Table 6 Comparative analysis performance metrics (Accuracy, sensitivity (SEN), F1-mesure, and specificity (SPC)) while using different classifiers with ResNet-50.
From: A novel neuroimaging based early detection framework for alzheimer disease using deep learning
Dataset | Classifiers along with ResNet-50 | Acc (%) | SEN (%) | F1-score (%) | SPC (%) |
|---|---|---|---|---|---|
ADNI | Softmax | 99.87 | 99.44 | 99.29 | 99.3 |
VGG-16 | 98.64 | 96.91 | 95.88 | 98.21 | |
reLU | 96.19 | 94.5 | 92.77 | 95.6 | |
Sigmoid | 92.35 | 90.1 | 89.86 | 90.08 | |
SVM | 90.49 | 88.33 | 88.4 | 88.3 | |
RF | 88.31 | 86.58 | 86 | 85.12 |
