Table 3 Comparative outcome of the FTLMO-BILCCD technique with existing models19,36]– [37.
Approach | \(\:\varvec{A}\varvec{c}\varvec{c}{\varvec{u}}_{\varvec{y}}\) | \(\:\varvec{P}\varvec{r}\varvec{e}{\varvec{c}}_{\varvec{n}}\) | \(\:\varvec{R}\varvec{e}\varvec{c}{\varvec{a}}_{\varvec{l}}\) | \(\:{\varvec{F}1}_{\varvec{s}\varvec{c}\varvec{o}\varvec{r}\varvec{e}}\) |
|---|---|---|---|---|
PortNet | 92.40 | 95.92 | 92.01 | 95.09 |
ResNet | 98.07 | 94.53 | 97.12 | 91.93 |
Xception | 95.40 | 97.75 | 96.40 | 91.18 |
MobileNetV2 | 91.59 | 95.84 | 94.56 | 93.95 |
CancerDetecNN V5 | 94.50 | 95.49 | 93.72 | 94.07 |
LCGANT Framework | 90.01 | 93.23 | 93.24 | 90.71 |
KPCA-CNN | 94.81 | 92.71 | 94.91 | 93.02 |
CNN + VGG19 | 96.16 | 98.37 | 97.14 | 91.72 |
AlexNet | 92.17 | 96.37 | 95.32 | 94.66 |
MFF-CNN | 95.03 | 96.15 | 94.49 | 94.75 |
FTLMO-BILCCD | 99.16 | 97.89 | 97.89 | 97.89 |
