Predicting Age-related Macular Degeneration Progression with Longitudinal Fundus Images Using Deep Learning

Lee, Jung Hwan; Wanyan, Tingyi; Chen, Qingyu; Keenan, Tiarnán D L; Glicksberg, Benjamin S.; Chew, Emily Y.; Lu, Zhiyong; Wang, Fei; Peng, Yifan

doi:10.1007/978-3-031-21014-3_2

Cited by 6 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, current approaches to automated analysis for macular atrophy generally do not incorporate longitudinal data, focusing on one instant in time. One way to incorporate longitudinal data is through the use of recurrent neural networks, such as the long short-term memory (LSTM) architecture, a modification of the recurrent neural network [38][39][40][41][42][43][44][45]. The LSTM architecture has been used in medical image analysis for the detection of cardiomegaly, consolidation, pleural effusion and hiatus hernia on X-ray and for Alzheimer's disease diagnosis [46][47].…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recurrent and Concurrent Prediction of Longitudinal Progression of Stargardt Atrophy and Geographic Atrophy

Mishra,

Wang,

et al. 2024

Preprint

View full text Add to dashboard Cite

Stargardt disease and age-related macular degeneration are the leading causes of blindness in the juvenile and geriatric populations, respectively. The formation of atrophic regions of the macula is a hallmark of the end-stages of both diseases. The progression of these diseases is tracked using various imaging modalities, two of the most common being fundus autofluorescence (FAF) imaging and spectral-domain optical coherence tomography (SD-OCT). This study seeks to investigate the use of longitudinal FAF and SD-OCT imaging (month 0, month 6, month 12, and month 18) data for the predictive modelling of future atrophy in Stargardt and geographic atrophy. To achieve such an objective, we develop a set of novel deep convolutional neural networks enhanced with recurrent network units for longitudinal prediction and concurrent learning of ensemble network units (termed ReConNet) which take advantage of improved retinal layer features beyond the mean intensity features. Using FAF images, the neural network presented in this paper achieved mean (standard deviation, SD) and median Dice coefficients of 0.895 (0.086) and 0.922 for Stargardt atrophy, and 0.864 (0.113) and 0.893 for geographic atrophy. Using SD-OCT images for Stargardt atrophy, the neural network achieved mean and median Dice coefficients of 0.882 (0.101) and 0.906, respectively. When predicting only the interval growth of the atrophic lesions with FAF images, mean (SD) and median Dice coefficients of 0.557 (0.094) and 0.559 were achieved for Stargardt atrophy, and 0.612 (0.089) and 0.601 for geographic atrophy. The prediction performance in OCT images is comparably good to that using FAF which opens a new, more efficient, and practical door in the assessment of atrophy progression for clinical trials and retina clinics, beyond widely used FAF. These results are highly encouraging for a high-performance interval growth prediction when more frequent or longer-term longitudinal data are available in our clinics. This is a pressing task for our next step in ongoing research.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Recurrent and Concurrent Prediction of Longitudinal Progression of Stargardt Atrophy and Geographic Atrophy

Mishra,

Wang,

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Previous research has demonstrated the use of AI and ML to analyze fundus photographs [14][15][16]. These papers primarily focused on disease detection [17,18], classification and grading [18,19], segmentation [20,21] and prediction [22] for retinopathy of prematurity (ROP) [23,24], diabetic retinopathy [18,25,26], age-related macular degeneration [21,[27][28][29][30], glaucoma [31][32][33], cataracts [34], lacrimal disorders [35], keratoconus [36], amblyopia [37] and optic nerve diseases [38,39]. Studies have demonstrated that AI and ML algorithms, including deep learning models such as convolutional neural networks (CNNs), RNNs, and Transformers, can accurately identify and classify different types of retinal lesions, such as hemorrhages, exudates, and micro-aneurysms [25,26].…”

Section: Introductionmentioning

confidence: 99%

“…These algorithms can analyze large datasets of fundus photographs and provide automated assessments of disease severity and progression. Furthermore, AI and ML have been utilized to predict the risk of developing certain retinal diseases, such as geographic atrophy, based on fundus image analysis [27,29]. By training algorithms on large datasets of fundus photographs and corresponding patient data, these technologies can identify patterns and markers that are indicative of disease progression or future complications [29].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Approach for Differentiating Etiologies of Pediatric Retinal Hemorrhages: A Multicenter Study

Khosravi,

Huck,

Shahraki

et al. 2023

IJMS

View full text Add to dashboard Cite

Retinal hemorrhages in pediatric patients can be a diagnostic challenge for ophthalmologists. These hemorrhages can occur due to various underlying etiologies, including abusive head trauma, accidental trauma, and medical conditions. Accurate identification of the etiology is crucial for appropriate management and legal considerations. In recent years, deep learning techniques have shown promise in assisting healthcare professionals in making more accurate and timely diagnosis of a variety of disorders. We explore the potential of deep learning approaches for differentiating etiologies of pediatric retinal hemorrhages. Our study, which spanned multiple centers, analyzed 898 images, resulting in a final dataset of 597 retinal hemorrhage fundus photos categorized into medical (49.9%) and trauma (50.1%) etiologies. Deep learning models, specifically those based on ResNet and transformer architectures, were applied; FastViT-SA12, a hybrid transformer model, achieved the highest accuracy (90.55%) and area under the receiver operating characteristic curve (AUC) of 90.55%, while ResNet18 secured the highest sensitivity value (96.77%) on an independent test dataset. The study highlighted areas for optimization in artificial intelligence (AI) models specifically for pediatric retinal hemorrhages. While AI proves valuable in diagnosing these hemorrhages, the expertise of medical professionals remains irreplaceable. Collaborative efforts between AI specialists and pediatric ophthalmologists are crucial to fully harness AI’s potential in diagnosing etiologies of pediatric retinal hemorrhages.

show abstract

Machine and deep learning for longitudinal biomedical data: a review of methods and applications

Cascarano,

Mur-Petit,

Hernández-González

et al. 2023

Artif Intell Rev

View full text Add to dashboard Cite

Exploiting existing longitudinal data cohorts can bring enormous benefits to the medical field, as many diseases have a complex and multi-factorial time-course, and start to develop long before symptoms appear. With the increasing healthcare digitisation, the application of machine learning techniques for longitudinal biomedical data may enable the development of new tools for assisting clinicians in their day-to-day medical practice, such as for early diagnosis, risk prediction, treatment planning and prognosis estimation. However, due to the heterogeneity and complexity of time-varying data sets, the development of suitable machine learning models introduces major challenges for data scientists as well as for clinical researchers. This paper provides a comprehensive and critical review of recent developments and applications in machine learning for longitudinal biomedical data. Although the paper provides a discussion of clustering methods, its primary focus is on the prediction of static outcomes, defined as the value of the event of interest at a given instant in time, using longitudinal features, which has emerged as the most commonly employed approach in healthcare applications. First, the main approaches and algorithms for building longitudinal machine learning models are presented in detail, including their technical implementations, strengths and limitations. Subsequently, most recent biomedical and clinical applications are reviewed and discussed, showing promising results in a wide range of medical specialties. Lastly, we discuss current challenges and consider future directions in the field to enhance the development of machine learning tools from longitudinal biomedical data.

show abstract

Predicting Age-related Macular Degeneration Progression with Longitudinal Fundus Images Using Deep Learning

Cited by 6 publications

References 21 publications

Recurrent and Concurrent Prediction of Longitudinal Progression of Stargardt Atrophy and Geographic Atrophy

Recurrent and Concurrent Prediction of Longitudinal Progression of Stargardt Atrophy and Geographic Atrophy

Deep Learning Approach for Differentiating Etiologies of Pediatric Retinal Hemorrhages: A Multicenter Study

Machine and deep learning for longitudinal biomedical data: a review of methods and applications

Contact Info

Product

Resources

About