MR Image Classification for Brain Tumor Texture Based on Pseudo-Label Learning and Optimized Feature Extraction

Table 5

Comparisons of classification results of different methods.

Feature extraction	Texture classification	Accuracy (%)	Time (s)
—	VGG	71.89	119
—	ResNet	79.33	108
—	DenseNet	81.39	105
—	ViT	86.67	197
—	CRNN	77.33	72
Autoencoder (DenseNet+ResNet)	CRNN	87.34	46
U-Net (DenseNet+ResNet)	CRNN	89.00	46
U-Net (DenseNet+ResNet)+CBAM	CRNN	94.23	49