scholarly journals Artificial intelligence can assist with diagnosing retinal vein occlusion

2021 ◽  
Vol 14 (12) ◽  
pp. 1895-1902
Author(s):  
Qiong Chen ◽  
◽  
Song Lin ◽  
Bo-Shi Liu ◽  
Yong Wang ◽  
...  

AIM: To assist with retinal vein occlusion (RVO) screening, artificial intelligence (AI) methods based on deep learning (DL) have been developed to alleviate the pressure experienced by ophthalmologists and discover and treat RVO as early as possible. METHODS: A total of 8600 color fundus photographs (CFPs) were included for training, validation, and testing of disease recognition models and lesion segmentation models. Four disease recognition and four lesion segmentation models were established and compared. Finally, one disease recognition model and one lesion segmentation model were selected as superior. Additionally, 224 CFPs from 130 patients were included as an external test set to determine the abilities of the two selected models. RESULTS: Using the Inception-v3 model for disease identification, the mean sensitivity, specificity, and F1 for the three disease types and normal CFPs were 0.93, 0.99, and 0.95, respectively, and the mean area under the curve (AUC) was 0.99. Using the DeepLab-v3 model for lesion segmentation, the mean sensitivity, specificity, and F1 for four lesion types (abnormally dilated and tortuous blood vessels, cotton-wool spots, flame-shaped hemorrhages, and hard exudates) were 0.74, 0.97, and 0.83, respectively. CONCLUSION: DL models show good performance when recognizing RVO and identifying lesions using CFPs. Because of the increasing number of RVO patients and increasing demand for trained ophthalmologists, DL models will be helpful for diagnosing RVO early in life and reducing vision impairment.

2019 ◽  
Vol 7 (4) ◽  
pp. 692-698
Author(s):  
Jecko Anto Kattampally ◽  
Koshy C Oommen ◽  
Vaibhavi Patil ◽  
Pranali Choudhari

2020 ◽  
Vol 9 (8) ◽  
pp. 2360
Author(s):  
Yusuke Arai ◽  
Hidenori Takahashi ◽  
Satoru Inoda ◽  
Shinichi Sakamoto ◽  
Xue Tan ◽  
...  

Purpose: To assess the efficacy and safety of a modified treat-and-extend (mTAE) regimen of aflibercept for macular edema (ME) due to branch retinal vein occlusion (BRVO). Methods: This prospective multicentre intervention study evaluated 50 eyes of 50 patients enrolled from October 2016 to September 2017. The patients received intravitreal aflibercept (IVA) injections on an mTAE regimen for a total of 12 months. The main outcome measures were best-corrected visual acuity (BCVA) and central subfield thickness (CST) at 12 months. Results: The baseline BCVA and CST were 0.33 (0.27) and 488 (171) µm (mean (standard deviation)), respectively. The BCVA and CST were significantly improved at month 12 (0.067 (0.19) LogMAR and 295 (110) µm; both p < 0.0001, paired t-test). The mean number of clinic visits and IVA injections was 6.71 (1.41) and 4.26 (0.71), respectively. The time to first recurrence from the first injection was most frequently 3 months. Conclusion: The mTAE regimen of IVA injections for ME due to BRVO effectively improved BCVA and reduced CST, and thus might be an effective therapy to reduce the number of injections and visits.


2019 ◽  
Vol 2019 ◽  
pp. 1-5 ◽  
Author(s):  
Dan-dan Zhu ◽  
Xun Liu

Purpose. To evaluate the neutrophil/lymphocyte ratio (NLR) and the platelet/lymphocyte ratio(PLR) value in the development of branch retinal vein occlusion (BRVO)patients. Methods. 81 patients with BRVO and 81 age and sex-matched subjects were recruited as the control group. The BRVO diagnosis was confirmed under comprehensive ophthalmologic examinations. NLR and PLR parameters obtained from peripheral blood were recorded. Results. Both the mean NLR and PLR was significantly higher in the BRVO group compared with the control group (p < 0.001). In ROC analysis, the AUC for NLR was 0.82, and NLR of >2.48 predicted BRVO with a sensitivity of 58% and specificity of 98%. The AUC for PLR was 0.78, and PLR of >110.2 predicted BRVO with a sensitivity of 72% and specificity of 72%. Conclusion. The current study demonstrated that BRVO patients had increased NLR and PLR levels compared with control subjects. The NLR and PLR may be used as independent predictors for identifying risk for the development of BRVO.


2018 ◽  
Vol 28 (6) ◽  
pp. 697-705 ◽  
Author(s):  
Francesco Bandello ◽  
Albert Augustin ◽  
Adnan Tufail ◽  
Richard Leaback

Purpose: Dexamethasone intravitreal implant and intravitreal ranibizumab are indicated for the treatment of macular edema secondary to retinal vein occlusion. This non-inferiority study compared dexamethasone with ranibizumab in patients with branch retinal vein occlusion. Methods: In this randomized, 12-month head-to-head comparison, subjects with branch retinal vein occlusion were assigned to dexamethasone 0.7 mg at day 1 and month 5 with the option of retreatment at month 10 or 11, or ranibizumab 0.5 mg at day 1 and monthly through month 5 with subsequent as-needed injections at month 6–month 11. The primary efficacy outcome was the mean change from baseline in best-corrected visual acuity at month 12; secondary outcomes included average change in best-corrected visual acuity, proportion of eyes with ≥10- and ≥15-letter gain/loss, change in central retinal thickness, and change in Vision Functioning Questionnaire-25 score. Results: In all, 307 of a planned 400 patients were enrolled in the study and received (mean) 2.5 dexamethasone injections (n = 154) and 8.0 ranibizumab injections (n = 153) over 12 months. The mean change from baseline in best-corrected visual acuity at month 12 was 7.4 letters for dexamethasone versus 17.4 letters for ranibizumab (least-squares mean difference (dexamethasone minus ranibizumab), −10.1 letters; 95% confidence interval, −12.9, −7.2; p = 0.0006). Conclusion: Dexamethasone and ranibizumab improved best-corrected visual acuity and anatomical outcomes; however, dexamethasone did not show non-inferiority to ranibizumab in this under-powered study. Dexamethasone was associated with an increased risk of intraocular pressure elevation and cataract progression, but a lower injection burden, compared to ranibizumab.


Diagnostics ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 530
Author(s):  
Christian Salvatore ◽  
Matteo Interlenghi ◽  
Caterina B. Monti ◽  
Davide Ippolito ◽  
Davide Capra ◽  
...  

We assessed the role of artificial intelligence applied to chest X-rays (CXRs) in supporting the diagnosis of COVID-19. We trained and cross-validated a model with an ensemble of 10 convolutional neural networks with CXRs of 98 COVID-19 patients, 88 community-acquired pneumonia (CAP) patients, and 98 subjects without either COVID-19 or CAP, collected in two Italian hospitals. The system was tested on two independent cohorts, namely, 148 patients (COVID-19, CAP, or negative) collected by one of the two hospitals (independent testing I) and 820 COVID-19 patients collected by a multicenter study (independent testing II). On the training and cross-validation dataset, sensitivity, specificity, and area under the curve (AUC) were 0.91, 0.87, and 0.93 for COVID-19 versus negative subjects, 0.85, 0.82, and 0.94 for COVID-19 versus CAP. On the independent testing I, sensitivity, specificity, and AUC were 0.98, 0.88, and 0.98 for COVID-19 versus negative subjects, 0.97, 0.96, and 0.98 for COVID-19 versus CAP. On the independent testing II, the system correctly diagnosed 652 COVID-19 patients versus negative subjects (0.80 sensitivity) and correctly differentiated 674 COVID-19 versus CAP patients (0.82 sensitivity). This system appears promising for the diagnosis and differential diagnosis of COVID-19, showing its potential as a second opinion tool in conditions of the variable prevalence of different types of infectious pneumonia.


1970 ◽  
Vol 2 (2) ◽  
pp. 121-126 ◽  
Author(s):  
R Sharma ◽  
SN Joshi ◽  
JK Shrestha

Introduction: Vitreous hemorrhage is one of the most common differential diagnoses of sudden painless decrease in vision. Objective: To find out the etiology of vitreous hemorrhage in cases of vitreous hemorrhage at a tertiary eye centre in Nepal. Materials and methods: This was a hospital-based cross-sectional study done over a period of one-and-a-half years. One hundred and one subjects with vitreous hemorrhage were evaluated in detail to establish the etiology. Statistics: The mean value and standard deviation were calculated. The data were analyzed using microsoft excel and SPSS 11.5 program. Results: A total of 122 eyes of 101 patients were evaluated. The mean age was 41.90 (± 21.50) years with a range of 2 months to 84 years. Male were 73 %. Bilateral involvement was found in 20.8 %. Proliferative diabetic retinopathy, retinal vasculitis, branch retinal vein occlusion, rhegmatogenous retinal detachment together with ocular trauma constituted the etilogoy of vitreous hemorrhage in more than 75 % of patients. Conclusion: Proliferative diabetic retinopathy, retinal vasculitis and branch retinal vein occlusion are the most common causes of vitreous hemorrhage in adults whereas in children trauma is the commonest cause. Keywords: vasculitis; vitreous hemorrhage; diabetic retinopathy; Eales disease DOI: 10.3126/nepjoph.v2i2.3718 Nep J Oph 2010;2(2) 121-126


2018 ◽  
Vol 4 (2) ◽  
pp. 110
Author(s):  
Citra Rahmadani ◽  
Nur Khoma Fatmawati ◽  
Rahmat Bakhtiar

Retinal vein occlusion is the second most common cause of blindness in retinal vascular disease after diabetic retinopathy and may lead to complications of macular edema. Bevacizumab is an influential treatment as an anti vascular endothelial growth factor (VEGF). This study aims to determine the difference of visual acuity and macular thickness before and after treatment of Bevacizumab. This is a quasi experimental study in patients with secondary macular edema retinal vein occlusion who meets the inclusion criteria. Visual acuity and macular thickness were evaluated after one month of treatment. This study was conducted for two months since May-June 2017 by collecting secondary data from medical record at SMEC Samarinda from January 2016 – June 2017. Data were analyzed using Wilcoxon. Sixteen eyes from 16 patients were diagnosed with macular edema secondary retinal vein occlusion given bevacizumab treatment. The mean visual acuity before therapy was 1.106 LogMAR ± 0.509 and increased to 0.889 logMAR ± 0.608 (p = 0.116) after treatment while the mean macular thickness before therapy was 504.06 μm ± 301.273 and decreased to 348.81 μm ± 181.17 (p = 0.017) after treatment. There was a significant effect on the decrease in macular thickness but no significant effect on visual acuity improvement in patients with macular edema secondary retinal vein occlusion at SMEC Samarinda.  Keywords: Retinal vein occlusion, macular edema, bevacizumab


2018 ◽  
Vol 28 (6) ◽  
pp. 690-696 ◽  
Author(s):  
Yelda Buyru Özkurt ◽  
Sezen Akkaya ◽  
Sibel Aksoy ◽  
Mert Hakan Şimşek

Purpose: To compare the effects of intravitreal ranibizumab injection and yellow (577 nm) subthreshold micropulse laser treatment in patients with macular edema following non-ischemic branch retinal vein occlusion. Methods: The medical records of 51 patients who underwent intravitreal ranibizumab (0.5 mg) injection or subthreshold micropulse laser for the treatment of macular edema due to branch retinal vein occlusion were retrospectively reviewed. Subthreshold micropulse laser was administered with a 10% duty cycle, 100 μm spot diameter, 200 ms exposure time. The patients received an injection or laser treatment at baseline and were, then, retreated as needed and were followed for 12 months. The mean best corrected visual acuity changes over the follow-up and the decrease in the mean central macular thickness were evaluated. Results: A total of 27 and 24 patients were assigned to intravitreal ranibizumab and subthreshold micropulse laser subgroups, respectively. The mean number of treatment was 3.81 of intravitreal ranibizumab group and 1.5 of subthreshold micropulse laser group (p < 0.05). The subgroups were similar with regard to the mean score of best corrected visual acuity at baseline, at 1, 6, and 12 months (p > 0.05). The decrease in the mean central macular thickness was significant in both intravitreal ranibizumab and subthreshold micropulse laser groups at 1, 6, and 12 months than that of values at baseline (p < 0.05). No new ocular or systemic adverse events were observed. Conclusion: Our study results showed that intravitreal ranibizumab or yellow subthreshold micropulse laser treatment for macular edema due to branch retinal vein occlusion was not found to be superior to each other for reducing macular thickness and increasing visual acuity for 1-year period. Based on these results, subthreshold micropulse laser may be a useful alternative approach in the treatment of macular edema secondary to branch retinal vein occlusion.


Author(s):  
Andrea Radotma Silitonga ◽  
Sindy Boru Sembiring ◽  
Christina Josephina Bangun ◽  
Heri Purwoko

Introduction: Central retinal vein occlusion (CRVO) and branch retinal vein occlusion (BRVO) caused sudden visual decrease that most often treatable. This paper aims to describe clinical characteristic and outcome using bevacizumab for macular edema caused by retinal vein occlusion in real-life practice. Methods: This retrospective study included 91 treatment-naïve eyes with macular edema due to CRVO (55 eyes) and BRVO (36 eyes), who were treated with intravitreal bevacizumab (IVB) in pro re nata (PRN) regimen. Best corrected visual acuity (BCVA) and central macular thickness (CMT) before and after treatment were evaluated. Result: The mean age of patients was 60.3 + 11.2 years for CRVO and 55.7 + 8.2 years for BRVO. The mean baseline BCVA in the CRVO group was 1.41 + 0.55 logMAR. There was statistically significant improvement in BCVA after intravitreal bevacizumab compared to baseline (p < 0.001) in CRVO and BRVO group. Twenty six (47.3%) eyes with CRVO had BCVA > 1.0 logMAR (Snellen 20/200) at the last follow-up. In the BRVO group, the mean baseline BCVA was 0.93 + 0.48 logMAR. At the end of the follow up, 19 eyes (52.8%) with BRVO had BCVA > 0.3 logMAR (Snellen 20/40). There was also statistically significant improvement in CMT between all time points and baseline (p < 0.001) in both groups. At the end of the follow up, 26 (47.3%) eyes with CRVO and 25 eyes (69.4%) in BRVO group presented resolution of macular edema (CMT < 300). Conclusion: Intravitreal bevacizumab resulted in significant anatomical and functional improvement in macular edema associated with CRVO and BRVO, although outcome in CRVO group was sub-optimal.


PLoS ONE ◽  
2021 ◽  
Vol 16 (6) ◽  
pp. e0252530
Author(s):  
Hae Min Kang ◽  
Md. Hasanuzzaman ◽  
So Won Kim ◽  
Hyoung Jun Koh ◽  
Sung Chul Lee

Purpose To investigate aqueous humor concentrations of endothelin-1 (ET-1) in patients with central retinal vein occlusion (CRVO) compared with patients with branch retinal vein occlusion (BRVO) and a normal control group. Methods A total 80 subjects were included in this prospective study, including 15 patients with CRVO, 20 patients with BRVO, and 45 patients who underwent cataract surgery and had no concomitant ocular disease. Aqueous humor levels of ET-1 were obtained before intravitreal bevacizumab injection (IVB) and after 1 month. Results At baseline, the mean aqueous ET-1 level was 12.7±3.6 pg/mL in the CRVO group, 8.0±2.3 pg/mL in the BRVO group, and 2.0±0.9 pg/mL in the control group (P<0.001). After IVB, the mean aqueous level of ET-1 was 3.4±1.9 pg/mL (0.5–6.9 pg/mL) in the CRVO group and 1.8±1.0 pg/mL (0.3–3.2 pg/mL) in the BRVO group (P = 0.008). The mean aqueous ET-1 level was significantly reduced in both the patients with CRVO and those with BRVO (P<0.001). Conclusion The mean aqueous humor ET-1 level was significant higher in the patients with CRVO than those with BRVO and in the control group. After IVB, the mean level was significantly reduced in both the patients with CRVO and those with BRVO.


Sign in / Sign up

Export Citation Format

Share Document