. 2025 Aug 25;9:187. doi: 10.1038/s41538-025-00551-3

Table 5.

Comparative classification performance of ResNet34 and DSAF-ResNet model using different input modalities

Inputs	Models	Traning set			Test set
Inputs	Models	Accuracy(%)	Precision(%)	Recall(%)	Accuracy(%)	Precision(%)	Recall(%)
GLCM texture features	ResNet34	88.87	94.72	94.71	81.22	80.90	81.22
GLCM texture features	DSAF-ResNet	88.73	92.53	92.21	83.43	84.84	83.43
Spectral features	ResNet34	89.85	94.45	93.60	86.74	89.07	86.74
Spectral features	DSAF-ResNet	93.74	96.31	95.97	91.16	92.42	91.16
Fused spectral-texture features	ResNet34	94.44	97.61	97.50	92.27	92.80	92.27
Fused spectral-texture features	DSAF-ResNet	98.61	100	100	97.24	97.31	97.24