Optical coherence tomography and imaging biomarkers as outcome predictors in diabetic macular edema treated with dexamethasone implant

Chou, Hung‐Da; Wu, Cheng-Hsiu; Chiang, Wen-Son; Chen, Nan-Ni; Hwang, Yih-Shiou; Chen, Kuan‐Jen; Lai, Chia-Yun; Wu, Pei-Chang; Chen, Yi-Hao; Yeung, Ling; Shao, Shih‐Chieh; Lai, Chi-Chun; Wu, Wei‐Chi

doi:10.1038/s41598-022-07604-7

Cited by 9 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After dexamethasone implants in eyes with DME, biomarkers such as subretinal fluid, inner segment/outer segment continuity, the lack of hyperreflective foci, and an attached vitreoretinal interface indicated improved visual results. Anti-VEGF (ranibizumab) biomarkers such as ellipsoid zone disruption and the lack of epiretinal membrane have been linked to superior therapy outcomes [13][14] . A potential predictive biomarker for the visual consequences of DME is the disorganization of the retinal inner layers.…”

Section: How To Detect Diabetic Macular Edemamentioning

confidence: 99%

Guidelines from an expert panel for the management of diabetic macular edema in the Malaysian population

Ngah¹,

Mohamed²,

Aziz³

et al. 2023

Int J Ophthalmol

View full text Add to dashboard Cite

AIM: To derive a Malaysia guideline and consensus as part of the Malaysia Retina Group’s efforts for diagnosis, treatment, and best practices of diabetic macular edema (DME). The experts’ panel suggests that the treatment algorithm to be divided into groups according to involvement the central macula. The purpose of DME therapy is to improve edema and achieve the best visual results with the least amount of treatment load. METHODS: On two different occasions, a panel of 14 retinal specialists from Malaysia, together with an external expert, responded to a questionnaire on management of DME. A consensus was sought by voting after compiling, analyzing and discussion on first-phase replies on the round table discussion. A recommendation was deemed to have attained consensus when 12 out of the 14 panellists (85%) agreed with it. RESULTS: The terms target response, adequate response, nonresponse, and inadequate response were developed when the DME patients’ treatment responses were first characterized. The panelists reached agreement on a number of DME treatment-related issues, including the need to classify patients prior to treatment, first-line treatment options, the right time to switch between treatment modalities, and side effects associated with steroids. From this agreement, recommendations were derived and a treatment algorithm was created. CONCLUSION: A detail and comprehensive treatment algorithm by Malaysia Retina Group for the Malaysian population provides guidance for treatment allocation of patients with DME.

show abstract

Section: How To Detect Diabetic Macular Edemamentioning

confidence: 99%

Guidelines from an expert panel for the management of diabetic macular edema in the Malaysian population

Ngah¹,

Mohamed²,

Aziz³

et al. 2023

Int J Ophthalmol

View full text Add to dashboard Cite

show abstract

“…[8][9][10][11] Several studies investigated OCT biomarkers in DME and found them to be predictive of treatment outcomes after intravitreal anti-VEGF injection and intravitreal steroid implant and to be related to the nal visual outcome. [12][13][14][15][16][17] In the last years, the high demand for screening and monitoring patients with DR prompted the development of Arti cial Intelligence (AI) in the ophthalmology eld in order to improve access of patients to DR screening and to improve diagnostic accuracy, particularly by means of retinal fundus images.…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning Approach to Hard Exudates Detection and Disorganization of Retinal Inner Layers Identification on OCT images

Toto,

Romano,

Pavan

et al. 2024

Preprint

View full text Add to dashboard Cite

The purpose of the study was to detect to detect Hard Exudates (HE) and classify Disorganization of Retinal Inner Layers (DRIL) implementing a Deep Learning (DL) system on optical coherence tomography (OCT) images of eyes with diabetic macular edema (DME). We collected a dataset composed of 442 OCT images on which we annotated 6847 HE and the presence of DRIL. We defined a complex operational pipeline to implement data cleaning and image transformations, and train two DL models. We exploited state-of-the-art neural network architectures (Yolov7, ConvNeXt, RegNetX) and advanced techniques to aggregate the results (Ensemble learning, Edge detection) and obtain a final model. In order to evaluate our DL system on the HE detection we calculated the AP@0.5, Precision and Recall, while for the DRIL classification, we computed the overall Accuracy, Sensitivity, Specificity, Area Under the ROC Curve, and Area Under the Precision-Recall values. Kappa coefficient and P-value were used to prove the statistical significance level. The DL approach reached good performance in detecting HE and classifying DRIL. Regarding HE detection the model got an AP@0.5 score equal to 34.4% with Precision of 48.7% and Recall of 43.1%; while for DRIL classification we obtained an Accuracy of 91.1% with Sensitivity and Specificity both of 91,1% and AUC and AUPR values equal to 91%. The P-value was lower than 0.05 and the Kappa coefficient was 0.82. The DL models proved to be able to identify HE and DRIL in eyes with DME with a very good accuracy and all the metrics calculated confirmed the system performance. Our DL approach demonstrated to be a good candidate as a supporting tool for ophthalmologists in OCT images analysis.

show abstract

“…The clinician’s choice between these different drugs is usually based on several factors that consider the patient’s compliance and motivation, age, and some general and ophthalmological comorbidities [ 2 ]. Furthermore, several imaging biomarkers have been identified as particularly useful to guide the therapeutical option choice [ 3 ], but a univocal consensus has not yet been reached on this topic.…”

Section: Introductionmentioning

confidence: 99%

“…Optical coherence tomography (OCT) and OCT angiography (OCTA) allow non-invasive recognition of imaging features that define a “DME profile”, distinguishing an inflammatory DME pattern characterized by the presence of subretinal fluid (SRF) and a high number of hyper-reflective foci (HRF) [ 4 , 5 ]. Furthermore, numerous imaging (OCT and OCTA) biomarkers have been identified in DME eyes as predictive of treatment response or disease progression, such as the retinal thickening characteristics [ 3 , 6 , 7 ], the presence, position, and internal reflectivity of microaneurysms (MAS) [ 8 , 9 ], the vitreomacular interface abnormalities (VMIAs) [ 6 ], the ellipsoid zone/external limiting membrane (EZ/ELM) integrity/disruption [ 7 ], the presence of nonperfusion areas (NPAs) [ 10 , 11 ], the foveal avascular zone (FAZ) abnormalities in terms of circularity and dimension [ 12 ], the involvement of deep capillary complex (DCP) [ 10 , 13 ], and the suspended scattering particles in motion (SSPiM) [ 14 , 15 ].…”

Section: Introductionmentioning

confidence: 99%

Prognostic Imaging Biomarkers in Diabetic Macular Edema Eyes Treated with Intravitreal Dexamethasone Implant

Costanzo

Giannini

Geronimo

et al. 2023

JCM

View full text Add to dashboard Cite

Background: The aim was to evaluate predictive value of baseline optical coherence tomography (OCT) and OCT angiography (OCTA) parameters in diabetic macular edema (DME) treated with dexamethasone implant (DEXi). Methods: OCT and OCTA parameters were collected: central macular thickness (CMT), vitreomacular abnormalities (VMIAs), intraretinal and subretinal fluid (mixed DME pattern), hyper-reflective foci (HRF), microaneurysms (MAs) reflectivity, ellipsoid zone disruption, suspended scattering particles in motion (SSPiM), perfusion density (PD), vessel length density, and foveal avascular zone. Responders’ (RES) and non-responders’ (n-RES) eyes were classified considering morphological (CMT reduction ≥ 10%) and functional (BCVA change ≥ 5 ETDRS letters) changes after DEXi. Binary logistic regression OCT, OCTA, and OCT/OCTA-based models were developed. Results: Thirty-four DME eyes were enrolled (18 treatment-naïve). OCT-based model combining DME mixed pattern + MAs + HRF and OCTA-based model combining SSPiM and PD showed the best performance to correctly classify the morphological RES eyes. In the treatment-naïve eyes, VMIAs were included with a perfect fit for n-RES eyes. Conclusion: The presence of DME mixed pattern, a high number of parafoveal HRF, hyper-reflective MAs, SSPiM in the outer nuclear layers, and high PD represent baseline predictive biomarkers for DEXi treatment responsiveness. The application of these models to treatment-naïve patients allowed a good identification of n-RES eyes.

show abstract

Optical coherence tomography and imaging biomarkers as outcome predictors in diabetic macular edema treated with dexamethasone implant

Cited by 9 publications

References 37 publications

Guidelines from an expert panel for the management of diabetic macular edema in the Malaysian population

Guidelines from an expert panel for the management of diabetic macular edema in the Malaysian population

A Deep Learning Approach to Hard Exudates Detection and Disorganization of Retinal Inner Layers Identification on OCT images

Prognostic Imaging Biomarkers in Diabetic Macular Edema Eyes Treated with Intravitreal Dexamethasone Implant

Contact Info

Product

Resources

About