Skip to main content

Table 3 Contingency table of the number of correctly and incorrectly classified images from the deep learning network

From: Deep learning networks find unique mammographic differences in previous negative mammograms between interval and screen-detected cancers: a case-case study

Number (Percent) Predicted Screened Predicted Interval Total
Actual Screened 134/173 (77.4%) 39/173 (22.5%) 173
Actual Interval 48/182 (26.4%) 134/182 (73.6%) 182
Total 182 173