Table 1 Results comparing different CNN architectures for our proposed model. ShuffleNet demonstrates superior performance across all evaluated metrics. All values are presented as the average (Mean) with a measure of variability (Standard Deviation, SD). Significant values are in bold.
From: Precise grading of non-muscle invasive bladder cancer with multi-scale pyramidal CNN
Models | Sensitivity % | Specificity % | Accuracy % | F1-Score % |
|---|---|---|---|---|
Proposed (ShuffleNet) | 94.47 ± 0.93 | 94.03 ± 0.95 | 94.25 ± 0.70 | 94.29 ± 0.70 |
Resnet-18 | 93.46 ± 0.99 | 91.57 ± 0.94 | 92.52 ± 0.68 | 92.61 ± 0.67 |
Pan et al.13 | 91.73 ± 1.13 | 90.21 ± 1.18 | 90.97 ± 0.81 | 91.07 ± 0.80 |
Slotman et al.27 | 93.37 ± 2.16 | 91.46 ± 1.99 | 92.42 ± 1.67 | 92.51 ± 1.68 |
