) to another (Parkinson's), when using the same imaging modalities (brain MRI) and different clinical variables. This makes it usable even for diseases that are rare or under-studied.

Combined brain network topological metrics with machine learning algorithms to identify essential tremor

BACKGROUND AND OBJECTIVE

Essential tremor (ET) is a common movement syndrome, and the pathogenesis mechanisms, especially the brain network topological changes in ET are still unclear. The combination of graph theory (GT) analysis with machine learning (ML) algorithms provides a promising way to identify ET from healthy controls (HCs) at the individual level, and further help to reveal the topological pathogenesis in ET.

METHODS

Resting-state functional magnetic resonance imaging (fMRI) data were obtained from 101 ET and 105 HCs. The topological properties were analyzed by using GT analysis, and the topological metrics under every single threshold and the area under the curve (AUC) of all thresholds were used as features. Then a Mann-Whitney U-test and least absolute shrinkage and selection operator (LASSO) were conducted to feature dimensionality reduction. Four ML algorithms were adopted to identify ET from HCs. The mean accuracy, mean balanced accuracy, mean sensitivity, mean specificity, and mean AUC were used to evaluate the classification performance. In addition, correlation analysis was carried out between selected topological features and clinical tremor characteristics.

RESULTS

All classifiers achieved good classification performance. The mean accuracy of Support vector machine (SVM), logistic regression (LR), random forest (RF), and naïve bayes (NB) was 84.65, 85.03, 84.85, and 76.31%, respectively. LR classifier achieved the best classification performance with 85.03% mean accuracy, 83.97% sensitivity, and an AUC of 0.924. Correlation analysis results showed that 2 topological features negatively and 1 positively correlated with tremor severity.

CONCLUSION

These results demonstrated that combining topological metrics with ML algorithms could not only achieve high classification accuracy for discrimination ET from HCs but also help us to reveal the potential topological pathogenesis of ET.