Ensemble Deep Learning for Diabetic Retinopathy Detection Using Optical Coherence Tomography Angiography

Heisler, Morgan; Karst, Sonja; Lo, Julian; Mammo, Zaid; Yu, Timothy T.; Warner, Simon; Maberley, David; Beg, Mirza Faisal; Navajas, Eduardo V.; Sarunic, Marinko V.

doi:10.1167/tvst.9.2.20

Cited by 89 publications

(57 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data collected from SFU and OHSU were used to investigate the relative performance of federated learning for the classification of RDR in OCT en face images. The image acquisition protocol, severity grading, and en face OCTA generation algorithm were as described in previous reports from our groups [16], [17]. Images with a signal strength greater than eight out of ten, or with sufficient capillary network visibility through manual evaluation, were included in the SFU dataset [31].…”

Section: Referable Diabetic Retinopathy Classificationmentioning

confidence: 99%

“…The threechannel input for RDR classification was generated from a combination of OCTA en face images from the superficial vascular complex (SVC), OCTA en face from the deep vascular complex (DVC), and a maximum intensity projection calculated from both of the OCT structural en face SVC and DVC. The DVC and SVC boundary extraction algorithms were specific to the commercial OCT image acquisition system [16], [17]. As with the microvasculature segmentation experiment, the federated learning performance was compared against models trained on one specific dataset, but fully-collaborative approaches could not be explored to uphold data privacy.…”

Section: Referable Diabetic Retinopathy Classificationmentioning

confidence: 99%

“…Reviews of deep learning and artificial intelligence in medicine discuss the research and future directions [9], including applications in glaucoma [10] and diabetic retinopathy [11]- [13]. In this study, we expand on previously published frameworks for microvasculature segmentation [14] and quantification [15], as well as DR classification [16], [17]. As deep learning applications increase in complexity, the amount of data required to train a robust and accurate deep neural network (DNN) model increases significantly.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Federated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data

et al. 2021

Ophthalmology Science

Self Cite

View full text Add to dashboard Cite

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

show abstract

Section: Referable Diabetic Retinopathy Classificationmentioning

confidence: 99%

Section: Referable Diabetic Retinopathy Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Federated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data

et al. 2021

Ophthalmology Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Determining the characteristics of all the convoluted layers that we analyzed with Grad-CAM implemented in Keras were evaluated as heatmaps of the areas that were analyzed by DL [33][34][35]. The heatmap images were superimposed on the choroidal OCT en face vascular images to determine where the DL system was focusing its attention on the choroid.…”

Section: Heatmap With Gradient-weighted Class Activation Mapping (Grad-cam) Implemented In Kerasmentioning

confidence: 99%

Diagnosis of central serous chorioretinopathy by deep learning analysis of en face images of choroidal vasculature: A pilot study

et al. 2021

View full text Add to dashboard Cite

Purpose To diagnose central serous chorioretinopathy (CSC) by deep learning (DL) analyses of en face images of the choroidal vasculature obtained by optical coherence tomography (OCT) and to analyze the regions of interest for the DL from heatmaps. Methods One-hundred eyes were studied; 53 eyes with CSC and 47 normal eyes. Volume scans of 12×12 mm square were obtained at the same time as the OCT angiographic (OCTA) scans (Plex Elite 9000 Swept-Source OCT®, Zeiss). High-quality en face images of the choroidal vasculature of the segmentation slab of one-half of the subfoveal choroidal thickness were created for the analyses. The 100 en face images were divided into 80 for training and 20 for validation. Thus, we divided it into five groups of 20 eyes each, trained the remaining 80 eyes in each group, and then calculated the correct answer rate for each group by validation with 20 eyes. The Neural Network Console (NNC) developed by Sony and the Keras-Tensorflow backend developed by Google were used as the software for the classification with 16 layers of convolutional neural networks. The active region of the heatmap based on the feature quantity extracted by DL was also evaluated as the percentages with gradient-weighted class activation mapping implemented in Keras. Results The mean accuracy rate of the validation was 95% for NNC and 88% for Keras. This difference was not significant (P >0.1). The mean active region in the heatmap image was 12.5% in CSC eyes which was significantly lower than the 79.8% in normal eyes (P<0.01). Conclusions CSC can be automatically diagnosed by DL with high accuracy from en face images of the choroidal vasculature with different programs, convolutional layer structures, and small data sets. Heatmap analyses showed that the DL focused on the area occupied by the choroidal vessels and their uniformity. We conclude that DL can help in the diagnosis of CSC.

show abstract

“…The outputs of the two modalities are fused with clinical, demographic, data and fed into a random forest (RF) classifier in which the reported accuracies for detecting the DR and the grades of the DR were 98.2% and 98.7% , respectively. Other studies have also utilized OCT with varying results [21][22][23][23][24][25][26][27][28][29][30][31][32][33][34][35][36] .…”

mentioning

confidence: 99%

Precise higher-order reflectivity and morphology models for early diagnosis of diabetic retinopathy using OCT images

Sharafeldeen

Elsharkawy

Khalifa

et al. 2021

Sci Rep

View full text Add to dashboard Cite

This study proposes a novel computer assisted diagnostic (CAD) system for early diagnosis of diabetic retinopathy (DR) using optical coherence tomography (OCT) B-scans. The CAD system is based on fusing novel OCT markers that describe both the morphology/anatomy and the reflectivity of retinal layers to improve DR diagnosis. This system separates retinal layers automatically using a segmentation approach based on an adaptive appearance and their prior shape information. High-order morphological and novel reflectivity markers are extracted from individual segmented layers. Namely, the morphological markers are layer thickness and tortuosity while the reflectivity markers are the 1st-order reflectivity of the layer in addition to local and global high-order reflectivity based on Markov-Gibbs random field (MGRF) and gray-level co-occurrence matrix (GLCM), respectively. The extracted image-derived markers are represented using cumulative distribution function (CDF) descriptors. The constructed CDFs are then described using their statistical measures, i.e., the 10th through 90th percentiles with a 10% increment. For individual layer classification, each extracted descriptor of a given layer is fed to a support vector machine (SVM) classifier with a linear kernel. The results of the four classifiers are then fused using a backpropagation neural network (BNN) to diagnose each retinal layer. For global subject diagnosis, classification outputs (probabilities) of the twelve layers are fused using another BNN to make the final diagnosis of the B-scan. This system is validated and tested on 130 patients, with two scans for both eyes (i.e. 260 OCT images), with a balanced number of normal and DR subjects using different validation metrics: 2-folds, 4-folds, 10-folds, and leave-one-subject-out (LOSO) cross-validation approaches. The performance of the proposed system was evaluated using sensitivity, specificity, F1-score, and accuracy metrics. The system’s performance after the fusion of these different markers showed better performance compared with individual markers and other machine learning fusion methods. Namely, it achieved $$96.15\%$$ 96.15 % , $$99.23\%$$ 99.23 % , $$97.66\%$$ 97.66 % , and $$97.69\%$$ 97.69 % , respectively, using the LOSO cross-validation technique. The reported results, based on the integration of morphology and reflectivity markers and by using state-of-the-art machine learning classifications, demonstrate the ability of the proposed system to diagnose the DR early.

show abstract

Ensemble Deep Learning for Diabetic Retinopathy Detection Using Optical Coherence Tomography Angiography

Cited by 89 publications

References 38 publications

Federated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data

Federated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data

Diagnosis of central serous chorioretinopathy by deep learning analysis of en face images of choroidal vasculature: A pilot study

Precise higher-order reflectivity and morphology models for early diagnosis of diabetic retinopathy using OCT images

Contact Info

Product

Resources

About