Table 4.

Comparison of evaluation results of the backbone model against the proposed model.

AI Model	Optimizer	Learning Rate/Loss Function	ACC	SEN	SPE	PRE	F1_Score	AUC
Backbone	Adam	${10}^{-4}$/Categorical smooth loss	0.95	0.91	0.97	0.91	0.91	0.94
Proposed			0.96	0.92	0.97	0.93	0.92	0.95
Backbone		${10}^{-3}/$Categorical smooth loss	0.94	0.88	0.96	0.89	0.88	0.92
Proposed			0.97	0.93	0.98	0.94	0.93	0.96
Backbone		${10}^{-4}$/Categorical cross-entropy	0.96	0.93	0.98	0.93	0.93	0.95
Proposed			0.98	0.96	0.97	0.96	0.96	0.97
Backbone		${10}^{-3}/$Categorical cross-entropy	0.84	0.67	0.89	0.78	0.65	0.78
Proposed			0.98	0.95	0.99	0.96	0.95	0.97
Backbone	SGD	${10}^{-4}$/Categorical smooth loss	0.94	0.88	0.96	0.89	0.88	0.92
Proposed			0.94	0.88	0.96	0.89	0.88	0.92
Backbone		${10}^{-3}/$Categorical smooth loss	0.94	0.88	0.96	0.90	0.88	0.92
Proposed			0.97	0.94	0.98	0.94	0.94	0.96
Backbone		${10}^{-4}$/Categorical cross-entropy	0.94	0.89	0.96	0.90	0.89	0.92
Proposed			0.95	0.89	0.96	0.91	0.90	0.93
Backbone		${10}^{-3}/$Categorical cross-entropy	0.70	0.40	0.80	0.58	0.32	0.60
Proposed			0.95	0.89	0.96	0.92	0.89	0.93