skip to main content


Title: Machine Learning for Parkinson’s Disease Diagnosis Using Fundus Eye Images
Purpose: Parkinson’s Disease (PD) is the second most common form of neural degeneration and defined by the decay of dopaminergic cells in the substantia nigra. The current standard for diagnosing PD occurs once 80% of dopaminergic cells have decayed. The degradation of these cells has been shown to create thinning of the retina walls and retina microvasculature. This work serves to find machine learning techniques to provide PD diagnosis using non-invasive fundus eye images. Materials and Methods: Two age and gender matched datasets where constructed using data from the UK Biobank (UKB) and data collected at the University of Florida (UF). The first dataset consists of 476 fundus eye images, 238 CN and 238 PD, sourced entirely from the UKB database. The second dataset, UF-UKB, consist of 100 images, 28 CN and 72 PD, collected at UF and 44 CN images from UKB. A second set of datasets, UKB-Green and UF-UKB-Green, were created using the green color channels to improve vessel segmentation. Vessel segmentation was performed using U-Net segmentation network. The vessel maps served as inputs to SVM classifying networks. Saliency maps were created to assess areas of interest for the networks. Results: The top performing SVM network for the UKB and UKB-Green datasets were the sigmoid SVM networks which achieved accuracies of .698 and .719 respectively. Meanwhile the top performing networks for the UF-UKB and UF-UKB-Green datasets where the linear SVM networks which achieved accuracies of .821 and .857 respectively. The saliency maps indicate that the different networks focused on different vessel structures with the most successful networks focusing more on smaller vessels. Conclusion: The results indicate that the machine learning networks can classify PD based on retina vasculature, with the key features being smaller blood vessels. The proposed methods further support the idea that changes in brain physiology can be observed in the eye. Machine learning networks can be applied to clinically available data and still provide accurate predictions Clinical Relevance statement, not to exceed 200 characters: The work illustrates the feasibility of utilizing eye images as a potential method for diagnosing PD, opposed to the current method of using motor symptoms.  more » « less
Award ID(s):
1908299
NSF-PAR ID:
10296704
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
Annual Meeting of Radiology Society of North America (RSNA)
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    Introduction: Alzheimer’s disease (AD) causes progressive irreversible cognitive decline and is the leading cause of dementia. Therefore, a timely diagnosis is imperative to maximize neurological preservation. However, current treatments are either too costly or limited in availability. In this project, we explored using retinal vasculature as a potential biomarker for early AD diagnosis. This project focuses on stage 3 of a three-stage modular machine learning pipeline which consisted of image quality selection, vessel map generation, and classification [1]. The previous model only used support vector machine (SVM) to classify AD labels which limited its accuracy to 82%. In this project, random forest and gradient boosting were added and, along with SVM, combined into an ensemble classifier, raising the classification accuracy to 89%. Materials and Methods: Subjects classified as AD were those who were diagnosed with dementia in “Dementia Outcome: Alzheimer’s disease” from the UK Biobank Electronic Health Records. Five control groups were chosen with a 5:1 ratio of control to AD patients where the control patients had the same age, gender, and eye side image as the AD patient. In total, 122 vessel images from each group (AD and control) were used. The vessel maps were then segmented from fundus images through U-net. A t-test feature selection was first done on the training folds and the selected features was fed into the classifiers with a p-value threshold of 0.01. Next, 20 repetitions of 5-fold cross validation were performed where the hyperparameters were solely tuned on the training data. An ensemble classifier consisting of SVM, gradient boosting tree, and random forests was built and the final prediction was made through majority voting and evaluated on the test set. Results and Discussion: Through ensemble classification, accuracy increased by 4-12% relative to the individual classifiers, precision by 9-15%, sensitivity by 2-9%, specificity by at least 9-16%, and F1 score by 712%. Conclusions: Overall, a relatively high classification accuracy was achieved using machine learning ensemble classification with SVM, random forest, and gradient boosting. Although the results are very promising, a limitation of this study is that the requirement of needing images of sufficient quality decreased the amount of control parameters that can be implemented. However, through retinal vasculature analysis, this project shows machine learning’s high potential to be an efficient, more cost-effective alternative to diagnosing Alzheimer’s disease. Clinical Application: Using machine learning for AD diagnosis through retinal images will make screening available for a broader population by being more accessible and cost-efficient. Mobile device based screening can also be enabled at primary screening in resource-deprived regions. It can provide a pathway for future understanding of the association between biomarkers in the eye and brain. 
    more » « less
  2. Abstract

    Attention control is a basic behavioral process that has been studied for decades. The currently best models of attention control are deep networks trained on free-viewing behavior to predict bottom-up attention control – saliency. We introduce COCO-Search18, the first dataset of laboratory-qualitygoal-directed behaviorlarge enough to train deep-network models. We collected eye-movement behavior from 10 people searching for each of 18 target-object categories in 6202 natural-scene images, yielding$$\sim$$300,000 search fixations. We thoroughly characterize COCO-Search18, and benchmark it using three machine-learning methods: a ResNet50 object detector, a ResNet50 trained on fixation-density maps, and an inverse-reinforcement-learning model trained on behavioral search scanpaths. Models were also trained/tested on images transformed to approximate a foveated retina, a fundamental biological constraint. These models, each having a different reliance on behavioral training, collectively comprise the new state-of-the-art in predicting goal-directed search fixations. Our expectation is that future work using COCO-Search18 will far surpass these initial efforts, finding applications in domains ranging from human-computer interactive systems that can anticipate a person’s intent and render assistance to the potentially early identification of attention-related clinical disorders (ADHD, PTSD, phobia) based on deviation from neurotypical fixation behavior.

     
    more » « less
  3. null (Ed.)
    Abstract Alzheimer's disease is the leading cause of dementia. The long progression period in Alzheimer's disease provides a possibility for patients to get early treatment by having routine screenings. However, current clinical diagnostic imaging tools do not meet the specific requirements for screening procedures due to high cost and limited availability. In this work, we took the initiative to evaluate the retina, especially the retinal vasculature, as an alternative for conducting screenings for dementia patients caused by Alzheimer's disease. Highly modular machine learning techniques were employed throughout the whole pipeline. Utilizing data from the UK Biobank, the pipeline achieved an average classification accuracy of 82.44%. Besides the high classification accuracy, we also added a saliency analysis to strengthen this pipeline's interpretability. The saliency analysis indicated that within retinal images, small vessels carry more information for diagnosing Alzheimer's diseases, which aligns with related studies. 
    more » « less
  4. Ensemble-based change detection can improve map accuracies by combining information from multiple datasets. There is a growing literature investigating ensemble inputs and applications for forest disturbance detection and mapping. However, few studies have evaluated ensemble methods other than Random Forest classifiers, which rely on uninterpretable “black box” algorithms with hundreds of parameters. Additionally, most ensemble-based disturbance maps do not utilize independently and systematically collected field-based forest inventory measurements. Here, we compared three approaches for combining change detection results generated from multi-spectral Landsat time series with forest inventory measurements to map forest harvest events at an annual time step. We found that seven-parameter degenerate decision tree ensembles performed at least as well as 500-tree Random Forest ensembles trained and tested on the same LandTrendr segmentation results and both supervised decision tree methods consistently outperformed the top-performing voting approach (majority). Comparisons with an existing national forest disturbance dataset indicated notable improvements in accuracy that demonstrate the value of developing locally calibrated, process-specific disturbance datasets like the harvest event maps developed in this study. Furthermore, by using multi-date forest inventory measurements, we are able to establish a lower bound of 30% basal area removal on detectable harvests, providing biophysical context for our harvest event maps. Our results suggest that simple interpretable decision trees applied to multi-spectral temporal segmentation outputs can be as effective as more complex machine learning approaches for characterizing forest harvest events ranging from partial clearing to clear cuts, with important implications for locally accurate mapping of forest harvests and other types of disturbances. 
    more » « less
  5. Abstract

    Age-related macular degeneration (AMD) is the principal cause of blindness in developed countries, and its prevalence will increase to 288 million people in 2040. Therefore, automated grading and prediction methods can be highly beneficial for recognizing susceptible subjects to late-AMD and enabling clinicians to start preventive actions for them. Clinically, AMD severity is quantified by Color Fundus Photographs (CFP) of the retina, and many machine-learning-based methods are proposed for grading AMD severity. However, few models were developed to predict the longitudinal progression status, i.e. predicting future late-AMD risk based on the current CFP, which is more clinically interesting. In this paper, we propose a new deep-learning-based classification model (LONGL-Net) that can simultaneously grade the current CFP and predict the longitudinal outcome, i.e. whether the subject will be in late-AMD in the future time-point. We design a new temporal-correlation-structure-guided Generative Adversarial Network model that learns the interrelations of temporal changes in CFPs in consecutive time-points and provides interpretability for the classifier's decisions by forecasting AMD symptoms in the future CFPs. We used about 30,000 CFP images from 4,628 participants in the Age-Related Eye Disease Study. Our classifier showed average 0.905 (95% CI: 0.886–0.922) AUC and 0.762 (95% CI: 0.733–0.792) accuracy on the 3-class classification problem of simultaneously grading current time-point's AMD condition and predicting late AMD progression of subjects in the future time-point. We further validated our model on the UK Biobank dataset, where our model showed average 0.905 accuracy and 0.797 sensitivity in grading 300 CFP images.

     
    more » « less