. Author manuscript; available in PMC: 2021 Dec 22.

Published in final edited form as: Phys Med Biol. 2020 Dec 22;65(24):245037. doi: 10.1088/1361-6560/abc812

Table 1.

Classification performance on training, validation, and testing datasets (values in bold font indicate better testing performance).

Dataset	Model	AUC	Accuracy	Sensitivity	Specificity
Training	Our model	0.97±0.004	0.97±0.004	0.98±0.005	0.94±0.008

Validation	Our model	0.87±0.084	0.84±0.059	0.88±0.062	0.82±0.098

Testing	Our model	0.91±0.008	0.85±0.011	0.90±0.007	0.77±0.024

	Multi-crop Net	0.89	0.83	0.81	0.83