Table 2.
Summary table for the different DL systems in the detection of retinal diseases using OCT
| DL systems | Year | Disease | OCT machines | Test images | CNN | AUC | Accuracy (%) | Sensitivity (%) | Specificity (%) |
| Lee et al 13 32 | 2017 | Exudative AMD | Spectralis | 20 613 | VGG-16 | 0.928 | 87.60 | 84.60 | 91.50 |
| Trader et al 33 | 2018 | Exudative AMD | Spectralis | 100 | Inception-V3 | 0.980 | 100 | NA | NA |
| Kermany et al 34 | 2018 | CNV | Spectralis | 1000 | Inception-V3 | ||||
| DMO | |||||||||
| Drusen | |||||||||
| 1. Multiclass comparison | 0.999 | 96.50 | 97.80 | 97.40 | |||||
| 2. Limited model | 0.988 | 93.40 | 96.60 | 94.00 | |||||
| 3. Binary model | |||||||||
| CNV vs normal | 1 | 100 | 100 | 100 | |||||
| DMO vs normal | 0.999 | 98.20 | 96.80 | 99.60 | |||||
| Drusen vs normal | 0.999 | 99 | 98 | 99.20 | |||||
| De Fauw et al 43 | 2018 | Urgent, semiurgent, routine and observation only | Topcon | 997 patients | 1. Deep segmentation network using U-Net | Urgent referral 0.992 |
94.5 | ||
| Normal, CNV, macular oedema, FTMH, PTMH, CSR, VMT, GA, drusen, ERM | Spectralis | 116 patients | 2. Deep classification network using a custom 29 CNN layers with 5 pooling layers | Urgent referral 0.999 |
96.6 |
The diagnostic performance is not comparable between the different DL systems given the different data sets used in the individual study. AUC for specific conditions: CNV 0.993; macular oedema 0.990; normal 0.995; FTMH 1.00; PTMH 0.999; CSR 0.995; VMT 0.980; GA 0.990; drusen 0.967; and ERM 0.966.
AMD, age-related macular degeneration; AUC, area under the receiver operating characteristic curve; CNN, convolutional neural network; CNV, choroidal neovascularisation; CSR, central serous chorioretinopathy; DL, deep learning; DMO, diabetic macular oedema; ERM, epiretinal membrane; FTMH, full-thickness macula hole; GA, geographic atrophy; NA, not available; OCT, optical coherence tomography; PTMH, partial thickness macula hole; VMT, vitreomacular traction.