Table 3 Performance of the STALNet model on Surgical Tasks across different encoders.
Task Name | ConvNeXt | ViT | SWIN V2 | |||
|---|---|---|---|---|---|---|
Accuracy | F1 Score | Accuracy | F1 Score | Accuracy | F1 Score | |
[01] Scope Setup | 0.99 ± 0.10 | 0.96 ± 0.04 | 0.99 ± 0.11 | 0.94 ± 0.05 | 0.99 ± 0.09 | 0.96 ± 0.04 |
[02] Instrument Setup | 1.00 ± 0.02 | 0.94 ± 0.06 | 1.00 ± 0.03 | 0.81 ± 0.19 | 1.00 ± 0.02 | 0.92 ± 0.08 |
[03] Site Setup | 1.00 ± 0.06 | 0.83 ± 0.17 | 1.00 ± 0.07 | 0.84 ± 0.16 | 1.00 ± 0.07 | 0.82 ± 0.18 |
[04] Pressure Setup | 0.99 ± 0.07 | 0.93 ± 0.07 | 0.99 ± 0.11 | 0.85 ± 0.15 | 0.99 ± 0.08 | 0.93 ± 0.07 |
[05] Landmarking | 0.99 ± 0.07 | 0.98 ± 0.02 | 0.98 ± 0.13 | 0.93 ± 0.06 | 0.99 ± 0.09 | 0.97 ± 0.03 |
[06] Mucosal Dissection | 0.98 ± 0.14 | 0.95 ± 0.04 | 0.94 ± 0.23 | 0.87 ± 0.10 | 0.98 ± 0.15 | 0.95 ± 0.04 |
[07] Submucosal Dissection | 0.98 ± 0.14 | 0.96 ± 0.03 | 0.96 ± 0.20 | 0.91 ± 0.06 | 0.98 ± 0.14 | 0.96 ± 0.03 |
[08] Circular Muscle Dissection | 0.99 ± 0.11 | 0.96 ± 0.04 | 0.96 ± 0.19 | 0.86 ± 0.12 | 0.98 ± 0.12 | 0.95 ± 0.04 |
[09] Longitudinal Muscle Dissection | 0.99 ± 0.11 | 0.97 ± 0.02 | 0.97 ± 0.17 | 0.93 ± 0.06 | 0.99 ± 0.11 | 0.97 ± 0.02 |
[10] Specimen Removal | 1.00 ± 0.03 | 0.98 ± 0.02 | 1.00 ± 0.04 | 0.96 ± 0.04 | 1.00 ± 0.02 | 0.99 ± 0.01 |
[11] Suturing | 0.99 ± 0.09 | 0.99 ± 0.00 | 0.98 ± 0.14 | 0.98 ± 0.01 | 0.99 ± 0.09 | 0.99 ± 0.00 |
[12] Scope removal | 1.00 ± 0.03 | 1.00 ± 0.00 | 1.00 ± 0.05 | 0.99 ± 0.01 | 1.00 ± 0.03 | 1.00 ± 0.00 |
