Table 2.

ROC and log loss results on the different test sets using the different transfer learning methods.

Method	Source	ROC AUC	Log Loss
Ensemble	combined	0.950 [0.925, 0.971]	0.135 [0.122, 0.148]
TL stomach	combined	0.953 [0.937, 0.966]	0.466 [0.426, 0.506]
TL ImageNet	combined	0.947 [0.923, 0.968]	0.555 [0.511, 0.594]
Stomach model	combined	0.896 [0.862, 0.923]	0.863 [0.814, 0.911]
TL stomach	Hospital 1	0.976 [0.936, 0.997]	0.236 [0.196, 0.271]
TL stomach	Hospital 2	0.964 [0.927, 0.991]	0.459 [0.347, 0.576]
TL stomach	Hospital 3	0.982 [0.966, 0.995]	0.195 [0.143, 0.244]
TL stomach	Hospital 4	0.964 [0.94, 0.983]	0.44 [0.36, 0.515]
TL stomach	Hospital 5	0.932 [0.886, 0.97]	0.949 [0.855, 1.081]
TL ImageNet	Hospital 1	0.903 [0.774, 0.993]	0.325 [0.284, 0.367]
TL ImageNet	Hospital 2	0.973 [0.939, 0.999]	0.613 [0.468, 0.72]
TL ImageNet	Hospital 3	0.983 [0.965, 0.997]	0.268 [0.209, 0.326]
TL ImageNet	Hospital 4	0.97 [0.948, 0.987]	0.48 [0.398, 0.549]
TL ImageNet	Hospital 5	0.923 [0.868, 0.969]	1.085 [0.972, 1.219]
Stomach model	Hospital 1	0.851 [0.739, 0.928]	1.055 [0.953, 1.167]
Stomach model	Hospital 2	0.865 [0.768, 0.951]	0.882 [0.722, 1.032]
Stomach model	Hospital 3	0.924 [0.864, 0.96]	0.607 [0.506, 0.716]
Stomach model	Hospital 4	0.923 [0.843, 0.981]	0.554 [0.475, 0.62]
Stomach model	Hospital 5	0.933 [0.881, 0.972]	1.2 [1.102, 1.326]