Research Article

[Retracted] Design of Optimal Deep Learning-Based Pancreatic Tumor and Nontumor Classification Model Using Computed Tomography Scans

Table 1

Comparative classification results analysis of ODL-PTNTC technique under varying training set (TS).

Training (%)ODL-PTNTCDS-WELMDS-KELMDS-ELM

Sensitivity
TS = 4099.8999.6996.9796.79
TS = 5098.5598.3598.2397.49
TS = 6098.3297.2098.0097.12
TS = 7097.5996.5397.0297.13
TS = 8099.3198.8997.8296.28
Average98.7398.1397.6196.96

Specificity
TS = 4096.9696.2296.8796.96
TS = 5097.2096.8497.1295.43
TS = 6098.8298.7095.7897.78
TS = 7097.5796.4697.1995.31
TS = 8098.1897.5397.6497.74
Average97.7597.1596.9296.64

Accuracy
TS = 4098.3498.2995.4497.46
TS = 5099.0897.6097.9298.93
TS = 6098.5098.4794.8794.59
TS = 7097.2196.5297.0294.32
TS = 8098.8697.4298.3796.90
Average98.4097.6696.7296.44

F-score
TS = 4098.9298.3998.5994.32
TS = 5099.0895.7698.8496.51
TS = 6099.8499.7097.1097.08
TS = 7098.2796.7195.5597.88
TS = 8097.9896.4094.3197.93
Average98.8297.3996.8896.74