Table 1.
Characteristics of the Training and External Validation Data
| Type of Data | Dataset Name | Country of Origin | Image Quantitya | Device (Manufacturer) |
|---|---|---|---|---|
| Image Quality Grading | ||||
| Training data | EyePACS-Q-train30,31 | USA | 12,543 (NR, more than 99%) | A variety of imaging devices, including DRS (CenterVue, Padova, Italy); iCam (Optovue, Fremont, CA); CR1/DGi/CR2 (Canon, Tokyo, Japan); Topcon NW 8 (Topcon, Tokyo, Japan) |
| Internal validation data | EyePACS-Q-test30,31 | USA | 16,249 (NR, more than 99%) | — |
| External validation data | DDR test32 | China | 4,105 (100%) | 42 types of fundus cameras, mainly Topcon D7000, Topcon TRC NW48, D5200 (Nikon, Tokyo, Japan), and Canon CR 2 cameras |
| Binary Vessel Segmentation | ||||
| Training data | DRIVE33 | Netherlands | 40 (100%) | CR5 non-mydriatic 3CCD camera (Canon) |
| STARE34 | USA | 20 (100%) | TRV-50 fundus camera (Topcon) | |
| CHASEDB135 | UK | 28 (0%) | NM-200D handheld fundus camera (Nidek, Aichi, Japan) | |
| HRF36 | Germany and Czech Republic | 45 (100%) | CF-60UVi camera (Canon) | |
| IOSTAR37 | Netherlands and China | 30 (53.3%) | EasyScan camera (i-Optics, Rijswijk, Netherlands) | |
| LES-AV38 | NR | 22 (0%) | Visucam Pro NM fundus camera (Carl Zeiss Meditec, Jena, Germany) | |
| External validation datab | AV-WIDE19,39 | USA | 30 (100%) | 200Tx Ultra-widefield Imaging Device (Optos, Dunfermline, UK) |
| DR HAGIS40 | UK | 39 (100%) | TRC-NW6s (Topcon), TRC-NW8 (Topcon), or CR-DGi fundus camera (Canon) | |
| Artery/Vein Segmentation | ||||
| Training data | DRIVE-AV33,41 | Netherlands | 40 (100%) | CR5 non-mydriatic 3CCD camera (Canon) |
| HRF-AV36,42 | Germany and Czech Republic | 45 (100%) | CF-60UVi camera (Canon) | |
| LES-AV38 | Nauru | 22 (9%) | Visucam Pro NM fundus camera (Zeiss) | |
| External validation data | IOSTAR-AV37,43 | Netherlands and China | 30 (53.3%) | EasyScan camera (i-Optics) |
| Optic Disc Segmentation | ||||
| Training data | REFUGE44 | China | 800 (100%) | Visucam 500 fundus camera (Zeiss) and CR-2 camera (Canon) |
| GAMMA45,46 | China | 100 (100%) | — | |
| External validation datac | IDRID47 | India | 81 (100%) | VX-10α digital fundus camera (Kowa, Las Vegas, NV) |
External validation data are unseen for model training and were purely used to evaluate the trained model performance on out-of-distribution data with different countries of origin and imaging devices. EyePACS-Q is a subset of EyePACS with image quality grading annotation. NR, not reported.
Image quantity indicates the image number used in this work and the parentheses show the proportion of macula-centered images.
Although we have evaluated the binary vessel segmentation model on the ultra-widefield retinal fundus dataset AV-WIDE, we recommend using AutoMorph on retinal fundus photographs with a 25° to 60° FOV, as all of the deep learning models are trained using images with FOV equals to 25° to 60°, and the preprocessing step is tailored for images with this FOV.
Evaluated on disc due to no cup annotation.