Table 2 Overall distribution of the diagnostic classes from the residual CNNs and the independent neuropathologist with the inter-rater agreement between CNNs correct predictions and the neuropathologist (NP)
NP | CNN 1 | CNN 2 | CNN 3 | ||
|---|---|---|---|---|---|
SRH images | n = 592 | ||||
(All) | 100% | ||||
Tumor | 462 (78.0%) | 459 (77.5%) | 456 (77%) | 469 (79.2%) | |
Non-tumor | 113 (19.1%) | 115 (19.4%) | 117 (19.8%) | 110 (18.6%) | |
Low quality | 17 (2.9%) | 18 (3%) | 19 (3.2%) | 13 (2.2%) | |
SRH images (three random areas) | n = 402 | ||||
(Ground truth) | |||||
Tumor | 326 (100%) | 297 (91.1%) | 298 (91.4%) | 305 (95.0%) | |
Non-tumor | 67 (100%) | 46 (68.7%) | 48 (71.6%) | 49 (73.1%) | |
Low quality | 9 (100%) | 5 (55.6%) | 5 (55.6%) | 6 (66.7%) |