This content will become publicly available on December 1, 2025
Title: Deep learning predicts prevalent and incident Parkinson’s disease from UK Biobank fundus imaging
Parkinson’s disease is the world’s fastest-growing neurological disorder. Research to elucidate the mechanisms of Parkinson’s disease and automate diagnostics would greatly improve the treatment of patients with Parkinson’s disease. Current diagnostic methods are expensive and have limited availability. Considering the insidious and preclinical onset and progression of the disease, a desirable screening should be diagnostically accurate even before the onset of symptoms to allow medical interventions. We highlight retinal fundus imaging, often termed a window to the brain, as a diagnostic screening modality for Parkinson’s disease. We conducted a systematic evaluation of conventional machine learning and deep learning techniques to classify Parkinson’s disease from UK Biobank fundus imaging. Our results suggest Parkinson’s disease individuals can be differentiated from age and gender-matched healthy subjects with 68% accuracy. This accuracy is maintained when predicting either prevalent or incident Parkinson’s disease. Explainability and trustworthiness are enhanced by visual attribution maps of localized biomarkers and quantified metrics of model robustness to data perturbations. more »« less
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.
Poor access to eye care is a major global challenge that could be ameliorated by low-cost, portable, and easy-to-use diagnostic technologies. Diffuser-based imaging has the potential to enable inexpensive, compact optical systems that can reconstruct a focused image of an object over a range of defocus errors. Here, we present a diffuser-based computational funduscope that reconstructs important clinical features of a model eye. Compared to existing diffuser-imager architectures, our system features an infinite-conjugate design by relaying the ocular lens onto the diffuser. This offers shift-invariance across a wide field-of-view (FOV) and an invariant magnification across an extended depth range. Experimentally, we demonstrate fundus image reconstruction over a 33°FOV and robustness to ±4D refractive error using a constant point-spread-function. Combined with diffuser-based wavefront sensing, this technology could enable combined ocular aberrometry and funduscopic screening through a single diffuser sensor.
Lin, Hely; Fang, Ruogu
(, Biomedical Engineering Society Annual Meeting)
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.
Singh, Shagundeep; Banoub, Raphael; Sanghvi, Harshal A; Agarwal, Ankur; Chalam, KV; Gupta, Shailesh; Pandya, Abhijit S
(, Current Medical Imaging Reviews)
Kim, Euishin E
(Ed.)
Background:Early disease detection is emphasized within ophthalmology now more than ever, and as a result, clinicians and innovators turn to deep learning toexpedite accurate diagnosis and mitigate treatment delay. Efforts concentrate on the creation of deep learning systems that analyze clinical imagedata to detect disease-specific features with maximum sensitivity. Moreover, these systems hold promise of early accurate diagnosis and treatmentof patients with common progressive diseases. DenseNet, ResNet, and VGG-16 are among a few of the deep learning Convolutional NeuralNetwork (CNN) algorithms that have been introduced and are being investigated for potential application within ophthalmology. Methods:In this study, the authors sought to create and evaluate a novel ensembled deep learning CNN model that analyzes a dataset of shuffled retinal colorfundus images (RCFIs) from eyes with various ocular disease features (cataract, glaucoma, diabetic retinopathy). Our aim was to determine (1) therelative performance of our finalized model in classifying RCFIs according to disease and (2) the diagnostic potential of the finalized model toserve as a screening test for specific diseases (cataract, glaucoma, diabetic retinopathy) upon presentation of RCFIs with diverse diseasemanifestations. Results:We found adding convolutional layers to an existing VGG-16 model, which was named as a proposed model in this article that, resulted insignificantly increased performance with 98% accuracy (p<0.05), including good diagnostic potential for binary disease detection in cataract,glaucoma, diabetic retinopathy. Conclusion:The proposed model was found to be suitable and accurate for a decision support system in Ophthalmology Clinical Framework.
Jung, Tony; Vij, Neeraj
(, Journal of Clinical Medicine)
First- and second-hand exposure to smoke or air pollutants is the primary cause of chronic obstructive pulmonary disease (COPD) pathogenesis, where genetic and age-related factors predispose the subject to the initiation and progression of obstructive lung disease. Briefly, airway inflammation, specifically bronchitis, initiates the lung disease, leading to difficulty in breathing (dyspnea) and coughing as initial symptoms, followed by air trapping and inhibition of the flow of air into the lungs due to damage to the alveoli (emphysema). In addition, mucus obstruction and impaired lung clearance mechanisms lead to recurring acute exacerbations causing progressive decline in lung function, eventually requiring lung transplant and other lifesaving interventions to prevent mortality. It is noteworthy that COPD is much more common in the population than currently diagnosed, as only 16 million adult Americans were reported to be diagnosed with COPD as of 2018, although an additional 14 million American adults were estimated to be suffering from COPD but undiagnosed by the current standard of care (SOC) diagnostic, namely the spirometry-based pulmonary function test (PFT). Thus, the main issue driving the adverse disease outcome and significant mortality for COPD is lack of timely diagnosis in the early stages of the disease. The current treatment regime for COPD emphysema is most effective when implemented early, on COPD onset, where alleviating symptoms and exacerbations with timely intervention(s) can prevent steep lung function decline(s) and disease progression to severe emphysema. Therefore, the key to efficiently combatting COPD relies on early detection. Thus, it is important to detect early regional pulmonary function and structural changes to monitor modest disease progression for implementing timely interventions and effectively eliminating emphysema progression. Currently, COPD diagnosis involves using techniques such as COPD screening questionnaires, PFT, arterial blood gas analysis, and/or lung imaging, but these modalities are limited in their capability for early diagnosis and real-time disease monitoring of regional lung function changes. Hence, promising emerging techniques, such as X-ray phase contrast, photoacoustic tomography, ultrasound computed tomography, electrical impedance tomography, the forced oscillation technique, and the impulse oscillometry system powered by robust artificial intelligence and machine learning analysis capability are emerging as novel solutions for early detection and real time monitoring of COPD progression for timely intervention. We discuss here the scope, risks, and limitations of current SOC and emerging COPD diagnostics, with perspective on novel diagnostics providing real time regional lung function monitoring, and predicting exacerbation and/or disease onset for prognosis-based timely intervention(s) to limit COPD–emphysema progression.
@article{osti_10539645,
place = {Country unknown/Code not available},
title = {Deep learning predicts prevalent and incident Parkinson’s disease from UK Biobank fundus imaging},
url = {https://par.nsf.gov/biblio/10539645},
DOI = {10.1038/s41598-024-54251-1},
abstractNote = {Parkinson’s disease is the world’s fastest-growing neurological disorder. Research to elucidate the mechanisms of Parkinson’s disease and automate diagnostics would greatly improve the treatment of patients with Parkinson’s disease. Current diagnostic methods are expensive and have limited availability. Considering the insidious and preclinical onset and progression of the disease, a desirable screening should be diagnostically accurate even before the onset of symptoms to allow medical interventions. We highlight retinal fundus imaging, often termed a window to the brain, as a diagnostic screening modality for Parkinson’s disease. We conducted a systematic evaluation of conventional machine learning and deep learning techniques to classify Parkinson’s disease from UK Biobank fundus imaging. Our results suggest Parkinson’s disease individuals can be differentiated from age and gender-matched healthy subjects with 68% accuracy. This accuracy is maintained when predicting either prevalent or incident Parkinson’s disease. Explainability and trustworthiness are enhanced by visual attribution maps of localized biomarkers and quantified metrics of model robustness to data perturbations.},
journal = {Scientific Reports},
volume = {14},
number = {1},
publisher = {Springer Nature},
author = {Tran, Charlie and Shen, Kai and Liu, Kang and Ashok, Akshay and Ramirez-Zamora, Adolfo and Chen, Jinghua and Li, Yulin and Fang, Ruogu},
}
Warning: Leaving National Science Foundation Website
You are now leaving the National Science Foundation website to go to a non-government website.
Website:
NSF takes no responsibility for and exercises no control over the views expressed or the accuracy of
the information contained on this site. Also be aware that NSF's privacy policy does not apply to this site.
An official website of the United States government
