Deep Features and Data Reduction for Classification of SD-OCT Images: Application to Diabetic Macular Edema

2018 ◽

Vol 46 (11) ◽

pp. 4455-4464 ◽

Cited By ~ 5

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.

Download Full-text

OCT-NET: A convolutional network for automatic classification of normal and diabetic macular edema using sd-oct volumes

2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) ◽

10.1109/isbi.2018.8363839 ◽

2018 ◽

Cited By ~ 14

Author(s):

Oscar Perdomo ◽

Sebastian Otalora ◽

Fabio A. Gonzalez ◽

Fabrice Meriaudeau ◽

Henning Muller

Keyword(s):

Macular Edema ◽

Diabetic Macular Edema ◽

Automatic Classification ◽

Convolutional Network ◽

Sd Oct

Download Full-text

External limiting membrane: retinal structural barrier in diabetic macular edema

International Journal of Retina and Vitreous ◽

10.1186/s40942-021-00284-x ◽

2021 ◽

Vol 7 (1) ◽

Author(s):

Sandeep Saxena ◽

Levent Akduman ◽

Carsten H. Meyer

Keyword(s):

Optical Coherence Tomography ◽

Macular Edema ◽

Diabetic Macular Edema ◽

Spectral Domain ◽

Optical Coherence ◽

Barrier Effect ◽

External Limiting Membrane ◽

Ellipsoid Zone ◽

Structural Barrier ◽

Sd Oct

AbstractAdvances in spectral-domain optical coherence tomography (SD-OCT) technology have enhanced the understanding of external limiting membrane (ELM) and ellipsoid zone (EZ) in diabetic macular edema. An increase in VEGF has been demonstrated to be associated with sequential ELM and EZ disruption on SD-OCT. An intact ELM is a prerequisite for an intact EZ in DME. Anti-VEGF therapy leads to restoration of barrier effect of ELM. The ELM restores first followed by EZ restoration.

Download Full-text

Repeatability of Bruch’s Membrane Opening-minimum Rim Width in Age-related Macular Degeneration and Diabetic Macular Edema

Journal of the Korean Ophthalmological Society ◽

10.3341/jkos.2021.62.11.1490 ◽

2021 ◽

Vol 62 (11) ◽

pp. 1490-1501

Author(s):

Bum Jun Kim ◽

Woo Hyuk Lee ◽

Ki Yup Nam ◽

Ji Hye Kim ◽

Tae Seen Kang ◽

...

Keyword(s):

Macular Degeneration ◽

Macular Edema ◽

Optic Disc ◽

Diabetic Macular Edema ◽

Age Related Macular Degeneration ◽

Disc Membrane ◽

Rnfl Thickness ◽

Age Related ◽

Bruch’S Membrane Opening ◽

Sd Oct

Purpose: To evaluate the repeatability of retinal nerve fiber layer (RNFL) thickness and Bruch’s membrane opening-minimum rim width (BMO-MRW) measurements by spectral-domain optical coherence tomography (SD-OCT) in wet age-related macular degeneration (wAMD) and diabetic macular edema (DME).Methods: This was a prospective study. The RNFL thickness and BMO-MRW parameters for each sector and global average were measured twice by SD-OCT. Repeatability was evaluated using the intraclass correlation coefficient (ICC) and coefficient of variation (CV). If the optic disc membrane was confirmed, it was analyzed by dividing it into three groups based on severity.Results: A total of 99 eyes (48 with wAMD, 51 with DME) were included in the analysis. The ICCs of the global RNFL thickness and global BMO-MRW measurements were 0.996 and 0.997, respectively, in wAMD and 0.994 and 0.996, respectively, in DME eyes. The CV values of global RNFL thickness and BMO-MRW were 0.60% and 0.73%, respectively, in wAMD eyes and 1.10% and 1.21%, respectively, in DME eyes. The disc membrane on the optic nerve head significantly affected global BMO-MRW repeatability (B = 0.814, p < 0.001).Conclusions: Both RNFL thickness and BMO-MRW measurements showed good repeatability in eyes with wAMD and DME. The severity of the optic disc membrane significantly affected the repeatability of BMO-MRW measurements in eyes with wAMD and DME. Therefore, physicians should examine the BMO-MRW in eyes with severe optic disc membrane.

Download Full-text

Rapid response to dexamethasone intravitreal implant in diabetic macular edema

European Journal of Ophthalmology ◽

10.5301/ejo.5000989 ◽

2017 ◽

Vol 28 (1) ◽

pp. 74-79 ◽

Cited By ~ 4

Author(s):

Giuseppe Lo Giudice ◽

Antonio Avarello ◽

Gianluca Campana ◽

Alessandro Galan

Keyword(s):

Visual Acuity ◽

Macular Edema ◽

Diabetic Macular Edema ◽

Secondary Outcome ◽

Dexamethasone Intravitreal Implant ◽

Clinical Series ◽

Intravitreal Implant ◽

Early Effects ◽

Sd Oct

Purpose: To evaluate the early effects of dexamethasone (DEX) intravitreal implants in patients with diabetic macular edema (DME). Methods: This was a prospective, single-arm, interventional clinical series. Eighteen patients (18 eyes) with chronic/recalcitrant or naive DME were included. Patients underwent single DEX intravitreal implant. Clinical assessments, including ophthalmologic examination, central retinal thickness (CRT) measurement by spectral-domain optical coherence tomography (SD-OCT) scan, best-corrected visual acuity (BCVA), and intraocular pressure (IOP) were carried out at baseline, 1-3 hours, and then 3, 7, and 30 days after treatment. The main outcome was change in CRT on SD-OCT, while secondary outcome measures included visual acuity (VA) and changes in IOP following implant. Results: Mean CRT significantly decreased from 565 ± 171 µm at baseline to 310 ± 89 µm at end of follow-up (p<0.001), with reduction becoming evident 1-3 hours after injection. Mean BCVA also significantly improved 7 days and 30 days after treatment up to 0.14 logMAR (p<0.05). All patients had a controlled IOP after the injection with only 1/18 eyes having a transient increase in IOP during follow-up. Conclusions: This is the first study showing very early effects of DEX implants on CRT reduction and VA improvement in DME.

Download Full-text

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

10.2337/figshare.14710284.v1 ◽

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>Objective:</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. Research Design and Methods: 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. Results: 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. Conclusion: 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.

Download Full-text

Correlation of retinal layer changes with vision gain in diabetic macular edema during conbercept treatment

10.21203/rs.2.343/v4 ◽

2019 ◽

Author(s):

Yupeng Xu ◽

Yuan Qu ◽

Yan Suo ◽

Jian Gao ◽

Xia Chen ◽

...

Keyword(s):

Visual Acuity ◽

Macular Edema ◽

Diabetic Macular Edema ◽

Outer Nuclear Layer ◽

Plexiform Layer ◽

Retinal Layer ◽

Central Field ◽

Inner Plexiform Layer ◽

Clinically Significant ◽

Sd Oct

Abstract Purpose To assess the changes in individual retinal layer thickness and visual function associated with gains in visual acuity after an intravitreal conbercept injection in the diabetic macular edema (DME) on spectral domain optical coherence tomography (SD-OCT) and microperimetry during 1-year follow-up. Methods Retrospective observational study. Twenty patients with clinically significant DME in the study eye were imaged by SD-OCT every three months and MP1 microperimeter in the third month while receiving anti-VEGF (conbercept) treatment. In each patient, seven retinal layers were segmented in 98 scans covering a 6mm×6mm area of the macula at baseline and during 1 year of treatment. An automatic, full-threshold microperimetry of the central field (10°×10°, 40 stimulated points) with the MP1 microperimeter. Thickness and microperimetry changes were quantitatively measured and evaluated for their correlation with increases in visual acuity. Results Although thicknesses of the inner nuclear layer (INL) and the outer nuclear layer (ONL) were reduced the most after treatment (p< 0.05), decreases of the ganglion cell layer (GCL) (r = 0.591, p= 0.006) and inner plexiform layer (IPL) (r= 0.663, p= 0.001) in central subfield area was associated with BCVA gain, and had the best estimation of BCVA gain (adjust R2=0.544). Mean macular sensitivity in the central subfield was also well correlated with BCVA gain (r=0.531, p=0.016). Conclusions Neural recovery occurred after the resolution of edema during conbercept treatment, due to the decreases in GCL and IPL associating with gains in vision and improved microperimetry.

Download Full-text