Table 3 Gender classification results for the ADNI1, ADNI2, PPMI, and CALSNIC2 datasets.
From: Effects of MRI scanner manufacturers in classification tasks with deep learning models
Scanner manufacturer | DL models | ADNI1 | ADNI2 | PPMI | CALSNIC2 | ||||
|---|---|---|---|---|---|---|---|---|---|
Acc | F1-score | Acc | F1-score | Acc | F1-score | Acc | F1-score | ||
GE | ResNet | 0.92 | 0.93 | 0.93 | 0.94 | 0.93 | 0.92 | 0.92 | 0.92 |
ShuffleNetV2 | 0.95 | 0.94 | 0.92 | 0.93 | 0.89 | 0.90 | 0.96 | 0.96 | |
MobileNetV2 | 0.92 | 0.93 | 0.91 | 0.90 | 0.88 | 0.89 | 0.92 | 0.92 | |
Siemens | ResNet | 0.94 | 0.94 | 0.92 | 0.91 | 0.90 | 0.90 | 0.91 | 0.90 |
ShuffleNetV2 | 0.94 | 0.93 | 0.97 | 0.95 | 0.94 | 0.92 | 0.92 | 0.92 | |
MobileNetV2 | 0.90 | 0.89 | 0.91 | 0.90 | 0.88 | 0.88 | 0.90 | 0.91 | |
Philips | ResNet | 0.92 | 0.91 | 0.90 | 0.90 | 0.86 | 0.87 | 0.95 | 0.94 |
ShuffleNetV2 | 0.93 | 0.93 | 0.90 | 0.88 | 0.85 | 0.84 | 0.94 | 0.94 | |
MobileNetV2 | 0.90 | 0.89 | 0.92 | 0.93 | 0.84 | 0.83 | 0.93 | 0.92 | |