IRR-Net: A Joint Learning Framework for Image Reconstruction and Recognition of Photoacoustic Tomography

Table 6

Evaluation metrics for binary classification and multiclass classification before and after data augmentation in the simulation study.

Data set	Binary classification				Multiclass classification
	Acc	Sens	Spec	F1 score	Acc				F1 score
					Cal	FC	LP	MC
Original data set	0.9330	0.9012	0.9467	0.9310	0.8274	0.8173	0.8168	0.8108	0.8569
Augmented data set	0.9474	0.9324	0.9524	0.9572	0.9191	0.9089	0.9161	0.8702	0.8878