Performance of three different segmentation models based on SLD and SPB
| SM1 | mIoU | mHD (mm) | mPA |
| SLD | 0.8735 | 0.2530 | 0.9479 |
| SPB | 0.7781 | 0.3507 | 0.8889 |
| SM2 | |||
| SLD | 0.5768 | 0.8215 | 0.7422 |
| SPB | 0.6784 | 0.5556 | 0.8317 |
| SM3 | |||
| SLD | 0.7299 | 0.3122 | 0.8235 |
| SPB | 0.8169 | 0.3139 | 0.9259 |
SM1, training with SLD; SM2, training with SPB; SM3, training with SLD and SPB.
mHD, mean hausdorff distance; mIoU, mean intersection over union; mPA, mean pixel accuracy; SLD, slit-lamp image dataset; SPB, smartphone-based dataset.