scholarly journals A Multitask Deep-Learning System to Classify Diabetic Macular Edema for Different Optical Coherence Tomography Devices: A Multicenter Analysis

2021 ◽  
Author(s):  
Fangyao Tang ◽  
Xi Wang ◽  
An-ran Ran ◽  
Carmen KM Chan ◽  
Mary Ho ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Deep Learning ◽  
Macular Edema ◽  
Diabetic Macular Edema ◽  
Vision Loss ◽  
Three Dimensional ◽  
Learning System ◽  
Optical Coherence ◽  
Automated Classification

<a><b>Objective:</b></a> Diabetic macular edema (DME) is the primary cause of vision loss among individuals with diabetes mellitus (DM). We developed, validated, and tested a deep-learning (DL) system for classifying DME using images from three common commercially available optical coherence tomography (OCT) devices. <p><b>Research Design and Methods:</b> We trained and validated two versions of a multi-task convolution neural network (CNN) to classify DME (center-involved DME [CI-DME], non-CI-DME, or absence of DME) using three-dimensional (3D) volume-scans and two-dimensional (2D) B-scans respectively. For both 3D and 2D CNNs, we employed the residual network (ResNet) as the backbone. For the 3D CNN, we used a 3D version of ResNet-34 with the last fully connected layer removed as the feature extraction module. A total of 73,746 OCT images were used for training and primary validation. External testing was performed using 26,981 images across seven independent datasets from Singapore, Hong Kong, the US, China, and Australia. </p> <p><b>Results:</b> In classifying the presence or absence of DME, the DL system achieved area under the receiver operating characteristic curves (AUROCs) of 0.937 (95% CI 0.920–0.954), 0.958 (0.930–0.977), and 0.965 (0.948–0.977) for primary dataset obtained from Cirrus, Spectralis, and Triton OCTs respectively, in addition to AUROCs greater than 0.906 for the external datasets. For the further classification of the CI-DME and non-CI-DME subgroups, the AUROCs were 0.968 (0.940–0.995), 0.951 (0.898–0.982), and 0.975 (0.947–0.991) for the primary dataset and greater than 0.894 for the external datasets. </p> <p><b>Conclusion:</b> We demonstrated excellent performance with a DL system for the automated classification of DME, highlighting its potential as a promising second-line screening tool for patients with DM, which may potentially create a more effective triaging mechanism to eye clinics. </p>

scholarly journals A Multitask Deep-Learning System to Classify Diabetic Macular Edema for Different Optical Coherence Tomography Devices: A Multicenter Analysis

2021 ◽  
Author(s):  
Fangyao Tang ◽  
Xi Wang ◽  
An-ran Ran ◽  
Carmen KM Chan ◽  
Mary Ho ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Deep Learning ◽  
Macular Edema ◽  
Diabetic Macular Edema ◽  
Vision Loss ◽  
Three Dimensional ◽  
Learning System ◽  
Optical Coherence ◽  
Automated Classification

<a><b>Objective:</b></a> Diabetic macular edema (DME) is the primary cause of vision loss among individuals with diabetes mellitus (DM). We developed, validated, and tested a deep-learning (DL) system for classifying DME using images from three common commercially available optical coherence tomography (OCT) devices. <p><b>Research Design and Methods:</b> We trained and validated two versions of a multi-task convolution neural network (CNN) to classify DME (center-involved DME [CI-DME], non-CI-DME, or absence of DME) using three-dimensional (3D) volume-scans and two-dimensional (2D) B-scans respectively. For both 3D and 2D CNNs, we employed the residual network (ResNet) as the backbone. For the 3D CNN, we used a 3D version of ResNet-34 with the last fully connected layer removed as the feature extraction module. A total of 73,746 OCT images were used for training and primary validation. External testing was performed using 26,981 images across seven independent datasets from Singapore, Hong Kong, the US, China, and Australia. </p> <p><b>Results:</b> In classifying the presence or absence of DME, the DL system achieved area under the receiver operating characteristic curves (AUROCs) of 0.937 (95% CI 0.920–0.954), 0.958 (0.930–0.977), and 0.965 (0.948–0.977) for primary dataset obtained from Cirrus, Spectralis, and Triton OCTs respectively, in addition to AUROCs greater than 0.906 for the external datasets. For the further classification of the CI-DME and non-CI-DME subgroups, the AUROCs were 0.968 (0.940–0.995), 0.951 (0.898–0.982), and 0.975 (0.947–0.991) for the primary dataset and greater than 0.894 for the external datasets. </p> <p><b>Conclusion:</b> We demonstrated excellent performance with a DL system for the automated classification of DME, highlighting its potential as a promising second-line screening tool for patients with DM, which may potentially create a more effective triaging mechanism to eye clinics. </p>

scholarly journals Optical coherence tomography findings predictive of response to treatment in diabetic macular edema

2018 ◽  
Vol 46 (11) ◽  
pp. 4455-4464 ◽  
Author(s):  
Young Joo Cho ◽  
Dong Hyun Lee ◽  
Min Kim
Keyword(s):  
Optical Coherence Tomography ◽  
Macular Edema ◽  
Diabetic Macular Edema ◽  
Serous Retinal Detachment ◽  
Intravitreal Bevacizumab ◽  
Internal Limiting Membrane ◽  
Response To Treatment ◽  
Optical Coherence ◽  
Sd Oct

Objective To evaluate the short-term efficacy of intravitreal bevacizumab (IVB) and posterior sub-tenon triamcinolone injections (PSTI) on the basis of spectral-domain optical coherence tomography (SD-OCT) patterns in diabetic macular edema (DME). Methods We retrospectively reviewed 73 eyes of 73 patients with DME. Based on the presence of serous retinal detachment (SRD), eyes were categorized into two groups, and either IVB or PSTI treatment was performed. Central macular thickness (CMT) and the degree of SRD were assessed preoperatively and 1 month postoperatively. The severity of intraretinal edema was approximated based on the distance from the external limiting membrane to the internal limiting membrane. Results In eyes with SRD, reduction of SRD was greater with IVB than with PSTI. Moreover, reduction of intraretinal edema was greater with PSTI than with IVB. In eyes without SRD, PSTI achieved greater CMT reduction, compared with IVB. Conclusions In DME patients with SRD, IVB achieved greater reduction of SRD, compared with PSTI; however, intraretinal edema responded more favorably to PSTI, regardless of the presence of SRD. Our results suggest that the classification of DME based on OCT findings may be useful to predict responses to IVB or PSTI treatments.

scholarly journals Optical coherence tomography in diabetic macular edema: patterns and related risk factors

2013 ◽  
Vol 5 (2) ◽  
pp. 190-194 ◽  
Author(s):  
Mohammadreza Ahmadpour-Baghdadabad ◽  
Masoudreza Manaviat ◽  
Ahmad Shojaoddiny-Ardekani
Keyword(s):  
Risk Factors ◽  
Optical Coherence Tomography ◽  
Visual Acuity ◽  
Macular Edema ◽  
Diabetic Macular Edema ◽  
Vision Loss ◽  
Cross Sectional Study ◽  
Optical Coherence ◽  
Foveal Thickness ◽  
Cross Sectional

Introduction: Diabetic Macular Edema (DME) is an important cause of vision loss in diabetic retinopathy. Optical Coherence Tomography (OCT) is a non-invasive modality that produces high-resolution images of retinal layers. Objective: To evaluate the prevalence of DME patterns and their association with risk factors and visual acuity. Materials and Methods: In this cross-sectional study, type 2 diabetics with macular edema referred to our center during a ten-month period underwent OCT. Patients with macular edema due to causes other than diabetes and with OCT images of improper quality were excluded from the study. Four distinct patterns were found in the OCT images. A questionnaire including age, sex, duration of diabetes, serum TG and cholesterol, HbA1c, BMI and visual acuity, as well as the findings of OCT images were filled for the subjects. Results: Eighty-six eyes from 46 patients were evaluated. The most and the least common patterns were sponge-like retinal swelling (SLRS) and posterior hyaloidal traction (PHT) found in 64.0% and 5.8% of the subjects, respectively. A sub-retinal fluid pattern was more common in males (p=0.011) and in patients with serum TG > 200mg/dl (p=0.037). There were significant associations between central foveal (r=0.45, p<0.001), nasal (r=0.35, p=0.001) and temporal (r=0.32, p=0.003) thicknesses with visual acuity. Moreover, the highest thickness (462.4±119.2μm) and also the worst visual acuity (1.0±0.5logMAR) pertained to the cystoid macular edema (CME) pattern. Conclusion: Our study showed that the most common OCT pattern of DME is the sponge-like retinal swelling, while posterior hyaloidal traction has the lowest prevalence. A higher foveal thickness and a lower visual acuity are seen in the CME pattern. Nepal J Ophthalmol 2013; 5(10): 190-194 DOI: http://dx.doi.org/10.3126/nepjoph.v5i2.8727

scholarly journals Optical Coherence Tomography (Angiography) Biomarkers in the Assessment and Monitoring of Diabetic Macular Edema

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Corina-Iuliana Suciu ◽  
Vlad-Ioan Suciu ◽  
Simona-Delia Nicoara
Keyword(s):  
Optical Coherence Tomography ◽  
Macular Edema ◽  
Diabetic Macular Edema ◽  
Choroidal Thickness ◽  
Outer Segment ◽  
Vision Loss ◽  
Foveal Avascular Zone ◽  
Vascular Density ◽  
Optical Coherence ◽  
Capillary Plexus

Retinopathy is one of the most severe diabetes-related complications, and macular edema is the major cause of central vision loss in patients with diabetes mellitus. Significant progress has been made in recent years in optical coherence tomography and angiography technology. At the same time, various parameters have been attributed the role of biomarkers creating the frame for new monitoring and treatment strategies and offering new insights into the pathogenesis of diabetic retinopathy and diabetic macular edema. In this review, we gathered the results of studies that investigated various specific OCT (angiography) parameters in diabetic macular edema, such as central subfoveal thickness (CST), cube average thickness (CAT), cube volume (CV), choroidal thickness (CT), retinal nerve fiber layer (RNFL), retinal thickness at the fovea (RTF), subfoveal choroidal thickness (SFCT), central macular thickness (CMT), choroidal vascularity index (CVI), total macular volume (TMV), central choroid thickness (CCT), photoreceptor outer segment (PROS), perfused capillary density (PCD), foveal avascular zone (FAZ), subfoveal neuroretinal detachment (SND), hyperreflective foci (HF), disorganization of the inner retinal layers (DRIL), ellipsoid zone (EZ), inner segment/outer segment (IS/OS) junctions, vascular density (VD), deep capillary plexus (DCP), and superficial capillary plexus (SCP), in order to provide a synthesis of biomarkers that are currently used for the early diagnosis, assessment, monitoring, and outlining of prognosis.

Sign in / Sign up

Export Citation Format

Share Document