Deep Learning Algorithm Detects Presence of Disorganization of Retinal Inner Layers (DRIL)–An Early Imaging Biomarker in Diabetic Retinopathy

To develop and train a deep learning-based algorithm for detecting disorganization of retinal inner layers (DRIL) on optical coherence tomography (OCT) to screen a cohort of patients with diabetic retinopathy (DR). In this cross-sectional study, subjects over age 18, with ICD-9/10 diagnoses of type...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Translational vision science & technology Ročník 12; číslo 7; s. 6
Hlavní autoři: Singh, Rupesh, Singuri, Srinidhi, Batoki, Julia, Lin, Kimberly, Luo, Shiming, Hatipoglu, Dilara, Anand-Apte, Bela, Yuan, Alex
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States The Association for Research in Vision and Ophthalmology 06.07.2023
Témata:
Adolescent
Artificial Intelligence
Biomarkers
Cross-Sectional Studies
Deep Learning
Diabetes Mellitus, Type 2 - diagnosis
Diabetes Mellitus, Type 2 - diagnostic imaging
Diabetic Retinopathy - diagnostic imaging
Fluorescein Angiography - methods
Humans
Retrospective Studies
Tomography, Optical Coherence - methods
Visual Acuity
ISSN:2164-2591, 2164-2591
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:To develop and train a deep learning-based algorithm for detecting disorganization of retinal inner layers (DRIL) on optical coherence tomography (OCT) to screen a cohort of patients with diabetic retinopathy (DR). In this cross-sectional study, subjects over age 18, with ICD-9/10 diagnoses of type 2 diabetes with and without retinopathy and Cirrus HD-OCT imaging performed between January 2009 to September 2019 were included in this study. After inclusion and exclusion criteria were applied, a final total of 664 patients (5992 B-scans from 1201 eyes) were included for analysis. Five-line horizontal raster scans from Cirrus HD-OCT were obtained from the shared electronic health record. Two trained graders evaluated scans for presence of DRIL. A third physician grader arbitrated any disagreements. Of 5992 B-scans analyzed, 1397 scans (∼30%) demonstrated presence of DRIL. Graded scans were used to label training data for the convolution neural network (CNN) development and training. On a single CPU system, the best performing CNN training took ∼35 mins. Labeled data were divided 90:10 for internal training/validation and external testing purpose. With this training, our deep learning network was able to predict the presence of DRIL in new OCT scans with a high accuracy of 88.3%, specificity of 90.0%, sensitivity of 82.9%, and Matthews correlation coefficient of 0.7. The present study demonstrates that a deep learning-based OCT classification algorithm can be used for rapid automated identification of DRIL. This developed tool can assist in screening for DRIL in both research and clinical decision-making settings. A deep learning algorithm can detect disorganization of retinal inner layers in OCT scans.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
RS and SS contributed equally to this work.
ISSN:2164-2591
2164-2591
DOI:10.1167/tvst.12.7.6