Table 8.
Benchmarking current research against previous studies.
| Authors | Artery Segment | DL Model | #Patients/#Images | Results | Bias Identified |
|---|---|---|---|---|---|
| Zhou et al. [66] | ICA, CCA | UNet++ | N1 = 144/510 N2 = 497/638 |
TPA error: 5.55 ± 4.34 mm2 | Data selection, model selection, validation bias |
| Jain et al. [68] | ICA | UNet, UNet+, SegNet, SegNet-UNet, SegNet-UNet+, | N = 97/970 | PA error 3.49 mm2 for SDL; 4.21 mm2 for HDL | Data selection bias |
| Jain et al. [78] | CCA | UNet | N1 = 379 N2 = 300 |
FoM of 70.96 and 91.14 (unseen) against 97.57, 88.89, and 99.14 (seen) | Validation bias |
| Jain et al. [73] | CCA | UNet, SegNet-UNet, AtheroEdge 2.0 | N1 = 379 | PA error HDL = 8 mm2 SDL = 9.9 mm2 AtheroEdge 2.0 = 9.6 mm2 |
Data selection bias, racial bias |
| Proposed method | ICA, CCA | UNet, UNet++, UNet3P, Attention-UNet | N1 = 970; N2 = 379; N3 = 300 |
CC: 0.99 and 0.96 for ICA and CCA experiments | Free from data selection, racial, and validation biases |