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
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. 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
  3. Abstract

    Alterations in vascular networks, including angiogenesis and capillary regression, play key roles in disease, wound healing, and development. The spatial structures of blood vessels can be captured through imaging, but effective characterization of network architecture requires both metrics for quantification and software to carry out the analysis in a high‐throughput and unbiased fashion. We present Rapid Editable Analysis of Vessel Elements Routine (REAVER), an open‐source tool that researchers can use to analyze high‐resolution 2D fluorescent images of blood vessel networks, and assess its performance compared to alternative image analysis programs. Using a dataset of manually analyzed images from a variety of murine tissues as a ground‐truth, REAVER exhibited high accuracy and precision for all vessel architecture metrics quantified, including vessel length density, vessel area fraction, mean vessel diameter, and branchpoint count, along with the highest pixel‐by‐pixel accuracy for the segmentation of the blood vessel network. In instances where REAVER's automated segmentation is inaccurate, we show that combining manual curation with automated analysis improves the accuracy of vessel architecture metrics. REAVER can be used to quantify differences in blood vessel architectures, making it useful in experiments designed to evaluate the effects of different external perturbations (eg, drugs or disease states).

     
    more » « less
  4. Eye image segmentation is a critical step in eye tracking that has great influence over the final gaze estimate. Segmentation models trained using supervised machine learning can excel at this task, their effectiveness is determined by the degree of overlap between the narrow distributions of image properties defined by the target dataset and highly specific training datasets, of which there are few. Attempts to broaden the distribution of existing eye image datasets through the inclusion of synthetic eye images have found that a model trained on synthetic images will often fail to generalize back to real-world eye images. In remedy, we use dimensionality-reduction techniques to measure the overlap between the target eye images and synthetic training data, and to prune the training dataset in a manner that maximizes distribution overlap. We demonstrate that our methods result in robust, improved performance when tackling the discrepancy between simulation and real-world data samples.

     
    more » « less
  5. 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