Translating prognostic quantification of c-MYC and BCL2 from tissue microarrays to whole slide images in diffuse large B-cell lymphoma using deep learning

Table 2 Results of WSI c-MYC and BCL2 scoring from models trained with TMA data

Stain	Pearson correlation	Sensitivity	Specificity
c-MYC	0.883 [0.860,0.902] 0.753 [0.696,0.800]	0.857 [0.801,0.907] 0.706 [0.638,0.771]	0.991 [0.980,1.000] 0.930 [0.902,0.956]
BCL2	0.749 [0.703,0.790] 0.765 [0.728,0.798]	0.856 [0.820,0.891] 0.855 [0.816,0.890]	0.719 [0.654,0.779] 0.690 [0.628,0.751]
Double-expressor	-	0.890 [0.636,1.000] 0.598 [0.273,0.913]	1.000 [1.000,1.000] 0.952 [0.873,1.000]

Pathologist 1 and 2 are both used as references for Pearson correlation, sensitivity, and specificity metrics and are indicated by two respective metrics reported in each cell. Pearson correlation, sensitivity, and specificity are reported along with 95% confidence intervals in brackets

ISSN: 1746-1596