Classification of Pachychoroid on Optical Coherence Tomographic En Face Images Using Deep Convolutional Neural Networks

Abstract

To study the efficacy of deep convolutional neural networks (DCNNs) to differentiate pachychoroid from nonpachychoroid on en face optical coherence tomography (OCT) images at the large choroidal vessel.Methods: En face OCT images were collected from eyes with neovascular age-related macular degeneration, polypoidal choroidal vasculopathy, and central serous chorioretinopathy. All images were prelabeled pachychoroid or nonpachychoroid based on quantitative and qualitative criteria for choroidal morphology on multimodal imaging by two retina specialists. In total, 1188 nonpachychoroid and 884 pachychoroid images were used for training (80%) and validation (20%). Accuracy for identification of pachychoroid by DCNN models was analyzed. Trained models were tested on a test set containing 79 nonpachychoroid and 93 pachychoroid images. Results:The accuracy on the validation set was 94.1%, 93.2%, 94.7%, and 94.4% in DenseNet, GoogLeNet, ResNet50, and Inception-v3, respectively. On a test set, each model demonstrated accuracy of 80.2%, 83.1%, 89.5%, and 90.1% and an F1 score of 0.782, 0.824, 0.904, and 0.901, respectively.Conclusions: DCNN models could classify pachychoroid and nonpachychoroid with good performance on OCT en face images. Automated classification of pachychoroid will be useful for tailored treatment of individual patients with exudative maculopathy.Translational Relevance: En face OCT images can be used by DCNN for classification of pachychoroid.

Predicting persistent central serous chorioretinopathy using multiple optical coherence tomographic images by deep learning

“…The models were trained using pretrained ResNet50 architecture on MATLAB 2021b (MathWorks, Inc., Natick, MA, USA) for each image set (B-scan, retinal thickness, mid-retinal, EZ, and choroid). Selection of deep and shallow convolutional neural network (CNN) architectures was based on our previous studies on DL of OCT images for macular diseases 29 , 30 . To evaluate the performance of binodal imaging, two OCT images from each set underwent concatenation, and the resulting image was used for model training, validation, and testing.…”

Influence of scan direction on subfoveal choroidal vascularity index using optical coherence tomography

“…Until recently, most studies on CVI used a single horizontal OCT B-scan image. Since the choroidal pachy-vessels, defined as dilated outer choroidal vessels 17 – 19 , tend to enter the posterior pole with oblique pattern from the equator, the authors hypothesized that CVI values would differ depending on the radial scan direction. To our best knowledge, however, there has been no study comparing CVI according to scan directions of OCT B-scans.…”

Artificial Intelligence in Choroid Through Optical Coherence Tomography: A Comprehensive Review

“…Kang et al achieved 96.31% using ResNet50 to classify pachychoroid [161]. Lee et al used ResNet50 and Inception-v3 to simplify pachychoroid classification [111]. Hosoda et al used k-means clustering to categorize unilateral CNV patients, revealing AI's pattern discovery potential [120].…”

“…vessel junctions in different imaging modalities, enabling direct comparisons and modalities registration[133]. Lee et al proposed a unique pipeline using proprietary software for Bruch's membrane segmentation, subsequently generating enface images for pachychoroid presence classification[111]. Miri et al demonstrated the use of an RF classifier for Bruch's membrane opening (BMO) segmentation in glaucoma patients' patients with CNV and pigmented retinitis[110].…”