Fig. 5: Visualization of uncertainty and confidence in a validation slide.

a One representative adenocarcinoma from the CPTAC evaluation dataset is shown, outlined with a pathologist-annotated ROI for reference only. Predictions were generated for all tiles from this whole-slide image excluding only background whitespace. Tile-level predictions from a model trained on the full TCGA dataset is shown in the top-right, with purple indicating prediction near 0 (consistent with the correct diagnosis of adenocarcinoma), and green indicating predictions near 1 (squamous cell carcinoma). Tile-level uncertainty is shown in the middle-right panel. The bottom right shows only high-confidence tile-level predictions using the predetermined uncertainty threshold, demonstrating that virtually all high-confidence predictions are consistent with the correct diagnosis. b Twenty-five of the lowest confidence tiles are shown on the left, and the 25 highest confidence tiles are shown on the right. All high-confidence tiles show clear adenocarcinoma morphology. Glandular structures are dominant among these tiles, although tiles I2 and J2 appear lepidic in nature, and H3 shows micropapillary morphology. In contrast, the majority of low-confidence tiles lack clear glandular structures. Lepidic morphology is seen in B4, C4, D5, and E5, and micropapillary structures can be found in E1, C2, B3, C4, D4, and E4. All image tiles have a width of 302 μm.