scholarly journals Distinguishing retinal angiomatous proliferation from polypoidal choroidal vasculopathy with a deep neural network based on optical coherence tomography

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Daniel Duck-Jin Hwang ◽  
Seong Choi ◽  
Junseo Ko ◽  
Jeewoo Yoon ◽  
Ji In Park ◽  
...  
Keyword(s):  
Neural Network ◽  
Optical Coherence Tomography ◽  
Deep Learning ◽  
Polypoidal Choroidal Vasculopathy ◽  
Retinal Angiomatous Proliferation ◽  
Optical Coherence ◽  
Proposed Model ◽  
Tertiary Center ◽  
Choroidal Vasculopathy ◽  
Sd Oct

AbstractThis cross-sectional study aimed to build a deep learning model for detecting neovascular age-related macular degeneration (AMD) and to distinguish retinal angiomatous proliferation (RAP) from polypoidal choroidal vasculopathy (PCV) using a convolutional neural network (CNN). Patients from a single tertiary center were enrolled from January 2014 to January 2020. Spectral-domain optical coherence tomography (SD-OCT) images of patients with RAP or PCV and a control group were analyzed with a deep CNN. Sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUROC) were used to evaluate the model’s ability to distinguish RAP from PCV. The performances of the new model, the VGG-16, Resnet-50, Inception, and eight ophthalmologists were compared. A total of 3951 SD-OCT images from 314 participants (229 AMD, 85 normal controls) were analyzed. In distinguishing the PCV and RAP cases, the proposed model showed an accuracy, sensitivity, and specificity of 89.1%, 89.4%, and 88.8%, respectively, with an AUROC of 95.3% (95% CI 0.727–0.852). The proposed model showed better diagnostic performance than VGG-16, Resnet-50, and Inception-V3 and comparable performance with the eight ophthalmologists. The novel model performed well when distinguishing between PCV and RAP. Thus, automated deep learning systems may support ophthalmologists in distinguishing RAP from PCV.

scholarly journals Classifying central serous chorioretinopathy subtypes with a deep neural network using optical coherence tomography images: a cross-sectional study

2022 ◽  
Vol 12 (1) ◽  
Author(s):  
Jeewoo Yoon ◽  
Jinyoung Han ◽  
Junseo Ko ◽  
Seong Choi ◽  
Ji In Park ◽  
...  
Keyword(s):  
Neural Network ◽  
Optical Coherence Tomography ◽  
Deep Learning ◽  
Central Serous Chorioretinopathy ◽  
Cross Validation ◽  
Learning Systems ◽  
Test Accuracy ◽  
Optical Coherence ◽  
Proposed Model ◽  
Sd Oct

AbstractCentral serous chorioretinopathy (CSC) is the fourth most common retinopathy and can reduce quality of life. CSC is assessed using optical coherence tomography (OCT), but deep learning systems have not been used to classify CSC subtypes. This study aimed to build a deep learning system model to distinguish CSC subtypes using a convolutional neural network (CNN). We enrolled 435 patients with CSC from a single tertiary center between January 2015 and January 2020. Data from spectral domain OCT (SD-OCT) images of the patients were analyzed using a deep CNN. Five-fold cross-validation was employed to evaluate the model’s ability to discriminate acute, non-resolving, inactive, and chronic atrophic CSC. We compared the performances of the proposed model, Resnet-50, Inception-V3, and eight ophthalmologists. Overall, 3209 SD-OCT images were included. The proposed model showed an average cross-validation accuracy of 70.0% (95% confidence interval [CI], 0.676–0.718) and the highest test accuracy was 73.5%. Additional evaluation in an independent set of 104 patients demonstrated the reliable performance of the proposed model (accuracy: 76.8%). Our model could classify CSC subtypes with high accuracy. Thus, automated deep learning systems could be useful in the classification and management of CSC.

scholarly journals Polypoidal Choroidal Vasculopathy in Congolese Patients

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Nelly N. Kabedi ◽  
David L. Kayembe ◽  
Gloria M. Elongo ◽  
Jean-Claude Mwanza
Keyword(s):  
Optical Coherence Tomography ◽  
Indocyanine Green ◽  
Polypoidal Choroidal Vasculopathy ◽  
Indocyanine Green Angiography ◽  
Clinical Presentation ◽  
Case Series ◽  
Systemic Hypertension ◽  
Optical Coherence ◽  
Blurred Vision ◽  
Choroidal Vasculopathy

Purpose. Polypoidal choroidal vasculopathy (PCV) is a visually debilitating disease that mostly affects people of African and Asian heritage. Indocyanine green angiography (ICGA) is the recommended exploratory method for definitive diagnosis. The disease has been extensively described in Asians and Caucasians, but not in Africans. This study was conducted to document the clinical presentation and optical coherence tomography features of polypoidal choroidal vasculopathy (PCV) in Congolese patients. Methods. A prospective case series of patients with PCV was performed between January 2017 and June 2019. Routine ocular examination was performed including best corrected visual acuity measurement, slit-lamp examination, dilated direct fundoscopy, and spectral domain optical coherence tomography (OCT). The diagnosis was based on a combination of clinical and OCT signs. Results. Fourteen patients were diagnosed with PCV during this period. The average age was 64.7 ± 6.9 years. There were 8 females. Ten (71.4%) patients had systemic hypertension. Most patients (n = 9, 64.3%) had bilateral involvement. Blurred vision was the most common complaint (71.4%). The main clinical presentation was subretinal exudates, seen in 19 (82.6%) eyes of 11 (78.6%) patients and subretinal hemorrhage in 10 (43.5%) eyes. Macular localization was found in 16 eyes (69.5%) of 12 (85.7%) patients. Drusen were observed in 35.7% of the patients. On OCT imaging, thumb-like pigment epithelial detachment and subretinal exudation were the most frequent features, observed in 92.9% and 71.4% of the patients, respectively. Conclusions. PCV in Congolese patients showed features that are more similar to those observed in Caucasians. In this setting where indocyanine green angiography is not available, OCT facilitates the diagnosis of PCV.

IMPROVED VISUALIZATION OF POLYPOIDAL CHOROIDAL VASCULOPATHY LESIONS USING SPECTRAL-DOMAIN OPTICAL COHERENCE TOMOGRAPHY

Retina ◽  
2009 ◽  
Vol 29 (1) ◽  
pp. 52-59 ◽  
Author(s):  
YUMIKO OJIMA ◽  
MASANORI HANGAI ◽  
ATSUSHI SAKAMOTO ◽  
AKITAKA TSUJIKAWA ◽  
ATSUSHI OTANI ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Polypoidal Choroidal Vasculopathy ◽  
Spectral Domain ◽  
Optical Coherence ◽  
Choroidal Vasculopathy

Discriminating glaucomatous and compressive optic neuropathy on spectral-domain optical coherence tomography with deep learning classifier

2020 ◽  
Vol 104 (12) ◽  
pp. 1717-1723 ◽  
Author(s):  
Jinho Lee ◽  
Jin-Soo Kim ◽  
Haeng Jin Lee ◽  
Seong-Joon Kim ◽  
Young Kook Kim ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Deep Learning ◽  
Optic Neuropathy ◽  
Spectral Domain ◽  
Optical Coherence ◽  
Compressive Optic Neuropathy ◽  
Diagnostic Parameters ◽  
Learning Classifier ◽  
Oct Image ◽  
Sd Oct

Background/aimsTo assess the performance of a deep learning classifier for differentiation of glaucomatous optic neuropathy (GON) from compressive optic neuropathy (CON) based on ganglion cell–inner plexiform layer (GCIPL) and retinal nerve fibre layer (RNFL) spectral-domain optical coherence tomography (SD-OCT).MethodsEighty SD-OCT image sets from 80 eyes of 80 patients with GON along with 81 SD-OCT image sets from 54 eyes of 54 patients with CON were compiled for the study. The bottleneck features extracted from the GCIPL thickness map, GCIPL deviation map, RNFL thickness map and RNFL deviation map were used as predictors for the deep learning classifier. The area under the receiver operating characteristic curve (AUC) was calculated to validate the diagnostic performance. The AUC with the deep learning classifier was compared with those for conventional diagnostic parameters including temporal raphe sign, SD-OCT thickness profile and standard automated perimetry.ResultsThe deep learning system achieved an AUC of 0.990 (95% CI 0.982 to 0.999) with a sensitivity of 97.9% and a specificity of 92.6% in a fivefold cross-validation testing, which was significantly larger than the AUCs with the other parameters: 0.804 (95% CI 0.737 to 0.872) with temporal raphe sign, 0.815 (95% CI 0.734 to 0.896) with superonasal GCIPL and 0.776 (95% CI 0.691 to 0.860) with superior GCIPL thicknesses (all p<0.001).ConclusionThe deep learning classifier can outperform the conventional diagnostic parameters for discrimination of GON and CON on SD-OCT.

scholarly journals Sensitivity, Specificity, and Limitations of Optical Coherence Tomography Angiography in Diagnosis of Polypoidal Choroidal Vasculopathy

2017 ◽  
Vol 2017 ◽  
pp. 1-7 ◽  
Author(s):  
Yi-Ming Huang ◽  
Ming-Hung Hsieh ◽  
An-Fei Li ◽  
Shih-Jen Chen
Keyword(s):  
Optical Coherence Tomography ◽  
Sensitivity And Specificity ◽  
Polypoidal Choroidal Vasculopathy ◽  
Optical Coherence Tomography Angiography ◽  
False Positive Rate ◽  
Correct Diagnosis ◽  
Age Related Macular Degeneration ◽  
Optical Coherence ◽  
Age Related ◽  
Choroidal Vasculopathy

Purpose. To evaluate the sensitivity and specificity of optical coherence tomography angiography (OCTA) in differentiating polypoidal choroidal vasculopathy (PCV) from age-related macular degeneration (AMD). Methods. Fundus color photographs, spectral-domain optical coherence tomography, and fluorescein angiography (step 1) and OCTA (step 2) of 50 eyes that had PCV or AMD were presented to two ophthalmologists. The final diagnoses of PCV were masked. Sensitivity and specificity were calculated and compared to the 2-step approach (before and after OCTA) in detecting PCV. The limitations were also evaluated. Results. Of the 50 eyes, 31 were PCV and 19 were non-PCV. The sensitivity increased from 69.5% to 90% after OCTA; however, there was no significant improvement in specificity after OCTA. 70.9% of the eyes with PCV had clear or obvious branching vascular nets (BVNs) in OCTA with high sensitivity (97.5%) after OCTA. Contrarily, 29.1% had insignificant BVNs with a low sensitivity (72.5%) after OCTA. 27% of the occult choroidal neovascularization (CNV) cases were overdiagnosed as PCV when OCTA was applied. Conclusions. OCTA based on clear BVNs at the choroidal level increased sensitivity of diagnosis of PCV by 20%. However, the false-positive rate also increased in occult CNV. Several limitations for a correct diagnosis of PCV were noted.

Sign in / Sign up

Export Citation Format

Share Document