Skip to main content
. 2022 Mar 2;7(2):100400. doi: 10.1016/j.esmoop.2022.100400

Figure 5.

Figure 5

Test performance on biopsies.

(A) Test performance based on cohort-specific threshold, fixed threshold values and learned thresholds. Confusion matrices follow the same layout as in Figure 2. (B and C) Examples of biopsy samples from the Yorkshire cohort and corresponding detection maps based on the tile-wise detection of the deep learning classifier.

dMMR, mismatch repair deficiency; MSI, microsatellite instability; MSS, microsatellite stable; pMMR, proficient mismatch repair.