Even though, there is still a lot of limitation for the conventional handcrafted feature approach to hinder the widely adoption of computer-aided diagnosis in the clinical settings. To accelerate the diagnostic process, several studies on ocular images were made to automate the interpretation workflow using various computer vision approaches 18, 19. Computer-aided diagnosis for ocular diseasesĭespite the diagnostic advantage of OCT on ocular diseases, interpretation of images is a time-consuming procedure for ophthalmologists. OCT now plays a vital role in visualizing ERMs, determining the appropriate timing and procedures for their management, as well as the prediction of postoperative outcomes 17. If left untreated, ERM may eventually lead to blurred vision and metamorphopsia, impairing the life quality and self-care capability of patients. Depending on the severity of the ERM, its management involves either conservative observation or surgical intervention to peel the membrane away from the retina 15, 16. Spectral domain OCT is a noncontact, noninvasive imaging technique based on the spectral analysis of interference patterns of back-scattered light to form two- and three-dimensional views of living retinal tissues 13, 14. ![]() In comparison, the more recently developed optical coherence tomography (OCT) has greater sensitivity 10, and becoming the mainstay for guiding ERM diagnosis and treatment 11, 12. Thus, the number of people afflicted likely increases with expanding aging populations.ĮRMs are diagnosed based on clinical examination historically. ERMs occur at higher rates in the elderly population (>65 years of age). The incidence of ERM is 1.1% per eye-year 8, with estimated prevalence as high as 28.9% (population-dependent) 9. ERMs can be either idiopathic or secondary to retinal vascular diseases, ocular inflammatory diseases, and retinal tear or detachment 6, 7. One hypothesis is that a separation of the vitreous membrane from the retina, or a posterior vitreous detachment, causes inflammation-mediated proliferation of retinal glial cells, fibrous astrocytes, hyalocytes, fibroblasts, myofibroblasts, and macrophages on the retinal surface 3, 4, 5. The exact pathogenic mechanisms remain determined. Clinical manifestations vary from asymptomatic cellophane-like films to fibrotic contractile membranes that result in blurred vision, monocular diplopia, micropsia, metamorphopsia, decreased visual acuity, and central vision loss 1, 2. The derived model may play a role to assist clinicians to promote the efficiency and safety of healthcare in the future.Īn epiretinal membrane (ERM), also known as macular pucker or cellophane maculopathy, is a pathological fibrocellular tissue that forms on the inner surface of the retina. The performance of the model was slightly better than the average non-retinal specialized ophthalmologists. Conclusions: An ophthalmologist-level DL model was built here to accurately identify ERM in OCT images. ![]() The DL model slightly outperformed the average non-retinal specialized ophthalmologists. The accuracy on the training dataset was 99.7% (95% CI: 99.4 - 99.9%), and for the testing dataset, diagnostic accuracy was 98.1% (95% CI: 96.5 - 99.1%). Results: Regarding the diagnosis of ERM in OCT images, the trained DL model had the following characteristics in performance: sensitivity: 98.7%, specificity: 98.0%, and F1 score: 0.945. Performance of the DL model was finally compared with that of non-retinal specialized ophthalmologists. These were calculated according to the gold standard results which were parallel diagnoses of the retinal specialist. Main Outcome Measures: We calculated for the derived DL model the following characteristics: sensitivity, specificity, F1 score and area under curve (AUC) of the receiver operating characteristic (ROC) curve. Diagnostic results by four board-certified non-retinal specialized ophthalmologists on the testing dataset were compared with those generated by the DL model. DL algorithm was used to train the interpretation model. ![]() A total of 3,141 OCT images was used as training dataset and 477 images as testing dataset. From these images, 2,171 were normal and 1,447 were ERM OCT. ![]() Methods: We retrospectively collected 7,652 OCT images from 1,197 patients. Participants: A total of 3,618 central fovea cross section OCT images from 1,475 eyes of 964 patients. We proposed a deep learning model that can identify epiretinal membrane (ERM) in OCT with ophthalmologist-level performance. Purpose: Previous deep learning studies on optical coherence tomography (OCT) mainly focused on diabetic retinopathy and age-related macular degeneration.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |