Table 9.

Portability tests on the public dataset (Cohen et al., 2020b). MAE and its SD are listed for both reporting radiologist $R_j$ and BS-Net-HA. The network has been used in three training conditions: (1) as is, originally trained on the Brixia COVID-19 dataset (full), (2) fine-tuned on the public dataset (subset, fine-tuning), and (3) completely retrained, classification part only, on the public dataset (subset, from scratch).

		Test	A	B	C	D	E	F	Avg. on regions	Global score
Radiologist $R_j$	MEr	full	0.135	0.182	0.156	0.115	0.177	0.021	0.131	0.786
		subset	0.149	0.234	0.191	0.000	0.191	0.021	0.131	0.787
BS-Net-HA		full	0.177	$-$0.167	$-$0.177	0.167	$-$0.208	$-$0.651	$-$0.143	$-$0.859
		subset	0.125	$-$0.104	$-$0.188	0.167	$-$0.063	$-$0.583	$-$0.108	$-$0.646
* from scratch		subset	0.208	0.396	0.104	0.250	0.042	0.063	0.177	1.063
* fine-tuning		subset	0.146	0.167	$-$0.042	0.229	0.167	$-$0.208	0.076	0.458
Radiologist	MAE	full	0.396	0.401	0.438	0.333	0.396	0.469	0.405	1.974
		subset	0.404	0.447	0.489	0.340	0.362	0.447	0.415	1.851
BS-Net-HA		full	0.521	0.438	0.552	0.385	0.438	0.776	0.518	2.214
		subset	0.458	0.479	0.521	0.375	0.479	0.625	0.490	2.396
* from scratch		subset	0.375	0.646	0.604	0.458	0.542	0.479	0.517	2.188
* fine-tuning		subset	0.479	0.500	0.500	0.354	0.458	0.500	0.465	2.000